[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ Skip to main content

Advertisement

Springer Nature Link
Log in

Improving the Subtype Classification of Non-small Cell Lung Cancer by Elastic Deformation Based Machine Learning

  • Published:
Journal of Digital Imaging Aims and scope Submit manuscript

Abstract

Non-invasive image-based machine learning models have been used to classify subtypes of non-small cell lung cancer (NSCLC). However, the classification performance is limited by the dataset size, because insufficient data cannot fully represent the characteristics of the tumor lesions. In this work, a data augmentation method named elastic deformation is proposed to artificially enlarge the image dataset of NSCLC patients with two subtypes (squamous cell carcinoma and large cell carcinoma) of 3158 images. Elastic deformation effectively expanded the dataset by generating new images, in which tumor lesions go through elastic shape transformation. To evaluate the proposed method, two classification models were trained on the original and augmented dataset, respectively. Using augmented dataset for training significantly increased classification metrics including area under the curve (AUC) values of receiver operating characteristics (ROC) curves, accuracy, sensitivity, specificity, and f1-score, thus improved the NSCLC subtype classification performance. These results suggest that elastic deformation could be an effective data augmentation method for NSCLC tumor lesion images, and building classification models with the help of elastic deformation has the potential to serve for clinical lung cancer diagnosis and treatment design.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
£29.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price includes VAT (United Kingdom)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

source of training set and test set: original dataset and augmented dataset. ROC curves of five folds were plotted (thin lines) along with the average ROC curve (thick blue line) and the standard deviation (gray area). For both RF and GBRT, training the model on augmented images (combination 2) led to significantly improved classification performance compared to training on original images (combination 1) (mean AUCs 0.788 to 0.977, 0.796 to 0.980). Training and testing on both augmented images (combination 3) further increased the AUCs

Fig. 6

source of training set and test set: original dataset and augmented dataset. ROC curves of five experiments were plotted (thin lines) along with the average ROC curve (thick blue line) and the standard deviation (gray area). For both RF and GBRT, training the model on augmented images (combination 2) led to significantly improved classification performance compared to training on original images (combination 1) (mean AUCs 0.758 to 0.972, 0.813 to 0.981). Training and testing on both augmented images (combination 3) further increased the AUCs

Fig. 7

Similar content being viewed by others

References

  1. Bhattacharjee A, Richards WG, Staunton J, et al. Classification of human lung carcinomas by mRNA expression profiling reveals distinct adenocarcinoma subclasses. Proceedings of the National Academy of Sciences. 2001; 98(24):13790-13795.

    Article  CAS  Google Scholar 

  2. Siegel R, Naishadham D, Jemal A. Cancer statistics, 2012. CA Cancer J Clin. 2012;62(1):10-29.

    Article  PubMed  Google Scholar 

  3. Jung K-W, Won Y-J, Oh C-M, et al. Prediction of Cancer Incidence and Mortality in Korea, 2016. Cancer research and treatment : official journal of Korean Cancer Association. 2016; 48(2):451-457.

    Article  Google Scholar 

  4. Center NC. China Cancer Report: 2017. Beijing 2017.

  5. Travis WD. Pathology & genetics tumours of the lung, pleura, thymus and heart. World Health Organization classification of tumours. 2004.

  6. Risch A, Plass C. Lung cancer epigenetics and genetics. International Journal of Cancer. 2008;123(1):1-7.

    Article  CAS  PubMed  Google Scholar 

  7. Weston A, Willey JC, Modali R, et al. Differential DNA sequence deletions from chromosomes 3, 11, 13, and 17 in squamous-cell carcinoma, large-cell carcinoma, and adenocarcinoma of the human lung. Proceedings of the National Academy of Sciences. 1989; 86(13):5099-5103.

    Article  CAS  Google Scholar 

  8. Pikor LA, Ramnarine VR, Lam S, Lam WL. Genetic alterations defining NSCLC subtypes and their therapeutic implications. Lung Cancer. 2013; 82(2):179-189.

    Article  PubMed  Google Scholar 

  9. Johnson DH, Fehrenbacher L, Novotny WF, et al. Randomized Phase II Trial Comparing Bevacizumab Plus Carboplatin and Paclitaxel With Carboplatin and Paclitaxel Alone in Previously Untreated Locally Advanced or Metastatic Non-Small-Cell Lung Cancer. J Clin Oncol. 2004; 22(11):2184-2191.

    Article  CAS  PubMed  Google Scholar 

  10. Scagliotti GV, Parikh P, von Pawel J, et al. Phase III Study Comparing Cisplatin Plus Gemcitabine With Cisplatin Plus Pemetrexed in Chemotherapy-Naive Patients With Advanced-Stage Non–Small-Cell Lung Cancer. J Clin Oncol. 2008; 26(21):3543-3551.

