Diagnostics

10 pages, 1170 KiB

Open AccessArticle

Loss of DUSP4 Expression as a Prognostic Biomarker in Clear Cell Renal Cell Carcinoma

by Seongsik Bang, Seungyun Jee, Hwangkyu Son, Young Chan Wi, Hyunsung Kim, Hosub Park, Jaekyung Myung, Su-Jin Shin and Seung Sam Paik

Diagnostics 2021, 11(10), 1939; https://doi.org/10.3390/diagnostics11101939 - 19 Oct 2021

Cited by 3 | Viewed by 2357

Abstract

Dual-specificity protein phosphatase 4 (DUSP4) is a negative regulator of mitogen-activated protein kinases. The prognostic impact of DUSP4 expression in renal cell carcinoma is not well studied. Therefore, we evaluated the clinicopathological implications of DUSP4 expression in clear cell renal cell carcinoma by [...] Read more.

Dual-specificity protein phosphatase 4 (DUSP4) is a negative regulator of mitogen-activated protein kinases. The prognostic impact of DUSP4 expression in renal cell carcinoma is not well studied. Therefore, we evaluated the clinicopathological implications of DUSP4 expression in clear cell renal cell carcinoma by performing immunohistochemistry (IHC). The clinical outcome according to DUSP4 expression was evaluated through survival analyses, and the association between mRNA expression and prognosis was confirmed by online analysis (Kaplan–Meier plotter). Loss of DUSP4 expression was noted in most histological subtypes of renal cell carcinoma. Loss of DUSP4 expression in clear cell renal cell carcinoma was significantly correlated with old age (p = 0.033), high histologic grade (p < 0.001), tumor necrosis (p < 0.001), and high pT category (p < 0.001). In survival analysis, loss of DUSP4 expression was associated with poor clinical outcomes in cancer-specific survival and recurrence-free survival (p = 0.010 and p = 0.007, respectively). Upon TCGA data analysis, patients with low DUSP4 mRNA expression showed a shorter overall survival (p = 0.023). These results suggest that loss of DUSP4 expression can be used as a potential biomarker for predicting clinical outcomes in clear cell renal cell carcinoma patients. Full article

(This article belongs to the Collection Biomarkers in Medicine)

► Show Figures

Figure 1

12 pages, 1473 KiB

Open AccessReview

The Role of Bronchoscopy in the Diagnosis and Management of Patients with SARS-Cov-2 Infection

by Davide Biondini, Marco Damin, Martina Bonifazi, Elisabetta Cocconcelli, Umberto Semenzato, Paolo Spagnolo, Stefano Gasparini, Marina Saetta and Elisabetta Balestro

Diagnostics 2021, 11(10), 1938; https://doi.org/10.3390/diagnostics11101938 - 19 Oct 2021

Cited by 4 | Viewed by 5592

Abstract

Bronchoscopy has several major diagnostic and therapeutic indications in pulmonology. However, it is an aerosol-generating procedure that places healthcare providers at an increased risk of infection. Now more than ever, during the spread of the coronavirus disease 2019 (COVID-19) pandemic, the infectious risk [...] Read more.

Bronchoscopy has several major diagnostic and therapeutic indications in pulmonology. However, it is an aerosol-generating procedure that places healthcare providers at an increased risk of infection. Now more than ever, during the spread of the coronavirus disease 2019 (COVID-19) pandemic, the infectious risk during bronchoscopy is significantly raised, and for this reason its role in diagnostic management is debated. In this review, we summarized current evidence regarding the indications for bronchoscopy and the measures that should be applied to decrease risk exposure. Indeed, seeing the long-lasting period of the pandemic, resuming standard of care for all patients is required. Full article

(This article belongs to the Special Issue Multidisciplinary Approaches to Manage COVID-19: From Surveillance to Diagnosis)

► Show Figures

Figure 1

22 pages, 5605 KiB

Open AccessArticle

Differences in Dynamics of Lung Computed Tomography Patterns between Survivors and Deceased Adult Patients with COVID-19

by Gevorg B. Akopyan, Alexander B. Berdalin, Ilya L. Gubskiy and Vladimir G. Lelyuk

Diagnostics 2021, 11(10), 1937; https://doi.org/10.3390/diagnostics11101937 - 19 Oct 2021

Cited by 2 | Viewed by 2377

Abstract

This study’s aim was to investigate CT (computed tomography) pattern dynamics differences within surviving and deceased adult patients with COVID-19, revealing new prognostic factors and reproducing already known data with our patients’ cohort: 635 hospitalized patients (55.3% of them were men, 44.7%—women), of [...] Read more.

This study’s aim was to investigate CT (computed tomography) pattern dynamics differences within surviving and deceased adult patients with COVID-19, revealing new prognostic factors and reproducing already known data with our patients’ cohort: 635 hospitalized patients (55.3% of them were men, 44.7%—women), of which 87.3% had a positive result of RT-PCR (reverse transcription-polymerase chain reaction) at admission. The number of deaths was 53 people (69.8% of them were men and 30.2% were women). In total, more than 1500 CT examinations were performed on patients, using a GE Optima CT 660 computed tomography (General Electric Healthcare, Chicago, IL, USA). The study was performed at hospital admission, the frequency of repetitive scans further varied based on clinical need. The interpretation of the imaging data was carried out by 11 radiologists with filling in individual registration cards that take into account the scale of the lesion, the location, contours, and shape of the foci, the dominating types of changes, as well as the presence of additional findings and the dynamics of the process—a total of 45 parameters. Statistical analysis was performed using the software packages SPSS Statistics version 23.0 (IBM, Armonk, NY, USA) and R software version 3.3.2. For comparisons in pattern dynamics across hospitalization we used repeated measures general linear model with outcome and disease phase as factors. The crazy paving pattern, which is more common and has a greater contribution to the overall CT picture in different phases of the disease in deceased patients, has isolated prognostic significance and is probably a reflection of faster dynamics of the process with a long phase of progression of pulmonary parenchyma damage with an identical trend of changes in the scale of the lesion (as recovered) in this group of patients. Already known data on typical pulmonological CT manifestations of infection, frequency of occurrence, and the prognostic significance of the scale of the lesion were reproduced, new differences in the dynamics of the process between recovered and deceased adult patients were also found that may have prognostic significance and can be reflected in clinical practice. Full article

(This article belongs to the Section Medical Imaging and Theranostics)

► Show Figures

Figure 1

25 pages, 16910 KiB

Open AccessArticle

Brain Cancer Prediction Based on Novel Interpretable Ensemble Gene Selection Algorithm and Classifier

by Abdulqader M. Almars, Majed Alwateer, Mohammed Qaraad, Souad Amjad, Hanaa Fathi, Ayda K. Kelany, Nazar K. Hussein and Mostafa Elhosseini

Diagnostics 2021, 11(10), 1936; https://doi.org/10.3390/diagnostics11101936 - 19 Oct 2021

Cited by 5 | Viewed by 2749

Abstract

The growth of abnormal cells in the brain causes human brain tumors. Identifying the type of tumor is crucial for the prognosis and treatment of the patient. Data from cancer microarrays typically include fewer samples with many gene expression levels as features, reflecting [...] Read more.

The growth of abnormal cells in the brain causes human brain tumors. Identifying the type of tumor is crucial for the prognosis and treatment of the patient. Data from cancer microarrays typically include fewer samples with many gene expression levels as features, reflecting the curse of dimensionality and making classifying data from microarrays challenging. In most of the examined studies, cancer classification (Malignant and benign) accuracy was examined without disclosing biological information related to the classification process. A new approach was proposed to bridge the gap between cancer classification and the interpretation of the biological studies of the genes implicated in cancer. This study aims to develop a new hybrid model for cancer classification (by using feature selection mRMRe as a key step to improve the performance of classification methods and a distributed hyperparameter optimization for gradient boosting ensemble methods). To evaluate the proposed method, NB, RF, and SVM classifiers have been chosen. In terms of the AUC, sensitivity, and specificity, the optimized CatBoost classifier performed better than the optimized XGBoost in cross-validation 5, 6, 8, and 10. With an accuracy of

0.91 \pm 0.12

, the optimized CatBoost classifier is more accurate than the CatBoost classifier without optimization, which is

0.81 \pm 0.24

. By using hybrid algorithms, SVM, RF, and NB automatically become more accurate. Furthermore, in terms of accuracy, SVM and RF (

0.97 \pm 0.08

) achieve equivalent and higher classification accuracy than NB (

0.91 \pm 0.12

). The findings of relevant biomedical studies confirm the findings of the selected genes. Full article

(This article belongs to the Special Issue Computer-Assisted Functional Diagnostics)

► Show Figures

Figure 1

16 pages, 16714 KiB

Open AccessArticle

MAGnitude-Image-to-Complex K-space (MAGIC-K) Net: A Data Augmentation Network for Image Reconstruction

by Fanwen Wang, Hui Zhang, Fei Dai, Weibo Chen, Chengyan Wang and He Wang

Diagnostics 2021, 11(10), 1935; https://doi.org/10.3390/diagnostics11101935 - 19 Oct 2021

Cited by 2 | Viewed by 2243

Abstract

Deep learning has demonstrated superior performance in image reconstruction compared to most conventional iterative algorithms. However, their effectiveness and generalization capability are highly dependent on the sample size and diversity of the training data. Deep learning-based reconstruction requires multi-coil raw k-space data, [...] Read more.

