Search Results (9,707)

Background: Cardiac magnetic resonance imaging (MRI) plays a crucial role in monitoring disease progression and evaluating the effectiveness of treatment interventions. Cardiac MRI allows medical practitioners to assess cardiac function accurately by providing comprehensive and quantitative information about the structure and function, hence making it an indispensable tool for monitoring the disease and treatment response. Deep learning-based segmentation enables the precise delineation of cardiac structures including the myocardium, right ventricle, and left ventricle. The accurate segmentation of these structures helps in the diagnosis of heart failure, cardiac functional response to therapies, and understanding the state of the heart functions after treatment. Objectives: The objective of this study is to develop a multiscale deep learning model to segment cardiac organs based on MRI imaging data. Good segmentation performance is difficult to achieve due to the complex nature of the cardiac structure, which includes a variety of chambers, arteries, and tissues. Furthermore, the human heart is also constantly beating, leading to motion artifacts that reduce image clarity and consistency. As a result, a multiscale method is explored to overcome various challenges in segmenting cardiac MRI images. Methods: This paper proposes DeSPPNet, a multiscale-based deep learning network. Its foundation follows encoder–decoder pair architecture that utilizes the Spatial Pyramid Pooling (SPP) layer to improve the performance of cardiac semantic segmentation. The SPP layer is designed to pool features from densely convolutional layers at different scales or sizes, which will be combined to maintain a set of spatial information. By processing features at different spatial resolutions, the multiscale densely connected layer in the form of the Pyramid Pooling Dense Module (PPDM) helps the network to capture both local and global context, preserving finer details of the cardiac structure while also capturing the broader context required to accurately segment larger cardiac structures. The PPDM is incorporated into the deeper layer of the encoder section of the deep learning network to allow it to recognize complex semantic features. Results: An analysis of multiple PPDM placement scenarios and structural variations revealed that the 3-path PPDM, positioned at the encoder layer 5, yielded optimal segmentation performance, achieving dice, intersection over union (IoU), and accuracy scores of 0.859, 0.800, and 0.993, respectively. Conclusions: Different PPDM configurations produce a different effect on the network; as such, a shallower layer placement, like encoder layer 4, retains more spatial data that need more parallel paths to gather the optimal set of multiscale features. In contrast, deeper layers contain more informative features but at a lower spatial resolution, which reduces the number of parallel paths required to provide optimal multiscale context. Full article

As the global population ages, the friendliness of urban spaces towards seniors becomes increasingly crucial. This research primarily investigates the environmental factors that influence the safety perception of elderly people in living street spaces. Taking Dingzigu Street in Tianjin, China, as an example, by employing deep learning fully convolutional network (FCN-8s) technology and the semantic segmentation method based on computer vision, the objective measurement data of street environmental elements are acquired. Meanwhile, the subjective safety perception evaluation data of elderly people are obtained through SD semantic analysis combined with the Likert scale. Utilizing Pearson correlation analysis and multiple linear regression analysis, the study comprehensively examines the impact of the physical environment characteristics of living street spaces on the spatial safety perception of seniors. The results indicate that, among the objective environmental indicators, ① the street greening rate is positively correlated with the spatial sense of security of seniors; ② there is a negative correlation between sky openness and interface enclosure; and ③ the overall safety perception of seniors regarding street space is significantly influenced by the spatial sense of security, the sense of security during walking behavior, and the security perception in visual recognition. This research not only uncovers the impact mechanism of the street environment on the safety perception of seniors, but also offers valuable references for the age-friendly design of urban spaces. Full article

Visual examination of nails can reflect human health status. Diseases such as nutritive imbalances and skin diseases can be identified by looking at the colors around the plate part of the nails. We present the AI-based NAILS method to detect fingernails through segmentation and labeling. The NAILS leverages a pre-trained Convolutional Neural Network model to segment and label fingernail regions from fingernail images, normalizing RGB values to monitor tiny color changes via a GUI and the use of an HD webcam in real time. The use of normalized RGB values combined with AI-based segmentation for real-time health monitoring is novel and innovative. The NAILS algorithm could be used to self-extract and archive primary signs of diseases in humans, especially in rural areas or when other testing may be not available. Full article