    Article  CAS  PubMed  Google Scholar 

  11. Scagliotti G, Hanna N, Fossella F, et al. The Differential Efficacy of Pemetrexed According to NSCLC Histology: A Review of Two Phase III Studies. The Oncologist. 2009; 14(3):253-263.

    Article  CAS  PubMed  Google Scholar 

  12. Travis WD. Classification of Lung Cancer. Semin Roentgenol. 2011; 46(3):178-186.

    Article  PubMed  Google Scholar 

  13. Barash O, Peled N, Tisch U, Bunn PA, Hirsch FR, Haick H. Classification of lung cancer histology by gold nanoparticle sensors. Nanomed Nanotechnol Biol Med. 2012; 8(5):580-589.

    Article  CAS  Google Scholar 

  14. Cufer T, Ovcaricek T, O’Brien MER. Systemic therapy of advanced non-small cell lung cancer: Major-developments of the last 5-years. Eur J Cancer. 2013; 49(6):1216-1225.

    Article  CAS  PubMed  Google Scholar 

  15. Mok TS, Wu YL, Thongprasert S, et al. Gefitinib or Carboplatin–Paclitaxel in Pulmonary Adenocarcinoma. N Engl J Med. 2009; 361(10):947-957.

    Article  CAS  PubMed  Google Scholar 

  16. 16. Swanton C. Intratumor heterogeneity: evolution through space and time. Cancer Res. 2012; 72(19):4875-4882.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  17. Wu W, Parmar C, Grossmann P, et al. Exploratory Study to Identify Radiomics Classifiers for Lung Cancer Histology. Front Oncol. 2016; 6(71).

  18. Saad M, Choi TS. Deciphering unclassified tumors of non-small-cell lung cancer through radiomics. Comput Biol Med. 2017; 91:222-230.

    Article  PubMed  Google Scholar 

  19. E L, Lu L, Li L, Yang H, Schwartz LH, Zhao B. Radiomics for Classification of Lung Cancer Histological Subtypes Based on Nonenhanced Computed Tomography. Acad Radiol. 2018.

  20. Saad M, Choi TS. Computer-assisted subtyping and prognosis for non-small cell lung cancer patients with unresectable tumor. Comput Med Imaging Graph. 2018; 67:1-8.

    Article  PubMed  Google Scholar 

  21. Lambin P, Leijenaar RTH, Deist TM, et al. Radiomics: the bridge between medical imaging and personalized medicine. Nature Reviews Clinical Oncology. 2017; 14:749.

    Article  PubMed  Google Scholar 

  22. Sanduleanu S, Woodruff HC, de Jong EEC, et al. Tracking tumor biology with radiomics: A systematic review utilizing a radiomics quality score. Radiother Oncol. 2018; 127(3):349-360.

    Article  PubMed  Google Scholar 

  23. Thawani R, McLane M, Beig N, et al. Radiomics and radiogenomics in lung cancer: A review for the clinician. Lung Cancer. 2018; 115:34-41.

    Article  PubMed  Google Scholar 

  24. Haga A, Takahashi W, Aoki S, et al. Classification of early stage non-small cell lung cancers on computed tomographic images into histological types using radiomic features: interobserver delineation variability analysis. Radiological Physics and Technology. 2018; 11(1):27-35.

    Article  PubMed  Google Scholar 

  25. Madani A, Moradi M, Karargyris A, Syeda-Mahmood T. Chest x-ray generation and data augmentation for cardiovascular abnormality classification. Paper presented at: SPIE Medical Imaging2018.

    Google Scholar 

  26. Zhu X, Dong D, Chen Z, et al. Radiomic signature as a diagnostic factor for histologic subtype classification of non-small cell lung cancer. Eur Radiol. 2018; 28(7):2772-2778.

    Article  PubMed  Google Scholar 

  27. Tanner MA, Wong WH. The Calculation of Posterior Distributions by Data Augmentation. J Am Stat Assoc. 1987; 82(398):528-540.

    Article  Google Scholar 

  28. van Dyk DA, Meng X-L. The Art of Data Augmentation. Journal of Computational and Graphical Statistics. 2001; 10(1):1-50.

    Article  Google Scholar 

  29. Ronneberger O, Fischer P, Brox T. U-Net: Convolutional Networks for Biomedical Image Segmentation. Paper presented at: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015; 2015//, 2015; Cham.

  30. Simard PY, Steinkraus D, Platt JC. Best practices for convolutional neural networks applied to visual document analysis. Paper presented at: Seventh International Conference on Document Analysis and Recognition, 2003. Proceedings.; 6–6 Aug. 2003, 2003.