Deep learning has demonstrated superior performance in image reconstruction compared to most conventional iterative algorithms. However, their effectiveness and generalization capability are highly dependent on the sample size and diversity of the training data. Deep learning-based reconstruction requires multi-coil raw k-space data, which are not collected by routine scans. On the other hand, large amounts of magnitude images are readily available in hospitals. Hence, we proposed the MAGnitude Images to Complex K-space (MAGIC-K) Net to generate multi-coil k-space data from existing magnitude images and a limited number of required raw k-space data to facilitate the reconstruction. Compared to some basic data augmentation methods applying global intensity and displacement transformations to the source images, the MAGIC-K Net can generate more realistic intensity variations and displacements from pairs of anatomical Digital Imaging and Communications in Medicine (DICOM) images. The reconstruction performance was validated in 30 healthy volunteers and 6 patients with different types of tumors. The experimental results demonstrated that the high-resolution Diffusion Weighted Image (DWI) reconstruction benefited from the proposed augmentation method. The MAGIC-K Net enabled the deep learning network to reconstruct images with superior performance in both healthy and tumor patients, qualitatively and quantitatively. Full article

(This article belongs to the Section Medical Imaging and Theranostics)

► Show Figures

Figure 1

12 pages, 2085 KiB

Open AccessArticle

Keratoconus Diagnostic and Treatment Algorithms Based on Machine-Learning Methods

by Boris Malyugin, Sergej Sakhnov, Svetlana Izmailova, Ernest Boiko, Nadezhda Pozdeyeva, Lyubov Axenova, Kirill Axenov, Aleksej Titov, Anna Terentyeva, Tamriko Zakaraiia and Viktoriya Myasnikova

Diagnostics 2021, 11(10), 1933; https://doi.org/10.3390/diagnostics11101933 - 19 Oct 2021

Cited by 15 | Viewed by 3444

Abstract

The accurate diagnosis of keratoconus, especially in its early stages of development, allows one to utilise timely and proper treatment strategies for slowing the progression of the disease and provide visual rehabilitation. Various keratometry indices and classifications for quantifying the severity of keratoconus [...] Read more.

The accurate diagnosis of keratoconus, especially in its early stages of development, allows one to utilise timely and proper treatment strategies for slowing the progression of the disease and provide visual rehabilitation. Various keratometry indices and classifications for quantifying the severity of keratoconus have been developed. Today, many of them involve the use of the latest methods of computer processing and data analysis. The main purpose of this work was to develop a machine-learning-based algorithm to precisely determine the stage of keratoconus, allowing optimal management of patients with this disease. A multicentre retrospective study was carried out to obtain a database of patients with keratoconus and to use machine-learning techniques such as principal component analysis and clustering. The created program allows for us to distinguish between a normal state; preclinical keratoconus; and stages 1, 2, 3 and 4 of the disease, with an accuracy in terms of the AUC of 0.95 to 1.00 based on keratotopographer readings, relative to the adapted Amsler–Krumeich algorithm. The predicted stage and additional diagnostic criteria were then used to create a standardised keratoconus management algorithm. We also developed a web-based interface for the algorithm, providing us the opportunity to use the software in a clinical environment. Full article

(This article belongs to the Special Issue Medical Optical Imaging: Current Diagnostics, Therapeutic and Surgical Applications in Ophthalmology)

► Show Figures

Figure 1

Figure 1
Study design. Full article ">Figure 2
Distribution of the train data on the 2-D plane after the PCA method and coloured according to the stages of keratoconus. Blue—normal; dark purple—preclinical keratoconus; light purple—stage 1; pink—stage 2; orange—stage 3; yellow—stage 4. Full article ">Figure 3
(A). Distribution of the test data on the 2-D plane after the PCA method and coloured according to the adopted AK algorithm stages. Blue—normal; dark purple—preclinical keratoconus; light purple—stage 1; pink—stage 2; orange—stage 3; yellow—stage 4. (B). Distribution of the test data after the QDA method and coloured according to the predicted stages of keratoconus. Full article ">Figure 4
Result of ROC analysis and calculation of AUC (area) for prediction of keratoconus stages from test data relative to the adapted AK algorithm. Full article ">Figure 5
Graphical interface of the software for determining the stage of keratoconus, as well as the indications for surgical intervention: (A)—field for manual input of parameters to determine stage of keratoconus; (B)—field for manual input of parameters to determine patient management tactics; (C)—graphical representation of model including data distribution after PCA and QDA fit (coloured points) as well as new patient data (red points) after PCA and QDA predictions; (D)—treatment algorithm result. Full article ">

15 pages, 1674 KiB

Open AccessArticle

Visual Evaluation of Image Quality of a Low Dose 2D/3D Slot Scanner Imaging System Compared to Two Conventional Digital Radiography X-ray Imaging Systems

by Ahmed Jibril Abdi, Bo Mussmann, Alistair Mackenzie, Oke Gerke, Gitte Maria Jørgensen, Thor Eriksen Bechsgaard, Janni Jensen, Lone Brunshøj Olsen and Poul Erik Andersen

Diagnostics 2021, 11(10), 1932; https://doi.org/10.3390/diagnostics11101932 - 19 Oct 2021

Cited by 6 | Viewed by 4207 | Correction

Abstract

The purpose of this study was to assess the image quality of the low dose 2D/3D slot scanner (LDSS) imaging system compared to conventional digital radiography (DR) imaging systems. Visual image quality was assessed using the visual grading analysis (VGA) method. This method [...] Read more.

The purpose of this study was to assess the image quality of the low dose 2D/3D slot scanner (LDSS) imaging system compared to conventional digital radiography (DR) imaging systems. Visual image quality was assessed using the visual grading analysis (VGA) method. This method is a subjective approach that uses a human observer to evaluate and optimise radiographic images for different imaging technologies. Methods and materials: ten posterior-anterior (PA) and ten lateral (LAT) images of a chest anthropomorphic phantoms and a knee phantom were acquired by an LDSS imaging system and two conventional DR imaging systems. The images were shown in random order to three (chest) radiologists and three experienced (knee) radiographers, who scored the images against a number of criteria. Inter- and intraobserver agreement was assessed using Fleiss’ kappa and weighted kappa. Results: the statistical comparison of the agreement between the observers showed good interobserver agreement, with Fleiss’ kappa coefficients of 0.27–0.63 and 0.23–0.45 for the chest and knee protocols, respectively. Comparison of intraobserver agreement also showed good agreement with weighted kappa coefficients of 0.27–0.63 and 0.23–0.45 for the chest and knee protocols, respectively. The LDSS imaging system achieved significantly higher VGA image quality compared to the DR imaging systems in the AP and LAT chest protocols (p < 0.001). However, the LDSS imaging system achieved lower image quality than one DR system (p ≤ 0.016) and equivalent image quality to the other DR systems (p ≤ 0.27) in the knee protocol. The LDSS imaging system achieved effective dose savings of 33–52% for the chest protocol and 30–35% for the knee protocol compared with DR systems. Conclusions: this work has shown that the LDSS imaging system has the potential to acquire chest and knee images at diagnostic quality and at a lower effective dose than DR systems. Full article

(This article belongs to the Section Medical Imaging and Theranostics)

► Show Figures

Figure 1

9 pages, 1526 KiB

Open AccessCase Report

Dominating Cause of Pulmonary Hypertension May Change Over Time—Diagnostic and Therapeutic Considerations in a Patient with Pulmonary Hypertension Due to Rheumatoid Arthritis with Lung Involvement

by Monika Szturmowicz, Monika Franczuk, Małgorzata Ewa Jędrych, Dorota Wyrostkiewicz, Karina Oniszh, Szymon Darocha, Krzysztof Kasperowicz and Marcin Kurzyna

Diagnostics 2021, 11(10), 1931; https://doi.org/10.3390/diagnostics11101931 - 19 Oct 2021

Cited by 5 | Viewed by 2896

Abstract

Chronic lung diseases are one of the most frequent causes of pulmonary hypertension (PH). The diagnostic challenge is to differentiate PH due to chronic lung disease from pulmonary arterial hypertension (PAH) with coexisting chronic lung disease. Moreover, the dominating cause of PH may [...] Read more.

Chronic lung diseases are one of the most frequent causes of pulmonary hypertension (PH). The diagnostic challenge is to differentiate PH due to chronic lung disease from pulmonary arterial hypertension (PAH) with coexisting chronic lung disease. Moreover, the dominating cause of PH may change over time, requiring the implementation of new diagnostic procedures and new treatment modalities. We present a 68-year-old female, initially diagnosed with PH in the course of interstitial lung disease, with restrictive impairment of lung function. Therapy with immunosuppressive drugs resulted in significant clinical, radiological and functional improvement. However, five years later, arthritis symptoms developed, with PH worsening, despite stable lung disease. The patient was diagnosed with PAH in the course of rheumatoid arthritis. The introduction of sildenafil resulted in marked clinical and hemodynamic responses. Long-term survival (eleven years from PH onset and five years from PAH confirmation) has been achieved, and the patient remains in good functional condition. As the differential diagnosis of PH in patients with lung diseases is complex, the cooperation of pulmonologists and cardiologists is mandatory to obtain therapeutic success. Full article

(This article belongs to the Section Medical Imaging and Theranostics)

► Show Figures

Figure 1

10 pages, 1148 KiB

Open AccessArticle

Radial Basis Function for Breast Lesion Detection from MammoWave Clinical Data

by Soumya Prakash Rana, Maitreyee Dey, Riccardo Loretoni, Michele Duranti, Lorenzo Sani, Alessandro Vispa, Mohammad Ghavami, Sandra Dudley and Gianluigi Tiberi

Diagnostics 2021, 11(10), 1930; https://doi.org/10.3390/diagnostics11101930 - 18 Oct 2021

Cited by 17 | Viewed by 2996

Abstract

Recently, a novel microwave apparatus for breast lesion detection (MammoWave), uniquely able to function in air with 2 antennas rotating in the azimuth plane and operating within the band 1–9 GHz has been developed. Machine learning (ML) has been implemented to understand information [...] Read more.