Semantic segmentation algorithms, such as UNet, that rely on convolutional neural network (CNN)-based architectures, due to their ability to capture local textures and spatial context, have shown promise for anthropogenic geomorphic feature extraction when using land surface parameters (LSPs) derived from digital terrain models (DTMs) as input predictor variables. However, the operationalization of these supervised classification methods is limited by a lack of large volumes of quality training data. This study explores the use of transfer learning, where information learned from another, and often much larger, dataset is used to potentially reduce the need for a large, problem-specific training dataset. Two anthropogenic geomorphic feature extraction problems are explored: the extraction of agricultural terraces and the mapping of surface coal mine reclamation-related valley fill faces. Light detection and ranging (LiDAR)-derived DTMs were used to generate LSPs. We developed custom transfer parameters by attempting to predict geomorphon-based landforms using a large dataset of digital terrain data provided by the United States Geological Survey’s 3D Elevation Program (3DEP). We also explored the use of pre-trained ImageNet parameters and initializing models using parameters learned from the other mapping task investigated. The geomorphon-based transfer learning resulted in the poorest performance while the ImageNet-based parameters generally improved performance in comparison to a random parameter initialization, even when the encoder was frozen or not trained. Transfer learning between the different geomorphic datasets offered minimal benefits. We suggest that pre-trained models developed using large, image-based datasets may be of value for anthropogenic geomorphic feature extraction from LSPs even given the data and task disparities. More specifically, ImageNet-based parameters should be considered as an initialization state for the encoder component of semantic segmentation architectures applied to anthropogenic geomorphic feature extraction even when using non-RGB image-based predictor variables, such as LSPs. The value of transfer learning between the different geomorphic mapping tasks may have been limited due to smaller sample sizes, which highlights the need for continued research in using unsupervised and semi-supervised learning methods, especially given the large volume of digital terrain data available, despite the lack of associated labels. Full article

Intelligent corrosion diagnosis plays a crucial role in enhancing the efficiency of operation and maintenance for steel structures. Presently, corrosion detection primarily depends on manual visual inspections and non-destructive testing methods, which are inefficient, costly, and subject to human bias. While machine vision has demonstrated significant potential in controlled laboratory settings, most studies have focused on environments with limited background interference, restricting their practical applicability. To tackle the challenges posed by complex backgrounds and multiple interference factors in field-collected images of steel components, this study introduces an intelligent corrosion grading method designed specifically for images containing background elements. By integrating an attention mechanism into the traditional U-Net network, we achieve precise segmentation of component pixels from background pixels in engineering images, attaining an accuracy of up to 94.1%. The proposed framework is validated using images collected from actual engineering sites. A sliding window sampling technique divides on-site images into several rectangular windows, which are filtered based on U-Net Attention segmentation results. Leveraging a dataset of steel plate corrosion images with known grades, we train an Inception v3 corrosion classification model. Transfer learning techniques are then applied to determine the corrosion grade of each filtered window, culminating in a weighted average to estimate the overall corrosion grade of the target component. This study provides a quantitative index for assessing large-scale steel structure corrosion, significantly impacting the improvement of construction and maintenance quality while laying a solid foundation for further research and development in related fields. Full article

The egg has natural barriers that prevent microbiological contamination and promote food safety. The use of non-destructive methods to obtain morphometric measurements of chicken eggs has the potential to replace traditional invasive techniques, offering greater efficiency and accuracy. This paper aims to demonstrate that estimates derived from non-invasive approaches, such as 3D computed tomography (CT) image analysis, can be comparable to conventional destructive methods. To achieve this goal, two widely recognized deep learning architectures, U-Net 3D and Fully Convolutional Networks (FCN) 3D, were modeled to segment and analyze 3D CT images of chicken eggs. A dataset of real CT images was created and labeled, allowing the extraction of important morphometric measurements, including height, width, shell thickness, and volume. The models achieved an accuracy of up to 98.69%, demonstrating their effectiveness compared to results from manual measurements. These findings highlight the potential of CT image analysis, combined with deep learning, as a non-invasive alternative in industrial and research settings. This approach not only minimizes the need for invasive procedures but also offers a scalable and reliable method for egg quality assessment. Full article