  31. Dosovitskiy A, Springenberg JT, Riedmiller M, Brox T. Discriminative Unsupervised Feature Learning with Convolutional Neural Networks. 2014:766--774.

  32. Al-masni MA, Al-antari MA, Park J-M, et al. Simultaneous detection and classification of breast masses in digital mammograms via a deep learning YOLO-based CAD system. Comput Methods Programs Biomed. 2018; 157(0):85-94.

    Article  PubMed  Google Scholar 

  33. Devalla SK, Renukanand PK, Sreedhar BK, et al. DRUNET: a dilated-residual U-Net deep learning network to segment optic nerve head tissues in optical coherence tomography images. Biomedical optics express. 2018; 9(7):3244-3265.

    Article  PubMed  PubMed Central  Google Scholar 

  34. Ramos-González J, López-Sánchez D, Castellanos-Garzón JA, de Paz JF, Corchado JM. A CBR framework with gradient boosting based feature selection for lung cancer subtype classification. Comput Biol Med. 2017; 86:98-106.

    Article  PubMed  Google Scholar 

  35. Rabbani M, Kanevsky J, Kafi K, Chandelier F, Giles FJ. Role of artificial intelligence in the care of patients with nonsmall cell lung cancer. Eur J Clin Invest. 2018; 48(4):e12901.

    Article  Google Scholar 

  36. Coudray N, Ocampo PS, Sakellaropoulos T, et al. Classification and mutation prediction from non–small cell lung cancer histopathology images using deep learning. Nat Med. 2018.

  37. Pedersen H, Brünner N, Francis D, et al. Prognostic Impact of Urokinase, Urokinase Receptor, and Type 1 Plasminogen Activator Inhibitor in Squamous and Large Cell Lung Cancer Tissue. Cancer Res. 1994; 54(17):4671-4675.

    CAS  PubMed  Google Scholar 

  38. Peterson P, Park K, Fossella F, Gatzemeier U, John W, Scagliotti G. P2-328: Is pemetrexed more effective in adenocarcinoma and large cell lung cancer than in squamous cell carcinoma? A retrospective analysis of a phase III trial of pemetrexed vs docetaxel in previously treated patients with advanced non-small cell lung cancer (NSCLC). J Thorac Oncol. 2007; 2(8):S851.

    Article  Google Scholar 

  39. Monica V, Ceppi P, Righi L, et al. Desmocollin-3: a new marker of squamous differentiation in undifferentiated large-cell carcinoma of the lung. Modern Pathol. 2009; 22:709.

    Article  CAS  Google Scholar 

  40. Zhao G-Y, Lin Z-W, Lu C-L, et al. USP7 overexpression predicts a poor prognosis in lung squamous cell carcinoma and large cell carcinoma. Tumor Biol. 2015; 36(3):1721-1729.

    Article  CAS  Google Scholar 

  41. Cai Z, Xu D, Zhang Q, Zhang J, Ngai S-M, Shao J. Classification of lung cancer using ensemble-based feature selection and machine learning methods. Mol Biosyst. 2015; 11(3):791-800.

    Article  CAS  PubMed  Google Scholar 

  42. Clark K, Vendt B, Smith K, et al. The Cancer Imaging Archive (TCIA): Maintaining and Operating a Public Information Repository. J Digit Imaging. 2013; 26(6):1045-1057.

    Article  PubMed  PubMed Central  Google Scholar 

  43. Aerts HJWL, Velazquez ER, Leijenaar RTH, et al. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nature communications. 2014; 5(0):4006.

    Article  CAS  PubMed  Google Scholar 

  44. Aerts HJWL, Rios Velazquez E, Leijenaar RTH, et al. Data From NSCLC-Radiomics. In: Archive TCI, ed2015.

  45. Maayan Frid-Adar ID, Eyal Klang, Michal Amitai, Jacob Goldberger, Hayit Greenspan. GAN-based Synthetic Medical Image Augmentation for increased CNN Performance in Liver Lesion Classification. ArXiv. 2018; 1803(01229).

  46. Beig N, Khorrami M, Alilou M, et al. Perinodular and Intranodular Radiomic Features on Lung CT Images Distinguish Adenocarcinomas from Granulomas. Radiology. 2018:180910.

  47. Bradski G. The OpenCV Library. Dr Dobb's Journal of Software Tools. 2000:2236121.

  48. Saeb S, Lonini L, Jayaraman A, Mohr DC, Kording KP. Voodoo Machine Learning for Clinical Predictions. bioRxiv. 2016.

  49. Pedregosa F, Varoquaux G, Gramfort A, et al. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research. 2011; 12(0):2825-2830.