Recently, a novel microwave apparatus for breast lesion detection (MammoWave), uniquely able to function in air with 2 antennas rotating in the azimuth plane and operating within the band 1–9 GHz has been developed. Machine learning (ML) has been implemented to understand information from the frequency spectrum collected through MammoWave in response to the stimulus, segregating breasts with and without lesions. The study comprises 61 breasts (from 35 patients), each one with the correspondent output of the radiologist’s conclusion (i.e., gold standard) obtained from echography and/or mammography and/or MRI, plus pathology or 1-year clinical follow-up when required. The MammoWave examinations are performed, recording the frequency spectrum, where the magnitudes show substantial discrepancy and reveals dissimilar behaviours when reflected from tissues with/without lesions. Principal component analysis is implemented to extract the unique quantitative response from the frequency response for automated breast lesion identification, engaging the support vector machine (SVM) with a radial basis function kernel. In-vivo feasibility validation (now ended) of MammoWave was approved in 2015 by the Ethical Committee of Umbria, Italy (N. 6845/15/AV/DM of 14 October 2015, N. 10352/17/NCAV of 16 March 2017, N 13203/18/NCAV of 17 April 2018). Here, we used a set of 35 patients. According to the radiologists conclusions, 25 breasts without lesions and 36 breasts with lesions underwent a MammoWave examination. The proposed SVM model achieved the accuracy, sensitivity, and specificity of 91%, 84.40%, and 97.20%. The proposed ML augmented MammoWave can identify breast lesions with high accuracy. Full article

(This article belongs to the Special Issue Advancement in Breast Diagnostic and Interventional Radiology)

► Show Figures

Figure 1

Figure 1
Proposed flow chart for the machine learning-based breast lesion detection. Full article ">Figure 2
MammoWave device with patient’s position and transmitting-receiving antenna positions. (a) Novel MammoWave device. (b) Transmitting and receiving antenna rotation positions. (c) Patient’s posture over MammoWave. (d) Antenna rotation around the breast. Full article ">Figure 3
NF and WF signal prediction results (accuracy, sensitivity, and specificity) obtained using real-parts of the MammoWave’s frequency response and <math display="inline"><semantics> <mrow> <mi>S</mi> <mi>V</mi> <msub> <mi>M</mi> <mrow> <mi>R</mi> <mi>B</mi> <mi>F</mi> </mrow> </msub> </mrow> </semantics></math>, applying different amounts of training data. Full article ">Figure 4
Percentage of variance obtained for 80 PCs measured from <math display="inline"><semantics> <mrow> <mi>R</mi> <mi>e</mi> <mi>a</mi> <msub> <mi>l</mi> <mrow> <mi>S</mi> <mn>21</mn> </mrow> </msub> </mrow> </semantics></math>. Full article ">Figure 5
NF and WF breast signal classification results considering PCs measured from <math display="inline"><semantics> <mrow> <mi>R</mi> <mi>e</mi> <mi>a</mi> <msub> <mi>l</mi> <mrow> <mi>S</mi> <mn>21</mn> </mrow> </msub> </mrow> </semantics></math> and employing SVM<math display="inline"><semantics> <msub> <mrow/> <mrow> <mi>R</mi> <mi>B</mi> <mi>F</mi> </mrow> </msub> </semantics></math>, (a) accuracy, (b) sensitivity, (c) specificity. Full article ">

12 pages, 2093 KiB

Open AccessArticle

Association of Cervical and Lumbar Paraspinal Muscle Composition Using Texture Analysis of MR-Based Proton Density Fat Fraction Maps

by Egon Burian, Edoardo A. Becherucci, Daniela Junker, Nico Sollmann, Tobias Greve, Hans Hauner, Claus Zimmer, Jan S. Kirschke, Dimitrios C. Karampinos, Karupppasamy Subburaj, Thomas Baum and Michael Dieckmeyer

Diagnostics 2021, 11(10), 1929; https://doi.org/10.3390/diagnostics11101929 - 18 Oct 2021

Cited by 4 | Viewed by 3160

Abstract

In this study, the associations of cervical and lumbar paraspinal musculature based on a texture analysis of proton density fat fraction (PDFF) maps were investigated to identify gender- and anatomical location-specific structural patterns. Seventy-nine volunteers (25 men, 54 women) participated in the present [...] Read more.

In this study, the associations of cervical and lumbar paraspinal musculature based on a texture analysis of proton density fat fraction (PDFF) maps were investigated to identify gender- and anatomical location-specific structural patterns. Seventy-nine volunteers (25 men, 54 women) participated in the present study (mean age ± standard deviation: men: 43.7 ± 24.6 years; women: 37.1 ± 14.0 years). Using manual segmentations of the PDFF maps, texture analysis was performed and texture features were extracted. A significant difference in the mean PDFF between men and women was observed in the erector spinae muscle (p < 0.0001), whereas the mean PDFF did not significantly differ in the cervical musculature and the psoas muscle (p > 0.05 each). Among others, Variance(global) and Kurtosis(global) showed significantly higher values in men than in women in all included muscle groups (p < 0.001). Not only the mean PDFF values (p < 0.001) but also Variance(global) (p < 0.001), Energy (p < 0.001), Entropy (p = 0.01), Homogeneity (p < 0.001), and Correlation (p = 0.037) differed significantly between the three muscle compartments. The cervical and lumbar paraspinal musculature composition seems to be gender-specific and has anatomical location-specific structural patterns. Full article

(This article belongs to the Section Medical Imaging and Theranostics)

► Show Figures

Figure 1

Figure 1
Segmentation example. (A,B) The segmented CE (left and right multifidus, semispinalis, and spinalis cervicis muscles (1)) at the level of C5. (C,D) The PS (2) and ES and the multifidus muscles (3) at the level of L4. Full article ">Figure 2
Representative color-coded PDFF maps. (A,C): 68-year-old female (PDFFCE = 22.9%, PDFFES = 40.0%, PDFFPS = 12.7%, BMI = 39.1 kg/m2). (B,D): 47-year-old male (PDFFCE = 23.4%, PDFFES = 14.8%, PDFFPS = 8.2%, BMI = 30.4 kg/m2). In the female subject, structural heterogeneity of the ES (C) is depicted exemplarily. PDFF, proton density fat fraction; CE, cervical muscles; ES, erector spinae muscles; PS, psoas muscles; BMI, body mass index. Full article ">Figure 3
Correlations r of mean PDFF measurements and TFs after adjustment for age and BMI. Shown are the TFs with the highest r for each muscle group. (A): Correlation between PDFFCE and the TF Correlation (r = 0.786; p < 0.001). (B): Correlation between PDFFES and the TF Variance (r = 0.863; p < 0.001). (C): Correlation between PDFFPS and the TF Homogeneity (r = 0.334; p = 0.03). r, Pearson correlation coefficient; PDFF, proton density fat fraction; TF, texture feature; BMI, body mass index; CE, cervical muscles; ES, erector spinae muscles; PS, psoas muscles. Full article ">

11 pages, 1381 KiB

Open AccessArticle

SERPINE2 Overexpression Is Associated with Poor Prognosis of Urothelial Carcinoma

by Hao-Wen Chuang, Kan-Tai Hsia, Jia-Bin Liao, Chih-Ching Yeh, Wei-Ting Kuo and Yi-Fang Yang

Diagnostics 2021, 11(10), 1928; https://doi.org/10.3390/diagnostics11101928 - 18 Oct 2021

Cited by 11 | Viewed by 2404

Abstract

Recent studies have reported that SERPINE2 contributes to the development of various cancers. However, its association with urothelial carcinoma (UC) remains unclear. In this study, data on urinary bladder UC (UBUC) cases from The Cancer Genome Atlas (TCGA) database were used to investigate [...] Read more.

Recent studies have reported that SERPINE2 contributes to the development of various cancers. However, its association with urothelial carcinoma (UC) remains unclear. In this study, data on urinary bladder UC (UBUC) cases from The Cancer Genome Atlas (TCGA) database were used to investigate the prognostic value of SERPINE2 mRNA expression. Then, SERPINE2 expression was analyzed with tissue microarrays constructed from 117 upper tract UC (UTUC) and 84 UBUC tissue specimens using immunohistochemical staining. Results were compared to clinicopathologic data by multivariate analysis. In the TCGA database, high SERPINE2 mRNA expression indicated a poor prognosis in patients with UBUC. Furthermore, Mann–Whitney U test showed that high SERPINE2 immunoexpression was significantly associated with adverse pathologic parameters including invasion, high grade, coexistence of UC in situ, and advanced pT stage (all p < 0.05, except for a marginal association with high-grade UBUC, p = 0.066). Kaplan–Meier analysis revealed that high SERPINE2 expression was associated with worse overall survival (OS; UTUC, p = 0.003; UBUC, p = 0.014) and disease-free survival (UTUC, p = 0.031; UBUC, p = 0.033). Moreover, multivariate analysis identified high SERPINE2 expression as an independent prognostic factor for OS (UTUC, p = 0.002; UBUC, p = 0.024). Taken together, our findings demonstrated that increased SERPINE2 expression is associated with adverse pathologic features and may serve as a prognostic biomarker for UC. Full article

(This article belongs to the Special Issue Advances in the Diagnosis and Management of Tumors/Cancers)

► Show Figures

Figure 1

Figure 1
Survival analysis using TCGA database plotted using Kaplan–Meier curves. The overall survival (A) and disease-free survival (B) curves comparing patients with high (red) and low (blue) SERPINE2 mRNA expressions were plotted. The log-rank test showed that high SERPINE2 mRNA expression predicted poor overall and disease-free survivals in bladder carcinoma. Full article ">Figure 2
SERPINE2 was upregulated in urothelial carcinoma tissues. Quantification of SERPINE2 immunoexpression in 75 paired urothelial carcinoma specimens and significance determined by the paired t-test. ***, p < 0.001. Full article ">Figure 3
Representative sections of the normal urothelium (A), low-grade urothelial carcinoma (UC) (B), and high-grade UC (C,D) stained with H&E and immunostained for SERPINE2 (E–H). SERPINE2 immunoreactivity to the normal urothelium, low-grade UC, and high-grade UC was observed as (E) negative, (F) weak (1+), (G) moderate (2+), and (H) strong (3+). Scale bar in (A), 100 µm. The scale bar applies to all panels. Full article ">Figure 4
(A,B) Overall survival and (C,D) disease-free survival rates according to SERPINE2 immunoreactivity in both upper tract and bladder urothelial carcinoma. Full article ">

16 pages, 1438 KiB

Open AccessArticle

Factors Influencing Concordance of PD-L1 Expression between Biopsies and Cytological Specimens in Non-Small Cell Lung Cancer

by Mohammed S. I. Mansour, Kim Hejny, Felicia Johansson, Joudy Mufti, Ante Vidis, Ulrich Mager, Annika Dejmek, Tomas Seidal and Hans Brunnström

Diagnostics 2021, 11(10), 1927; https://doi.org/10.3390/diagnostics11101927 - 18 Oct 2021

Cited by 8 | Viewed by 2401

Abstract

PD-L1 expression assessed by immunohistochemical staining is used for the selection of immunotherapy in non-small cell lung cancer (NSCLC). Appropriate validation of PD-L1 expression in cytology specimens is important as cytology is often the only diagnostic material in NSCLC. In a previous study [...] Read more.