Accurately understanding the stand composition of shelter forests is essential for the construction and benefit evaluation of shelter forest projects. This study explores classification methods for dominant tree species in shelter forests using UAV-derived RGB, hyperspectral, and LiDAR data. It also investigates the impact of individual tree crown (ITC) delineation accuracy, crown morphological parameters, and various data sources and classifiers. First, as a result of the overlap and complex structure of tree crowns in shelterbelt forests, existing ITC delineation methods often lead to over-segmentation or segmentation errors. To address this challenge, we propose a watershed and multi-feature-controlled spectral clustering (WMF-SCS) algorithm for ITC delineation based on UAV RGB and LiDAR data, which offers clearer and more reliable classification objects, features, and training data for tree species classification. Second, spectral, texture, structural, and crown morphological parameters were extracted using UAV hyperspectral and LiDAR data combined with ITC delineation results. Twenty-one classification images were constructed using RF, SVM, MLP, and SAMME for tree species classification. The results show that (1) the proposed WMF-SCS algorithm demonstrates significant performance in ITC delineation in complex mixed forest scenarios (Precision = 0.88, Recall = 0.87, F1-Score = 0.87), resulting in a 1.85% increase in overall classification accuracy; (2) the inclusion of crown morphological parameters derived from LiDAR data improves the overall accuracy of the random forest classifier by 5.82%; (3) compared to using LiDAR or hyperspectral data alone, the classification accuracy using multi-source data improves by an average of 7.94% and 7.52%, respectively; (4) the random forest classifier combined with multi-source data achieves the highest classification accuracy and consistency (OA = 90.70%, Kappa = 0.8747). Full article

Background: The liver is one of the most common sites for the spread of pancreatic ductal adenocarcinoma (PDAC) cells, with metastases present in about 80% of patients. Clinical and preclinical studies of PDAC require quantification of the liver’s metastatic burden from several acquired images, which can benefit from automatic image segmentation tools. Methods: We developed three neural networks based on U-net architecture to automatically segment the healthy liver area (HL), the metastatic liver area (MLA), and liver metastases (LM) in micro-CT images of a mouse model of PDAC with liver metastasis. Three alternative U-nets were trained for each structure to be segmented following appropriate image preprocessing and the one with the highest performance was then chosen and applied for each case. Results: Good performance was achieved, with accuracy of 92.6%, 88.6%, and 91.5%, specificity of 95.5%, 93.8%, and 99.9%, Dice of 71.6%, 74.4%, and 29.9%, and negative predicted value (NPV) of 97.9%, 91.5%, and 91.5% on the pilot validation set for the chosen HL, MLA, and LM networks, respectively. Conclusions: The networks provided good performance and advantages in terms of saving time and ensuring reproducibility. Full article

Abdominal aortic aneurysm (AAA) is a complex vascular condition associated with high mortality rates. Accurate abdominal aorta segmentation is essential in medical imaging, facilitating diagnosis and treatment for a range of cardiovascular diseases. In this regard, deep learning-based automated segmentation has shown significant promise in the precise delineation of the aorta. However, comparisons across different models remain limited, with most studies performing algorithmic training and testing on the same dataset. Furthermore, due to the variability in AAA presentation, using healthy controls for deep learning AAA segmentation poses a significant challenge. This study provides a detailed comparative analysis of four deep learning architectures—UNet, SegResNet, UNet Transformers (UNETR), and Shifted-Windows UNet Transformers (SwinUNETR)—for full abdominal aorta segmentation. The models were evaluated both qualitatively and quantitatively using private and public 3D (Computed Tomography) CT datasets. Moreover, they were successful in attaining high performance in delineating AAA aorta, while being trained on healthy aortic imaging data. Our findings indicate that the UNet architecture achieved the highest segmentation accuracy among the models tested. Full article