    Google Scholar 

  50. Muller A, Guido S. Introduction to machine learning with python. O'Reilly; 2016.

  51. He B, Zhao W, Pi J-Y, et al. A biomarker basing on radiomics for the prediction of overall survival in non–small cell lung cancer patients. Respir Res. 2018; 19(1):199.

    Article  PubMed  PubMed Central  Google Scholar 

  52. W.D. Travis EB, A.P. Burke, A. Marx, A.G. Nicholson (Eds.). WHO classification of tumours of the lung, pleura, thymus and heart (4th ed.). International Agency for Research on Cancer, Lyon, France; 2015.

  53. Pezeshk A, Petrick N, Chen W, Sahiner B. Seamless Lesion Insertion for Data Augmentation in CAD Training. IEEE Trans Med Imaging. 2017; 36(4):1005-1015.

    Article  PubMed  Google Scholar 

  54. Gevaert O, Xu J, Hoang CD, et al. Non–Small Cell Lung Cancer: Identifying Prognostic Imaging Biomarkers by Leveraging Public Gene Expression Microarray Data—Methods and Preliminary Results. Radiology. 2012; 264(2):387-396.

    Article  PubMed  PubMed Central  Google Scholar 

  55. Bakr S, Gevaert O, Echegaray S, et al. Data for NSCLC Radiogenomics Collection. In: Archive TCI, ed2017.

  56. Bakr S, Gevaert O, Echegaray S, et al. A radiogenomic dataset of non-small cell lung cancer. Scientific Data. 2018; 5:180202.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  57. Schuurbiers OCJ, Meijer TWH, Kaanders JHAM, et al. Glucose Metabolism in NSCLC Is Histology-Specific and Diverges the Prognostic Potential of 18FDG-PET for Adenocarcinoma and Squamous Cell Carcinoma. J Thorac Oncol. 2014; 9(10):1485-1493.

    Article  CAS  PubMed  Google Scholar 

  58. Liu J, Cui J, Liu F, Yuan Y, Guo F, Zhang G. Multi-subtype classification model for non-small cell lung cancer based on radiomics: SLS model. Med Phys. 2019; 46(7):3091-3100.

    Article  PubMed  Google Scholar 

  59. Neto ACdS, Diniz PHB, Diniz JOB, et al. Diagnosis of Non-Small Cell Lung Cancer Using Phylogenetic Diversity in Radiomics Context. Image Analysis and Recognition. 2018:598–604.

  60. Han Y, Ma Y, Wu Z, et al. Histologic subtype classification of non-small cell lung cancer using PET/CT images. Eur J Nucl Med Mol Imaging. 2020.

Download references

Funding

This work was partially supported by the National Natural Science Foundation of China (Nos. 61871251, 62027901 , 61601019, 61871022), the 111 Project (No. B13003), the Fundamental Research Funds for Central Universities, and the Beijing Natural Science Foundation (7202102).

Author information

Author notes

  1. Yang Gao and Fan Song contributed equally to this work.

Authors and Affiliations

  1. Department of Biomedical Engineering, School of Medicine, Tsinghua University, Beijing, China

    Yang Gao & Jianwen Luo

  2. Beijing Advanced Innovation Center for Biomedical Engineering, Beihang University, Beijing, 100083, China

    Fan Song, Peng Zhang, Jian Liu, Jingjing Cui & Guanglei Zhang

  3. School of Biological Science and Medical Engineering, Beihang University, Beijing, 100083, China

    Fan Song, Peng Zhang, Jian Liu, Jingjing Cui & Guanglei Zhang

  4. Medical Engineering Management Office, Shandong Provincial Hospital Affiliated To Shandong University, Jinan, 250021, China

    Yingying Ma

  5. Center for Biomedical Imaging Research, Tsinghua University, Beijing, China

    Jianwen Luo

Authors
  1. Yang Gao
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Fan Song
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Peng Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Jian Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Jingjing Cui
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Yingying Ma
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Guanglei Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Jianwen Luo
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding authors

Correspondence to Guanglei Zhang or Jianwen Luo.

Additional information

Publisher's Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Supplementary Information

Below is the link to the electronic supplementary material.

Supplementary file1 (DOCX 586 KB)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Gao, Y., Song, F., Zhang, P. et al. Improving the Subtype Classification of Non-small Cell Lung Cancer by Elastic Deformation Based Machine Learning. J Digit Imaging 34, 605–617 (2021). https://doi.org/10.1007/s10278-021-00455-0

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10278-021-00455-0

Keywords

Search

Navigation