PD-L1 expression assessed by immunohistochemical staining is used for the selection of immunotherapy in non-small cell lung cancer (NSCLC). Appropriate validation of PD-L1 expression in cytology specimens is important as cytology is often the only diagnostic material in NSCLC. In a previous study comprising two different cohorts of paired biopsies and cytological specimens, we found a fairly good cyto-histological correlation of PD-L1 expression in one, whereas only a moderate correlation was found in the other cohort. Therefore, that cohort with additional new cases was now further investigated for the impact of preanalytical factors on PD-L1 concordance in paired biopsies and cytological specimens. A total of 100 formalin-fixed paraffin-embedded cell blocks from 19 pleural effusions (PE), 17 bronchial brushes (BB), and 64 bronchoalveolar lavage (BAL) and concurrent matched biopsies from 80 bronchial biopsies and 20 transthoracic core biopsies from NSCLC patients were stained using the PD-L1 28-8 assay. Using the cutoffs ≥1%, ≥5%, ≥10%, and ≥50% positive tumour cells, the overall agreement between histology and cytology was 77–85% (κ 0.51–0.70) depending on the applied cutoff value. The concordance was better for BALs (κ 0.53–0.81) and BBs (κ 0.55–0.85) than for PEs (κ −0.16–0.48), while no difference was seen for different types of biopsies or histological tumour type. A high number of tumour cells (>500) in biopsies was associated with better concordance at the ≥50% cutoff. In conclusion, the study results suggest that PEs may be less suitable for evaluation of PD-L1 due to limited cyto-histological concordance, while a high amount of tumour cells in biopsies may be favourable when regarding cyto-histological PD-L1 concordance. Full article

(This article belongs to the Special Issue Cyto-Histopathological Correlations in Pathology Diagnostics)

► Show Figures

Figure 1

12 pages, 1937 KiB

Open AccessReview

Diagnostic Accuracy of Non-Invasive Imaging for Detection of Colonic Inflammation in Patients with Inflammatory Bowel Disease: A Systematic Review and Meta-Analysis

by Meshari T. Alshammari, Rebecca Stevenson, Buraq Abdul-Aema, Guangyong Zou, Vipul Jairath, Shellie Radford, Luca Marciani and Gordon W. Moran

Diagnostics 2021, 11(10), 1926; https://doi.org/10.3390/diagnostics11101926 - 18 Oct 2021

Cited by 13 | Viewed by 3377

Abstract

Endoscopy is the gold standard for objective assessment of colonic disease activity in inflammatory bowel disease (IBD). Non-invasive colonic imaging using bowel ultrasound (US), computed tomography (CT), and magnetic resonance imaging (MRI) may have a role in quantifying colonic disease activity. We reviewed [...] Read more.

Endoscopy is the gold standard for objective assessment of colonic disease activity in inflammatory bowel disease (IBD). Non-invasive colonic imaging using bowel ultrasound (US), computed tomography (CT), and magnetic resonance imaging (MRI) may have a role in quantifying colonic disease activity. We reviewed the diagnostic accuracy of these modalities for assessment of endoscopically or histopathologically defined colonic disease activity in IBD. We searched Embase, MEDLINE, and the Web of Science from inception to 20 September 2021. QUADAS-2 was used to evaluate the studies’ quality. A meta-analysis was performed using a bivariate model approach separately for MRI and US studies only, and summary receiver operating characteristic (ROC) curves were obtained. CT studies were excluded due to the absence of diagnostic test data. Thirty-seven studies were included. The mean sensitivity and specificity for MRI studies was 0.75 and 0.91, respectively, while for US studies it was 0.82 and 0.90, respectively. The area under the ROC curves (AUC) was 0.88 (95% CI, 0.82 to 0.93) for MRI, and 0.90 (95% CI, 0.75 to 1.00) for US. Both MRI and US show high diagnostic accuracy in the assessment of colonic disease activity in IBD patients. Full article

(This article belongs to the Special Issue Diagnostic Imaging of Gastrointestinal Diseases)

► Show Figures

Figure 1

8 pages, 259 KiB

Open AccessArticle

A Multivariate Model to Predict Chronic Heart Failure after Acute ST-Segment Elevation Myocardial Infarction: Preliminary Study

by Valentin Elievich Oleynikov, Elena Vladimirovna Averyanova, Anastasia Aleksandrovna Oreshkina, Nadezhda Valerievna Burko, Yulia Andreevna Barmenkova, Alena Vladimirovna Golubeva and Vera Aleksandrovna Galimskaya

Diagnostics 2021, 11(10), 1925; https://doi.org/10.3390/diagnostics11101925 - 18 Oct 2021

Cited by 2 | Viewed by 2398

Abstract

A multivariate model for predicting the risk of decompensated chronic heart failure (CHF) within 48 weeks after ST-segment elevation myocardial infarction (STEMI) has been developed and tested. Methods. The study included 173 patients with acute STEMI aged 51.4 (95% confidence interval (CI): 42–61) [...] Read more.

A multivariate model for predicting the risk of decompensated chronic heart failure (CHF) within 48 weeks after ST-segment elevation myocardial infarction (STEMI) has been developed and tested. Methods. The study included 173 patients with acute STEMI aged 51.4 (95% confidence interval (CI): 42–61) years. Two-dimensional (2D) speckle-tracking echocardiography (STE) has been performed on the 7th–9th days, and at the 12th, 24th, and 48th weeks after the index event with the analysis of volumetric parameters and values for global longitudinal strain (GLS), global circumferential strain (GCS), and global radial strain (GRS). A 24-h ECG monitoring (24 h ECG) of the electrocardiogram (ECG) to assess heart rate turbulence (HRT) has been performed on the 7th–9th days of STEMI. The study involved two stages of implementation. At the first stage, a multivariate model to assess the risk of CHF progression within 48 weeks after STEMI has been built on the basis of examination and follow-up data for 113 patients (group M). At the second stage, the performance of the model has been assessed based on a 48-week follow-up of 60 patients (group T). Results. A multivariate regression model for CHF progression in STEMI patients has been created based on the results of the first stage. It included the following parameters: HRT, left ventricular (LV) end-systolic dimension (ESD), and GLS. The contribution of each factor for the relative risk (RR) of decompensated CHF has been found: 3.92 (95% CI: 1.66–9.25) (p = 0.0018) for HRT; 1.04 (95% CI: 1.015–1.07) (p = 0.0027) for ESD; 0.9 (95% CI: 0.815–0.98) (p = 0.028) for GLS. The diagnostic efficiency of the proposed model has been evaluated at the second stage. It appeared to have a high specificity of 83.3%, a sensitivity of 95.8%, and a diagnostic accuracy of 93.3%. Conclusion. The developed model for predicting CHF progression within 48 weeks after STEMI has a high diagnostic efficiency and can be used in early stages of myocardial infarction to stratify the risk of patients. Full article

(This article belongs to the Special Issue Diagnosis and Management of Heart Failure)

16 pages, 2244 KiB

Open AccessReview

A Promising and Challenging Approach: Radiologists’ Perspective on Deep Learning and Artificial Intelligence for Fighting COVID-19

by Tianming Wang, Zhu Chen, Quanliang Shang, Cong Ma, Xiangyu Chen and Enhua Xiao

Diagnostics 2021, 11(10), 1924; https://doi.org/10.3390/diagnostics11101924 - 18 Oct 2021

Cited by 3 | Viewed by 3221

Abstract

Chest X-rays (CXR) and computed tomography (CT) are the main medical imaging modalities used against the increased worldwide spread of the 2019 coronavirus disease (COVID-19) epidemic. Machine learning (ML) and artificial intelligence (AI) technology, based on medical imaging fully extracting and utilizing the [...] Read more.

Chest X-rays (CXR) and computed tomography (CT) are the main medical imaging modalities used against the increased worldwide spread of the 2019 coronavirus disease (COVID-19) epidemic. Machine learning (ML) and artificial intelligence (AI) technology, based on medical imaging fully extracting and utilizing the hidden information in massive medical imaging data, have been used in COVID-19 research of disease diagnosis and classification, treatment decision-making, efficacy evaluation, and prognosis prediction. This review article describes the extensive research of medical image-based ML and AI methods in preventing and controlling COVID-19, and summarizes their characteristics, differences, and significance in terms of application direction, image collection, and algorithm improvement, from the perspective of radiologists. The limitations and challenges faced by these systems and technologies, such as generalization and robustness, are discussed to indicate future research directions. Full article

(This article belongs to the Section Machine Learning and Artificial Intelligence in Diagnostics)

► Show Figures

Figure 1

20 pages, 1921 KiB

Open AccessReview

Features of Mobile Apps for People with Autism in a Post COVID-19 Scenario: Current Status and Recommendations for Apps Using AI

by Ikram Ur Rehman, Drishty Sobnath, Moustafa M. Nasralla, Maria Winnett, Aamir Anwar, Waqar Asif and Hafiz Husnain Raza Sherazi

Diagnostics 2021, 11(10), 1923; https://doi.org/10.3390/diagnostics11101923 - 17 Oct 2021

Cited by 38 | Viewed by 9507

Abstract

The new ‘normal’ defined during the COVID-19 pandemic has forced us to re-assess how people with special needs thrive in these unprecedented conditions, such as those with Autism Spectrum Disorder (ASD). These changing/challenging conditions have instigated us to revisit the usage of telehealth [...] Read more.