Artificial Intelligence (AI) is a concept whose goal is to imitate human intellectual activity in computers. It emerged in the 1950s and has gone through three booms. We are in the third boom, and it will continue. Medical applications of AI include diagnosing otitis media from images of the eardrum, often outperforming human doctors. Temporal bone CT and MRI analyses also benefit from AI, with segmentation accuracy improved in anatomically significant structures or diagnostic accuracy improved in conditions such as otosclerosis and vestibular schwannoma. In treatment, AI predicts hearing outcomes for sudden sensorineural hearing loss and post-operative hearing outcomes for patients who have undergone tympanoplasty. AI helps patients with hearing aids hear in challenging situations, such as in noisy environments or when multiple people are speaking. It also provides fitting information to help improve hearing with hearing aids. AI also improves cochlear implant mapping and outcome prediction, even in cases of cochlear malformation. Future trends include generative AI, such as ChatGPT, which can provide medical advice and information, although its reliability and application in clinical settings requires further investigation. Full article

Among the emerging applications of artificial intelligence is animal instance segmentation, which has provided a practical means for various researchers to accomplish some aim or execute some order. Though video and image processing are two of the several complex tasks in artificial intelligence, these tasks have become more complex due to the large data and resources needed for training deep learning models. However, these challenges are beginning to be overcome by the transfer learning method of deep learning. In furtherance of the application of the transfer learning method, a system is proposed in this study that applies transfer learning to the detection and recognition of animal activity in a typical farm environment using deep learning models. Among the deep learning models compared, Enhanced Mask R-CNN obtained a significant computing time of 0.2 s and 97% mAP results, which are better than the results obtained by Mask R-CNN, Faster R-CNN, SSD, and YOLOv3, respectively. The findings from the results obtained in this study validate the innovative use of transfer learning to address challenges in cattle segmentation by optimizing the segmentation accuracy and processing time (0.2 s) of the proposed Enhanced Mask R-CNN. Full article

Change vector analysis in posterior probability space (CVAPS) is an effective change detection (CD) framework that does not require sound radiometric correction and is robust against accumulated classification errors. Based on training samples within target images, CVAPS can generate a uniformly scaled change-magnitude map that is suitable for a global threshold. However, vigorous user intervention is required to achieve optimal performance. Therefore, to eliminate user intervention and retain the merit of CVAPS, an unsupervised CVAPS (UCVAPS) CD method, RFCC, which does not require rigorous user training, is proposed in this study. In the RFCC, we propose an unsupervised remote sensing image segmentation algorithm based on the Mamba model, i.e., RVMamba differentiable feature clustering, which introduces two loss functions as constraints to ensure that RVMamba achieves accurate segmentation results and to supply the CSBN module with high-quality training samples. In the CD module, the fuzzy C-means clustering (FCM) algorithm decomposes mixed pixels into multiple signal classes, thereby alleviating cumulative clustering errors. Then, a context-sensitive Bayesian network (CSBN) model is introduced to incorporate spatial information at the pixel level to estimate the corresponding posterior probability vector. Thus, it is suitable for high-resolution remote sensing (HRRS) imagery. Finally, the UCVAPS framework can generate a uniformly scaled change-magnitude map that is suitable for the global threshold and can produce accurate CD results. The experimental results on seven change detection datasets confirmed that the proposed method outperforms five state-of-the-art competitive CD methods. Full article