The new ‘normal’ defined during the COVID-19 pandemic has forced us to re-assess how people with special needs thrive in these unprecedented conditions, such as those with Autism Spectrum Disorder (ASD). These changing/challenging conditions have instigated us to revisit the usage of telehealth services to improve the quality of life for people with ASD. This study aims to identify mobile applications that suit the needs of such individuals. This work focuses on identifying features of a number of highly-rated mobile applications (apps) that are designed to assist people with ASD, specifically those features that use Artificial Intelligence (AI) technologies. In this study, 250 mobile apps have been retrieved using keywords such as autism, autism AI, and autistic. Among 250 apps, 46 were identified after filtering out irrelevant apps based on defined elimination criteria such as ASD common users, medical staff, and non-medically trained people interacting with people with ASD. In order to review common functionalities and features, 25 apps were downloaded and analysed based on eye tracking, facial expression analysis, use of 3D cartoons, haptic feedback, engaging interface, text-to-speech, use of Applied Behaviour Analysis therapy, Augmentative and Alternative Communication techniques, among others were also deconstructed. As a result, software developers and healthcare professionals can consider the identified features in designing future support tools for autistic people. This study hypothesises that by studying these current features, further recommendations of how existing applications for ASD people could be enhanced using AI for (1) progress tracking, (2) personalised content delivery, (3) automated reasoning, (4) image recognition, and (5) Natural Language Processing (NLP). This paper follows the PRISMA methodology, which involves a set of recommendations for reporting systematic reviews and meta-analyses. Full article

(This article belongs to the Section Machine Learning and Artificial Intelligence in Diagnostics)

► Show Figures

Figure 1

11 pages, 1723 KiB

Open AccessArticle

Detection Accuracy and Latency of Colorectal Lesions with Computer-Aided Detection System Based on Low-Bias Evaluation

by Hiroaki Matsui, Shunsuke Kamba, Hideka Horiuchi, Sho Takahashi, Masako Nishikawa, Akihiro Fukuda, Aya Tonouchi, Natsumaro Kutsuna, Yuki Shimahara, Naoto Tamai and Kazuki Sumiyama

Diagnostics 2021, 11(10), 1922; https://doi.org/10.3390/diagnostics11101922 - 17 Oct 2021

Cited by 2 | Viewed by 2616

Abstract

We developed a computer-aided detection (CADe) system to detect and localize colorectal lesions by modifying You-Only-Look-Once version 3 (YOLO v3) and evaluated its performance in two different settings. The test dataset was obtained from 20 randomly selected patients who underwent endoscopic resection for [...] Read more.

We developed a computer-aided detection (CADe) system to detect and localize colorectal lesions by modifying You-Only-Look-Once version 3 (YOLO v3) and evaluated its performance in two different settings. The test dataset was obtained from 20 randomly selected patients who underwent endoscopic resection for 69 colorectal lesions at the Jikei University Hospital between June 2017 and February 2018. First, we evaluated the diagnostic performances using still images randomly and automatically extracted from video recordings of the entire endoscopic procedure at intervals of 5 s, without eliminating poor quality images. Second, the latency of lesion detection by the CADe system from the initial appearance of lesions was investigated by reviewing the videos. A total of 6531 images, including 662 images with a lesion, were studied in the image-based analysis. The AUC, sensitivity, specificity, positive predictive value, negative predictive value, and accuracy were 0.983, 94.6%, 95.2%, 68.8%, 99.4%, and 95.1%, respectively. The median time for detecting colorectal lesions measured in the lesion-based analysis was 0.67 s. In conclusion, we proved that the originally developed CADe system based on YOLO v3 could accurately and instantaneously detect colorectal lesions using the test dataset obtained from videos, mitigating operator selection biases. Full article

(This article belongs to the Special Issue Advancements in Colonoscopy)

► Show Figures

Figure 1

4 pages, 1281 KiB

Open AccessInteresting Images

Coronary-Pulmonary Artery Fistula Recanalization on Coronary Computed Tomography Angiography Images

by Paweł Gać, Adrian Martuszewski, Patrycja Paluszkiewicz and Rafał Poręba

Diagnostics 2021, 11(10), 1921; https://doi.org/10.3390/diagnostics11101921 - 17 Oct 2021

Cited by 1 | Viewed by 1931

Abstract

Coronary computed tomography angiography (CCTA) is a non-invasive diagnostic method used (apart from the diagnosis of coronary artery disease) in the diagnosis of malformations of the coronary circulation and monitoring the effects of their treatment. In this paper, the authors present the case [...] Read more.

Coronary computed tomography angiography (CCTA) is a non-invasive diagnostic method used (apart from the diagnosis of coronary artery disease) in the diagnosis of malformations of the coronary circulation and monitoring the effects of their treatment. In this paper, the authors present the case of recanalization of the coronary-pulmonary fistula, which was surgically closed in the past. This case highlights that follow-up CCTA after surgical treatment of coronary artery fistula should be performed in every patient. The recommendations regarding the frequency of such follow-up should be made. Full article

(This article belongs to the Section Medical Imaging and Theranostics)

► Show Figures

Figure 1

20 pages, 2251 KiB

Open AccessArticle

Deep Semi-Supervised Algorithm for Learning Cluster-Oriented Representations of Medical Images Using Partially Observable DICOM Tags and Images

by Teo Manojlović and Ivan Štajduhar

Diagnostics 2021, 11(10), 1920; https://doi.org/10.3390/diagnostics11101920 - 17 Oct 2021

Cited by 5 | Viewed by 2421

Abstract

The task of automatically extracting large homogeneous datasets of medical images based on detailed criteria and/or semantic similarity can be challenging because the acquisition and storage of medical images in clinical practice is not fully standardised and can be prone to errors, which [...] Read more.

The task of automatically extracting large homogeneous datasets of medical images based on detailed criteria and/or semantic similarity can be challenging because the acquisition and storage of medical images in clinical practice is not fully standardised and can be prone to errors, which are often made unintentionally by medical professionals during manual input. In this paper, we propose an algorithm for learning cluster-oriented representations of medical images by fusing images with partially observable DICOM tags. Pairwise relations are modelled by thresholding the Gower distance measure which is calculated using eight DICOM tags. We trained the models using 30,000 images, and we tested them using a disjoint test set consisting of 8000 images, gathered retrospectively from the PACS repository of the Clinical Hospital Centre Rijeka in 2017. We compare our method against the standard and deep unsupervised clustering algorithms, as well as the popular semi-supervised algorithms combined with the most commonly used feature descriptors. Our model achieves an NMI score of

0.584

with respect to the anatomic region, and an NMI score of

0.793

with respect to the modality. The results suggest that DICOM data can be used to generate pairwise constraints that can help improve medical images clustering, even when using only a small number of constraints. Full article

(This article belongs to the Section Machine Learning and Artificial Intelligence in Diagnostics)

► Show Figures

Figure 1

8 pages, 1088 KiB

Open AccessArticle

Identifying Thrombus on Non-Contrast CT in Patients with Acute Ischemic Stroke

by Shakeel Qazi, Emmad Qazi, Alexis T. Wilson, Connor McDougall, Fahad Al-Ajlan, James Evans, Henrik Gensicke, Michael D. Hill, Ting Lee, Mayank Goyal, Andrew M. Demchuk, Bijoy K. Menon and Nils D. Forkert

Diagnostics 2021, 11(10), 1919; https://doi.org/10.3390/diagnostics11101919 - 16 Oct 2021

Cited by 6 | Viewed by 3689

Abstract

The hyperdense sign is a marker of thrombus in non-contrast computed tomography (NCCT) datasets. The aim of this work was to determine optimal Hounsfield unit (HU) thresholds for thrombus segmentation in thin-slice non-contrast CT (NCCT) and use these thresholds to generate 3D thrombus [...] Read more.

The hyperdense sign is a marker of thrombus in non-contrast computed tomography (NCCT) datasets. The aim of this work was to determine optimal Hounsfield unit (HU) thresholds for thrombus segmentation in thin-slice non-contrast CT (NCCT) and use these thresholds to generate 3D thrombus models. Patients with thin-slice baseline NCCT (≤2.5 mm) and MCA-M1 occlusions were included. CTA was registered to NCCT, and three regions of interest (ROIs) were placed in the NCCT, including: the thrombus, contralateral brain tissue, and contralateral patent MCA-M1 artery. Optimal HU thresholds differentiating the thrombus from non-thrombus tissue voxels were calculated using receiver operating characteristic analysis. Linear regression analysis was used to predict the optimal HU threshold for discriminating the clot only based on the average contralateral vessel HU or contralateral parenchyma HU. Three-dimensional models from 70 participants using standard (45 HU) and patient-specific thresholds were generated and compared to CTA clot characteristics. The optimal HU threshold discriminating thrombus in NCCT from other structures varied with a median of 51 (IQR: 49–55). Experts chose 3D models derived using patient-specific HU models as corresponding better to the thrombus seen in CTA in 83.8% (31/37) of cases. Patient-specific HU thresholds for segmenting the thrombus in NCCT can be derived using normal parenchyma. Thrombus segmentation using patient-specific HU thresholds is superior to conventional 45 HU thresholds. Full article

(This article belongs to the Section Medical Imaging and Theranostics)

► Show Figures

Figure 1

Figure 1
Regions of interest (ROIs) selected from three separate regions in the baseline NCCT: (1) thrombus: four 3 × 3 voxel ROIs were placed within the thrombus with the boundaries being determined using corresponding registered CTA datasets. (2) Contralateral artery: four 3 × 3 voxel ROIs were placed within the contralateral artery; the lumen of the artery was identified on the registered CTA and four 3 × 3 ROIs were placed along the center axis of the lumen. Hounsfield units were measured in the NCCT. (3) Contralateral parenchyma: a 10 × 10 voxel ROI was placed in the contralateral parenchyma in the NCCT. Full article ">Figure 2
Patient with right distal middle cerebral artery M1 occlusion extending into the M2: (A) hyperdense sign in NCCT (marked by the arrow); (B) thrombus in baseline CTA; (C) three-dimensional model using conventional 45 HU threshold, which does not accurately depict CTA thrombus; (D) patient-specific threshold of 48 HU; (E) three-dimensional model using patient-specific HU threshold super-imposed onto CTA. Full article ">Figure 3
Panel (A) shows a box plot of the distribution of optimal thresholds that were calculated using ROC analysis comparing thrombus HU to normal tissue (parenchymal + contralateral vessel). A wide distribution indicates that there is no single HU threshold that is optimal to discriminate thrombus from normal tissue. Panel (B) is a two-way scatter plot showing that contralateral HU and parenchyma HU predict optimal HU threshold similarly. Full article ">Figure 4
Qualitatively comparing three-dimensional models of the hyperdense thrombus in NCCT with CTA thrombus. Three-dimensional model formed using either (1) calculated patient-specific thresholds or (2) conventional single 45HU threshold. Full article ">

12 pages, 737 KiB

Open AccessArticle

Reactive Hyperemia-Triggered Wrist Pulse Analysis for Early Monitoring of Young Men with High Atherosclerotic Risk

by Jian-Jung Chen, Hsien-Tsai Wu and Bagus Haryadi

Diagnostics 2021, 11(10), 1918; https://doi.org/10.3390/diagnostics11101918 - 16 Oct 2021

Cited by 2 | Viewed by 2802

Abstract

The high prevalence of cardiovascular disease in young adults has raised significant concern regarding the early identification of risk factors to allow for timely intervention. This study aimed to identify young males at risk of atherosclerosis using a noninvasive instrument and an initial [...] Read more.

The high prevalence of cardiovascular disease in young adults has raised significant concern regarding the early identification of risk factors to allow for timely intervention. This study aimed to identify young males at risk of atherosclerosis using a noninvasive instrument and an initial application percussion entropy analysis of the wrist pressure pulse (WPP). In total, 49 young males aged 18 to 28, without any known history of vascular disease, were recruited. Blood samples were obtained whereby a TC/HDL cutoff value of 4 was used to divide the young men into low-risk (Group 1, TC/HDL < 4, N = 32) and high-risk (Group 2, TC/HDL ≥ 4, N = 17) groups regarding atherosclerosis. The reactive hyperemia-triggered WPPs were measured using a modified air-pressure-sensing system (MAPSS). The dilation index (DI) of the endothelial function and percussion entropy index (PEI) of the heart rate variability (HRV) assessments, calculated using pragmatic signal-processing techniques, were compared between the two groups. The nonparametric Mann–Whitney U test showed that the DI and PEI of the two groups showed statistical differences (both p < 0.05). Not only could the MAPSS assess endothelial function and HRV in young males, but the results also showed that waist circumference and PEI may serve as indicators for the early identification of young males at risk of atherosclerosis. Full article

(This article belongs to the Special Issue Challenges and Advances in Monitoring and Diagnosis in Medical Sciences 2.0)

► Show Figures

Graphical abstract

9 pages, 862 KiB

Open AccessArticle

Hysteroscopy as a Primary Tool in Exploration and Treatment of Infertility: Single Center Experience in Western Romania

by Cosmin Citu, Florin Gorun, Andrei Motoc, Ioan Sas, Oana Maria Gorun, Bogdan Burlea, Denis Mihai Serban, Radu Neamtu and Ioana Mihaela Citu

Diagnostics 2021, 11(10), 1917; https://doi.org/10.3390/diagnostics11101917 - 16 Oct 2021

Cited by 5 | Viewed by 2827

Abstract

(1) Background: Infertility is a disease that affects millions of individuals worldwide. Intrauterine lesions are common in infertile women, hysteroscopy being considered the gold standard for assessing them, even if in routine clinical practice indirect imaging techniques are the first-line investigative tools. The [...] Read more.

(1) Background: Infertility is a disease that affects millions of individuals worldwide. Intrauterine lesions are common in infertile women, hysteroscopy being considered the gold standard for assessing them, even if in routine clinical practice indirect imaging techniques are the first-line investigative tools. The aim of the study was to evaluate hysteroscopic findings among women with unexplained infertility and to analyze fertility outcomes after operative hysteroscopy; (2) Methods: a retrospective cohort study was conducted among 198 women with infertility that had undergone hysteroscopy as the first step of their infertility workup. (3) Results: The median age of the participants was 34 years, 67.7% of them being diagnosed with primary infertility. The most common abnormalities were endometrial polyps, uterine synechiae and uterine fibroids. In addition, pregnancy rates were 23.1% after hysteroscopic polypectomy, 11.1% after hysteroscopic myomectomy and 23.8% after uterine synechiae resection; (4) Conclusions: Endometrial polyps were the most common uterine abnormality found in women with infertility. Hysteroscopic interventions appeared to increase pregnancy rates and outcomes among these women. Full article

(This article belongs to the Special Issue Updates in the Hysteroscopic Approach to Uterine Diseases: Molecular Bases, Diagnostics and Therapeutics)

► Show Figures

Figure 1

19 pages, 3215 KiB

Open AccessArticle

A Survival Guide for the Rapid Transition to a Fully Digital Workflow: The “Caltagirone Example”

by Filippo Fraggetta, Alessandro Caputo, Rosa Guglielmino, Maria Giovanna Pellegrino, Giampaolo Runza and Vincenzo L'Imperio

Diagnostics 2021, 11(10), 1916; https://doi.org/10.3390/diagnostics11101916 - 16 Oct 2021

Cited by 45 | Viewed by 4189

Abstract

Digital pathology for the routine assessment of cases for primary diagnosis has been implemented by few laboratories worldwide. The Gravina Hospital in Caltagirone (Sicily, Italy), which collects cases from 7 different hospitals distributed in the Catania area, converted the entire workflow to digital [...] Read more.

Digital pathology for the routine assessment of cases for primary diagnosis has been implemented by few laboratories worldwide. The Gravina Hospital in Caltagirone (Sicily, Italy), which collects cases from 7 different hospitals distributed in the Catania area, converted the entire workflow to digital starting from 2019. Before the transition, the Caltagirone pathology laboratory was characterized by a non-tracked workflow, based on paper requests, hand-written blocks and slides, as well as manual assembling and delivering of the cases and glass slides to the pathologists. Moreover, the arrangement of the spaces and offices in the department was illogical and under-productive for the linearity of the workflow. For these reasons, an adequate 2D barcode system for tracking purposes, the redistribution of the spaces inside the laboratory and the implementation of the whole-slide imaging (WSI) technology based on a laboratory information system (LIS)-centric approach were adopted as a needed prerequisite to switch to a digital workflow. The adoption of a dedicated connection for transfer of clinical and administrative data between different software and interfaces using an internationally recognised standard (Health Level 7, HL7) in the pathology department further facilitated the transition, helping in the integration of the LIS with WSI scanners. As per previous reports, the components and devices chosen for the pathologists’ workstations did not significantly impact on the WSI-based reporting phase in primary histological diagnosis. An analysis of all the steps of this transition has been made retrospectively to provide a useful “handy” guide to lead the digital transition of “analog”, non-tracked pathology laboratories following the experience of the Caltagirone pathology department. Following the step-by-step instructions, the implementation of a paperless routine with more standardized and safe processes, the possibility to manage the priority of the cases and to implement artificial intelligence (AI) tools are no more an utopia for every “analog” pathology department. Full article

(This article belongs to the Special Issue Digital Pathology: Records of Successful Implementations)

► Show Figures

Figure 1

Figure 1
(A), Location of the Catania area in Sicily, south of Italy. (B), the different hospitals in the Catania territory referring to the Caltagirone pathology laboratory at Gravina Hospital. Full article ">Figure 2
One of the “home-made” working stations used by pathologists for the off-site sign-out and reporting. The smaller monitor (on the left) has a sufficient size and resolution to run the LIS. The right display allows an adequate visualization of the WSI. Full article ">Figure 3
Comparison of some of the principal checkpoints before and after the implementation of DP tools. On the left, during the grossing phase the case identification number was handwritten on every cassette before the introduction of case-specific 2D-barcodes directly generated by the LIS and laser-printed on the cassettes. Similarly, hand-labeled glass slides were randomly returned to the technicians and manually archived (right). The introduction of WSI and scanner next to the staining instrument allowed the direct archiving of physical glass slides using the 2D barcodes. Full article ">Figure 4
Digital pictures taken at each step of the life of the specimen and respective cassettes fully document the flow of tissue in the lab, allowing global traceability and high-resolution error tracking. (A) Specimen container as it is received; (B) Cassette at grossing, before closing its lid; (C) Surface of the FFPE block after microtome sectioning; (D) Macro picture of the glass slide after staining. Full article ">Figure 5
The reading process of barcodes directly from the rack containing the blocks during the processing phase after the digital transition. In the upper right inset the code extracted from the 2D barcode directly in the LIS. Full article ">Figure 6
The BlocDoc at the embedding phase. Full article ">Figure 7
An example of a sectioning station. The technician can identify the block through a barcode reader (red arrow), entering the LIS page of the case and printing the related glass slides with a laser printer (yellow arrow). After sectioning, the technician can directly scan the cut surface positioning the block on the dedicated space in the BlocDoc instrument (green arrow), with the possibility to assess the preview of the obtained image (blue arrow). Full article ">Figure 8
The importance and relationship of the main points required for the development of a reliable, sustainable and safe digital pathology workflow. Full article ">

9 pages, 622 KiB

Open AccessArticle

Long-Term Monitoring of the Antibody Response to a SARS-CoV-2 Infection

by Václav Šimánek, Ladislav Pecen, Hana Řezáčková, Ondřej Topolčan, Karel Fajfrlík, Dalibor Sedláček, Robin Šín, Monika Bludovská, Petr Pazdiora, David Slouka and Radek Kučera

Diagnostics 2021, 11(10), 1915; https://doi.org/10.3390/diagnostics11101915 - 16 Oct 2021

Cited by 2 | Viewed by 2240

Abstract

A group of 110 patients from the West Bohemian region who had been infected with COVID-19 was monitored for the purposes of this study. We focused on cases of mild or moderate COVID-19; statistically the most likely to occur. Day zero was defined [...] Read more.

A group of 110 patients from the West Bohemian region who had been infected with COVID-19 was monitored for the purposes of this study. We focused on cases of mild or moderate COVID-19; statistically the most likely to occur. Day zero was defined as the day on which a positive PCR test was first established. The mean length of observation was 6.5 months, the maximum length 12 months. The first blood samples were taken from a smaller cohort during the 1–3 months following the first positive PCR test. We assumed that SARS-CoV-2 antibodies would be present during this period and therefore a limited number of samples were taken for the purpose of detecting antibodies. More samples were collected, starting 4 months after the first positive PCR test. A subsequent set of blood samples were drawn, mostly 6 months after the first ones. Our study confirmed the presence of total IgG SARS-CoV-2 antibodies up to 1 year after the onset of the disease. The peak of antibody production was observed in the third month after the first positive PCR test. A mathematical estimate of the median duration of antibody positivity was calculated to be 18 months from the onset of the COVID-19 infection. Full article

(This article belongs to the Section Diagnostic Microbiology and Infectious Disease)

► Show Figures

Figure 1

13 pages, 803 KiB

Open AccessArticle

Obesity and Bone Loss at Menopause: The Role of Sclerostin

by Paolo Marzullo, Chiara Mele, Stefania Mai, Antonio Nardone, Massimo Scacchi and Gianluca Aimaretti

Diagnostics 2021, 11(10), 1914; https://doi.org/10.3390/diagnostics11101914 - 16 Oct 2021

Cited by 6 | Viewed by 2743

Abstract

Background. Peripheral fat tissue is known to positively influence bone health. However, evidence exists that the risk of non-vertebral fractures can be increased in postmenopausal women with obesity as compared to healthy controls. The role of sclerostin, the SOST gene protein product, [...] Read more.