Intracranial calcifications, particularly within the falx cerebri, serve as crucial diagnostic markers ranging from benign accumulations to signs of severe pathologies. The falx cerebri, a dural fold that separates the cerebral hemispheres, presents challenges in visualization due to its low contrast in standard imaging techniques. Recent advancements in artificial intelligence (AI), particularly in machine learning and deep learning, have significantly transformed radiological diagnostics. This study aims to explore the application of AI in the segmentation and detection of falx cerebri calcifications using Cone-Beam Computed Tomography (CBCT) images through a comprehensive literature review and a detailed case report. The case report presents a 59-year-old patient diagnosed with falx cerebri calcifications whose CBCT images were analyzed using a cloud-based AI platform, demonstrating effectiveness in segmenting these calcifications, although challenges persist in distinguishing these from other cranial structures. A specific search strategy was employed to search electronic databases, yielding four studies exploring AI-based segmentation of the falx cerebri. The review detailed various AI models and their accuracy across different imaging modalities in identifying and segmenting falx cerebri calcifications, also highlighting the gap in publications in this area. In conclusion, further research is needed to improve AI-driven methods for accurately identifying and measuring intracranial calcifications. Advancing AI applications in radiology, particularly for detecting falx cerebri calcifications, could significantly enhance diagnostic precision, support disease monitoring, and inform treatment planning. Full article

Background: Cardiothoracic ratio (CTR) and transverse cardiac diameter (TCD) are parameters that are used to assess cardiac size on chest radiographs (CXRs). We aimed to investigate the performance and efficiency of artificial intelligence (AI) in screening for cardiomegaly on CXRs. Methods: The U-net architecture was designed for lung and heart segmentation. The CTR and TCD were then calculated using these labels and a mathematical algorithm. For the training set, we retrospectively included 65 randomly selected patients who underwent CXRs, while for the testing set, we chose 50 patients who underwent cardiac magnetic resonance (CMR) imaging and had available CXRs in the medical documentation. Results: Using U-net for the training set, the Dice coefficient for the lung was 0.984 ± 0.003 (min. 0.977), while for the heart it was 0.983 ± 0.004 (min. 0.972). For the testing set, the Dice coefficient for the lung was 0.970 ± 0.012 (min. 0.926), while for the heart it was 0.950 ± 0.021 (min. 0.871). The mean CTR and TCD measurements were slightly greater when calculated from either manual or automated segmentation than when manually read. Receiver operating characteristic analyses showed that both the CTR and TCD measurements calculated from either manual or automated segmentation, or when manually read, were good predictors of cardiomegaly diagnosed in CMR. However, McNemar tests have shown that diagnoses made with TCD, rather than CTR, were more consistent with CMR diagnoses. According to a different definition of cardiomegaly based on CMR imaging, accuracy for CTR measurements ranged from 62.0 to 74.0% for automatic segmentation (for TCD it ranged from 64.0 to 72.0%). Conclusion: The use of AI may optimize the screening process for cardiomegaly on CXRs. Future studies should focus on improving the accuracy of AI algorithms and on assessing the usefulness both of CTR and TCD measurements in screening for cardiomegaly. Full article

Background/Objectives: According to the World Health Organization, the gold standard for diagnosing COVID-19 is the Reverse Transcription Polymerase Chain Reaction (RT-PCR) test. However, to confirm the diagnosis in patients who have negative results but still show symptoms, imaging tests, especially computed tomography (CT), are used. In this study, using convolutional neural networks, we compared the following topics using manual and automatic lung segmentation methods: (1) the performance of an automatic segmentation of COVID-19 areas using two strategies for data partitioning, CT scans, and slice strategies; (2) the performance of an automatic segmentation method of COVID-19 when there was interobserver agreement between two groups of radiologists; and (3) the performance of the area affected by COVID-19. Methods: Two datasets and two deep neural network architectures are used to evaluate the automatic segmentation of lungs and COVID-19 areas. The performance of the U-Net architecture is compared with the performance of a new architecture proposed by the research group. Results: With automatic lung segmentation, the Dice metrics for the segmentation of the COVID-19 area were 73.01 ± 9.47% and 84.66 ± 5.41% for the CT-scan strategy and slice strategy, respectively. With manual lung segmentation, the Dice metrics for the automatic segmentation of COVID-19 were 74.47 ± 9.94% and 85.35 ± 5.41% for the CT-scan and the slice strategy, respectively. Conclusions: The main conclusions were as follows: COVID-19 segmentation was slightly better for the slice strategy than for the CT-scan strategy; a comparison of the performance of the automatic COVID-19 segmentation and the interobserver agreement, in a group of 7 CT scans, revealed that there was no statistically significant difference between any metric. Full article