Background. Peripheral fat tissue is known to positively influence bone health. However, evidence exists that the risk of non-vertebral fractures can be increased in postmenopausal women with obesity as compared to healthy controls. The role of sclerostin, the SOST gene protein product, and body composition in this condition is unknown. Methods. We studied 28 severely obese premenopausal (age, 44.7 ± 3.9 years; BMI, 46.0 ± 4.2 kg/m²) and 28 BMI-matched post-menopausal women (age, 55.5 ± 3.8 years; BMI, 46.1 ± 4.8 kg/m²) thorough analysis of bone density (BMD) and body composition by dual X-ray absorptiometry (DXA), bone turnover markers, sclerostin serum concentration, glucose metabolism, and a panel of hormones relating to bone health. Results. Postmenopausal women harbored increased levels of the bone turnover markers CTX and NTX, while sclerostin levels were non-significantly higher as compared to premenopausal women. There were no differences in somatotroph, thyroid and adrenal hormone across menopause. Values of lumbar spine BMD were comparable between groups. By contrast, menopause was associated with lower BMD values at the hip (p < 0.001), femoral neck (p < 0.0001), and total skeleton (p < 0.005). In multivariate regression analysis, sclerostin was the strongest predictor of lumbar spine BMD (p < 0.01), while menopausal status significantly predicted BMD at total hip (p < 0.01), femoral neck (p < 0.001) and total body (p < 0.05). Finally, lean body mass emerged as the strongest predictor of total body BMD (p < 0.01). Conclusions. Our findings suggest a protective effect of obesity on lumbar spine and total body BMD at menopause possibly through mechanisms relating to lean body mass. Given the mild difference in sclerostin levels between pre- and postmenopausal women, its potential actions in obesity require further investigation. Full article

(This article belongs to the Special Issue Advance in the Diagnostics and Management of Musculoskeletal Diseases)

► Show Figures

Figure 1

9 pages, 586 KiB

Open AccessArticle

Do We Really Need Hazard Prevention at the Expense of Safeguarding Death Dignity in COVID-19?

by Cristoforo Pomara, Francesco Sessa, Domenico Galante, Lorenzo Pace, Antonio Fasanella, Nunzio Di Nunno, Massimiliano Esposito and Monica Salerno

Diagnostics 2021, 11(10), 1913; https://doi.org/10.3390/diagnostics11101913 - 15 Oct 2021

Cited by 7 | Viewed by 2232

Abstract

To date, little is known regarding the transmission risks of SARS-CoV-2 infection for subjects involved in handling, transporting, and examining deceased persons with known or suspected COVID-19 positivity at the time of death. This experimental study aims to define if and/or how long [...] Read more.

To date, little is known regarding the transmission risks of SARS-CoV-2 infection for subjects involved in handling, transporting, and examining deceased persons with known or suspected COVID-19 positivity at the time of death. This experimental study aims to define if and/or how long SARS-CoV-2 persists with replication capacity in the tissues of individuals who died with/from COVID-19, thereby generating infectious hazards. Sixteen patients who died with/from COVID-19 who underwent autopsy between April 2020 and April 2021 were included in this study. Based on PMI, all samples were subdivided into two groups: ‘short PMI’ group (eight subjects who were autopsied between 12 to 72 h after death); ‘long PMI’ (eight subjects who were autopsied between 24 to 78 days after death). All patients tested positive for RT-PCR at nasopharyngeal swab both before death and on samples collected during post-mortem investigation. Moreover, a lung specimen was collected and frozen at −80 °C in order to perform viral culture. The result was defined based on the cytopathic effect (subjective reading) combined with the positivity of the RT-PCR test (objective reading) in the supernatant. Only in one sample (PMI 12 h), virus vitality was demonstrated. This study, supported by a literature review, suggests that the risk of cadaveric infection in cases of a person who died from/with COVID-19 is extremely low in the first hours after death, becoming null after 12 h after death, confirming the World Health Organization (WHO) assumed in March 2020 and suggesting that the corpse of a subject who died from/with COVID-19 should be generally considered not infectious. Full article

(This article belongs to the Special Issue Multidisciplinary Approaches to Manage COVID-19: From Surveillance to Diagnosis)

► Show Figures

Figure 1

15 pages, 2351 KiB

Open AccessArticle

Before and after Endovascular Aortic Repair in the Same Patients with Aortic Dissection: A Cohort Study of Four-Dimensional Phase-Contrast Magnetic Resonance Imaging

by Chien-Wei Chen, Yueh-Fu Fang, Yuan-Hsi Tseng, Min Yi Wong, Yu-Hui Lin, Yin-Chen Hsu, Bor-Shyh Lin and Yao-Kuang Huang

Diagnostics 2021, 11(10), 1912; https://doi.org/10.3390/diagnostics11101912 - 15 Oct 2021

Cited by 1 | Viewed by 2373

Abstract

(1) Background: We used four-dimensional phase-contrast magnetic resonance imaging (4D PC-MRI) to evaluate the impact of an endovascular aortic repair (TEVAR) on aortic dissection. (2) Methods: A total of 10 patients received 4D PC-MRI on a 1.5-T MR both before and after TEVAR. [...] Read more.

(1) Background: We used four-dimensional phase-contrast magnetic resonance imaging (4D PC-MRI) to evaluate the impact of an endovascular aortic repair (TEVAR) on aortic dissection. (2) Methods: A total of 10 patients received 4D PC-MRI on a 1.5-T MR both before and after TEVAR. (3) Results: The aortas were repaired with either a GORE TAG Stent (Gore Medical; n = 7) or Zenith Dissection Endovascular Stent (Cook Medical; n = 3). TEVAR increased the forward flow volume of the true lumen (TL) (at the abdominal aorta, p = 0.047). TEVAR also reduced the regurgitant fraction in the TL at the descending aorta but increased it in the false lumen (FL). After TEVAR, the stroke distance increased in the TL (at descending and abdominal aorta, p = 0.018 and 0.015), indicating more effective blood transport per heartbeat. Post-stenting quantitative flow revealed that the reductions in stroke volume, backward flow volume, and absolute stroke volume were greater when covered stents were used than when bare stents were used in the FL of the descending aorta. Bare stents had a higher backward flow volume than covered stents did. (4) Conclusions: TEVAR increased the stroke volume in the TL and increased the regurgitant fraction in the FL in patients with aortic dissection. Full article

(This article belongs to the Special Issue Advanced Techniques in Body Magnetic Resonance Imaging 2.0)

► Show Figures

Figure 1

Figure 1
Illustration of QFlow scanning and drawing the region of interest (ROI). The QFlow scanning is performed at four levels to obtain two-dimensional images (perpendicular to blood flow and aortic curve). By drawing ROI on the vascular lumens (completely covering the true lumen and false lumen), eight hemodynamic variables can be obtained for each ROI for the subsequent statistical analysis. The flow direction to the head was set as positive flow. Full article ">Figure 2
Phase-contrast magnetic resonance imaging (PC-MRI) quantitative flow measurements after thoracic endovascular aortic repair (TEVAR) compared with those before TEVAR (A) stroke volume (SV): SV decreased in the false lumen and increased in the true lumen after TEVAR; (B) forward flow volume (FFV): FFV increased in the true lumen; (C) backward flow volume; (D) regurgitant fraction (RF): RF in the aortic arch increased in the false lumen and decreased in the true lumen. Full article ">Figure 3
Phase-contrast magnetic resonance imaging (PC-MRI) quantitative flow measurements after thoracic endovascular aortic repair (TEVAR) compared with those before TEVAR: (A) absolute stroke volume (ASV): ASV in the true lumen increased in a manner similar to the increase in stroke volume; (B) mean flux (MF): MF decreased in the false lumen in the aortic arch; (C) stroke distance (SD): SD in the true lumen increased after TEVAR; (D) mean velocity (MV): MV in the true lumen increased after TEVAR. Full article ">Figure 4
Covered (graft) stent and bare stent: Phase-contrast magnetic resonance imaging (PC-MRI) quantitative flow measurements after thoracic endovascular aortic repair (TEVAR) compared with those before TEVAR: (A) stroke volume (SV): SV exhibited a similar distribution between false and true lumens; (B) forward flow volume (FFV): FFV exhibited a similar distribution between false and true lumens; (C) backward flow volume (BFV): BFV in the false lumen was higher in patients with bare stents than in those with covered stents; (D) regurgitant fraction (RF): RF in the false lumen was higher in patients with graft stent than in those with bare stents. Full article ">Figure 5
Covered (graft) stent and bare stent: Phase-contrast magnetic resonance imaging (PC-MRI) quantitative flow measurements after thoracic endovascular aortic repair (TEVAR) compared with those before TEVAR: (A) absolute stroke volume (ASV): ASV in the false lumen was higher in the bare stent group, indicating fewer communicator occlusions by the bare stent in the thoracic aorta; (B) mean flux (MF): MF was higher in the true lumen in patients with bare stents; (C) stroke distance (SD): SD in the true lumen was smaller in patients with bare stents than in those with covered stents after thoracic endovascular aortic repair (TEVAR); (D) mean velocity (MV): MV was higher in the descending segment but lower in the abdominal aorta in the bare stent group than in the covered stent group after TEVAR. Full article ">

13 pages, 1653 KiB

Open AccessArticle

Assessment of Serum Neopterin as a Biomarker in Peripheral Artery Disease

by Agnieszka Zembron-Lacny, Wioletta Dziubek, Anna Tylutka, Eryk Wacka, Barbara Morawin, Katarzyna Bulinska, Malgorzata Stefanska, Marek Wozniewski and Andrzej Szuba

Diagnostics 2021, 11(10), 1911; https://doi.org/10.3390/diagnostics11101911 - 15 Oct 2021

Cited by 5 | Viewed by 2144

Abstract

Neopterin (NPT), a pyrazino-pyrimidine compound mainly produced by activated macrophages, has been regarded as a proinflammatory and proatherosclerotic agent. The study was designed to evaluate NPT level and its interaction with conventional peripheral artery disease (PAD) biomarkers and vascular regenerative potential in severe [...] Read more.

Neopterin (NPT), a pyrazino-pyrimidine compound mainly produced by activated macrophages, has been regarded as a proinflammatory and proatherosclerotic agent. The study was designed to evaluate NPT level and its interaction with conventional peripheral artery disease (PAD) biomarkers and vascular regenerative potential in severe PAD. The study included 59 patients (females n = 17, males n = 42) aged 67.0 ± 8.2 years classified into two groups based on ankle-brachial index (ABI) measurements (ABI ≤ 0.9 n = 43, ABI ≤ 0.5 n = 16). A total of 60 subjects aged 70.4 ± 5.5 years (females n = 42, males n = 18) with ABI > 0.9 constituted a reference group. NPT concentration reached values above 10 nmol/L in patients with PAD, which differed significantly from reference group (8.15 ± 1.33 nmol/L). High levels of CRP > 5 mg/L, TC > 200 mg/dL as well as lipoproteins LDL > 100 mg/dL and non-HDL > 130 mg/dL were found in the same group, indicating the relationship between NPT and conventional atherogenic markers. The endothelial progenitor cells (EPCs) tended toward lower values in patients with ABI ≤ 0.5 when compared to reference group, and inversely correlated with NPT. These findings indicate a crucial role of NPT in atheromatous process and its usefulness in monitoring PAD severity. However, the role of NPT in chronic PAD needs further studies including relatively high number of subjects. Full article

(This article belongs to the Special Issue Biomarkers of Vascular Diseases 2.0)

► Show Figures

Figure 1

14 pages, 24381 KiB

Open AccessArticle

Comprehensive Molecular Analysis of DMD Gene Increases the Diagnostic Value of Dystrophinopathies: A Pilot Study in a Southern Italy Cohort of Patients

by Fatima Domenica Elisa De Palma, Marcella Nunziato, Valeria D’Argenio, Maria Savarese, Gabriella Esposito and Francesco Salvatore

Diagnostics 2021, 11(10), 1910; https://doi.org/10.3390/diagnostics11101910 - 15 Oct 2021

Cited by 9 | Viewed by 2740

Abstract

Duchenne/Becker muscular dystrophy (DMD/BMD) is an X-linked neuromuscular disease due to pathogenic sequence variations in the dystrophin (DMD) gene, one of the largest human genes. More than 70% of DMD gene defects result from genomic rearrangements principally leading to large deletions, while [...] Read more.

Duchenne/Becker muscular dystrophy (DMD/BMD) is an X-linked neuromuscular disease due to pathogenic sequence variations in the dystrophin (DMD) gene, one of the largest human genes. More than 70% of DMD gene defects result from genomic rearrangements principally leading to large deletions, while the remaining are small nucleotide variants, including nonsense and missense variants, small insertions/deletions or splicing alterations. Considering the large size of the gene and the wide mutational spectrum, the comprehensive molecular diagnosis of DMD/BMD is complex and may require several laboratory methods, thus increasing the time and costs of the analysis. In an attempt to simplify DMD/BMD molecular diagnosis workflow, we tested an NGS method suitable for the detection of all the different types of genomic variations that may affect the DMD gene. Forty previously analyzed patients were enrolled in this study and re-analyzed using the next generation sequencing (NGS)-based single-step procedure. The NGS results were compared with those from multiplex ligation-dependent probe amplification (MLPA)/multiplex PCR and/or Sanger sequencing. Most of the previously identified deleted/duplicated exons and point mutations were confirmed by NGS and 1 more pathogenic point mutation (a nonsense variant) was identified. Our results show that this NGS-based strategy overcomes limitations of traditionally used methods and is easily transferable to routine diagnostic procedures, thereby increasing the diagnostic power of DMD molecular analysis. Full article

(This article belongs to the Section Pathology and Molecular Diagnostics)

► Show Figures

Figure 1

Figure 1
Summary of the analytic workflow. After genomic DNA quality and quantity assessment, each sample has been analyzed according to traditional molecular techniques (A) and NGS (B). In particular, MLPA and/or Sanger sequencing were carried out to detect DMD pathogenic mutations (A). The same samples were analyzed blindly by NGS (B). DNA libraries were prepared with an amplicon-based protocol for each study subject. Obtained libraries (corresponding to 40 individual samples) were sequenced in one sequencing run using the MiSeq system. NGS sequence data analysis was carried out using two different pipelines. Finally, NGS results were compared to those obtained with conventional diagnostic procedures. Full article ">Figure 2
Single nucleotide variants (SNVs) identified in the study group. (A) Pie chart illustrating the distribution (%) of the SNVs detected by NGS and classified according to their clinical significance by ClinVar Database; 3% of them corresponds to pathogenic mutations. (B) The c.583C>T (p.Arg195*) hemizygous mutation was found in one male subject by NGS and confirmed by Sanger sequencing as shown in the electropherogram assembled with the reference sequence ENST00000357033.8 (NM_000109; NP_000100). The figure highlights the presence of the variant in the forward and reverse strand respectively, as indicated by the arrows. DMD, Duchenne muscular dystrophy; NGS, next generation sequencing; UCV, uncertain significance variant. Full article ">Figure 3
Examples of NGS-based CNV detection in DMD by Sophia Genetics Software. (A,B) Plots illustrate the presence of duplicated (A) or deleted (B) amplicons highlighted in red rectangles. (C) The panel displays a rejected sample for which despite the crosses along the entire gene, it is possible to notice the presence of a potential deletion at the end of the line (corresponding to the exon 2); (D) representation of the normal profile (blue dots indicate exons without CNVs) of a male with no GRs. The horizontal axis shows the exons (from exon 1 to the right, to exon 79 to the left) and the vertical axis the copy number value. CNV, copy number variation; GR, genomic rearrangement. Full article ">Figure 4
Comparison of the performances of traditional analytical approaches with respect to the NGS strategy used in the present study. *mPCR amplifies only mutational hotspots in 24 out of 79 exons of DMD gene. DMD, Duchenne muscular dystrophy; INDELs, small insertions and deletions; MLPA, multiplex ligation-dependent probe amplification; mPCR, multiplex polymerase chain reaction; NGS, next generation sequencing. Full article ">

12 pages, 2189 KiB

Open AccessArticle

Machine Learning-Based Three-Month Outcome Prediction in Acute Ischemic Stroke: A Single Cerebrovascular-Specialty Hospital Study in South Korea

by Dougho Park, Eunhwan Jeong, Haejong Kim, Hae Wook Pyun, Haemin Kim, Yeon-Ju Choi, Youngsoo Kim, Suntak Jin, Daeyoung Hong, Dong Woo Lee, Su Yun Lee and Mun-Chul Kim

Diagnostics 2021, 11(10), 1909; https://doi.org/10.3390/diagnostics11101909 - 15 Oct 2021

Cited by 20 | Viewed by 3186

Abstract

Background: Functional outcomes after acute ischemic stroke are of great concern to patients and their families, as well as physicians and surgeons who make the clinical decisions. We developed machine learning (ML)-based functional outcome prediction models in acute ischemic stroke. Methods: This retrospective [...] Read more.

Background: Functional outcomes after acute ischemic stroke are of great concern to patients and their families, as well as physicians and surgeons who make the clinical decisions. We developed machine learning (ML)-based functional outcome prediction models in acute ischemic stroke. Methods: This retrospective study used a prospective cohort database. A total of 1066 patients with acute ischemic stroke between January 2019 and March 2021 were included. Variables such as demographic factors, stroke-related factors, laboratory findings, and comorbidities were utilized at the time of admission. Five ML algorithms were applied to predict a favorable functional outcome (modified Rankin Scale 0 or 1) at 3 months after stroke onset. Results: Regularized logistic regression showed the best performance with an area under the receiver operating characteristic curve (AUC) of 0.86. Support vector machines represented the second-highest AUC of 0.85 with the highest F1-score of 0.86, and finally, all ML models applied achieved an AUC > 0.8. The National Institute of Health Stroke Scale at admission and age were consistently the top two important variables for generalized logistic regression, random forest, and extreme gradient boosting models. Conclusions: ML-based functional outcome prediction models for acute ischemic stroke were validated and proven to be readily applicable and useful. Full article

(This article belongs to the Special Issue Artificial Intelligence Approaches for Medical Diagnostics in Korea)

► Show Figures

Figure 1

Figure 1
Flow chart of patient inclusion and exclusion. LNT, last normal time; mRS, modified Rankin Scale. Full article ">Figure 2
Entire machine learning modeling process for this study. SMOTE, synthetic minority oversampling technique; ADASYN, adaptive synthetic; RLR, regularized logistic regression; SVM, support vector machines; RF, random forest; KNN, k-nearest neighbors; XGB, extreme gradient boosting; AUC, area under the receiver operating characteristic curve; ACC, accuracy. Full article ">Figure 3
Results of external validation of each machine learning algorithm. (a) Receiver operating characteristic curves and (b) calibration plots are represented. The regularized logistic regression model showed the best performance with an AUC of 0.86 (red line). Overall, all the ML models showed AUC > 0.8. AUC, area under the receiver operating characteristic curve; RLR, regularized logistic regression; SVM, support vector machines; RF, random forest; KNN, k-nearest neighbors; XGB, extreme gradient boosting. Full article ">Figure 4
Top ten important variables in (a) regularized logistic regression, (b) random forest, and (c) extreme gradient boosting models. The top two important features were consistent in all three models; NIHSS at admission, followed by age. Additionally, random glucose, hemoglobin, and triglyceride were also included in the top ten important variables in all three models. NIHSS, National Institute of Health Stroke Scale; IV, intravenous; IA, intraarterial. Full article ">Figure 4 Cont.
Top ten important variables in (a) regularized logistic regression, (b) random forest, and (c) extreme gradient boosting models. The top two important features were consistent in all three models; NIHSS at admission, followed by age. Additionally, random glucose, hemoglobin, and triglyceride were also included in the top ten important variables in all three models. NIHSS, National Institute of Health Stroke Scale; IV, intravenous; IA, intraarterial. Full article ">

Journal Menu

Journal Browser

Diagnostics, Volume 11, Issue 10 (October 2021) – 203 articles

Further Information

Guidelines

MDPI Initiatives

Follow MDPI