Comparison of Deep Learning Approaches for Multi-Label Chest X-Ray Classification

Abstract

The increased availability of labeled X-ray image archives (e.g. ChestX-ray14 dataset) has triggered a growing interest in deep learning techniques. To provide better insight into the different approaches, and their applications to chest X-ray classification, we investigate a powerful network architecture in detail: the ResNet-50. Building on prior work in this domain, we consider transfer learning with and without fine-tuning as well as the training of a dedicated X-ray network from scratch. To leverage the high spatial resolution of X-ray data, we also include an extended ResNet-50 architecture, and a network integrating non-image data (patient age, gender and acquisition type) in the classification process. In a concluding experiment, we also investigate multiple ResNet depths (i.e. ResNet-38 and ResNet-101). In a systematic evaluation, using 5-fold re-sampling and a multi-label loss function, we compare the performance of the different approaches for pathology classification by ROC statistics and analyze differences between the classifiers using rank correlation. Overall, we observe a considerable spread in the achieved performance and conclude that the X-ray-specific ResNet-38, integrating non-image data yields the best overall results. Furthermore, class activation maps are used to understand the classification process, and a detailed analysis of the impact of non-image features is provided.

Full text

Its licence does not allow us to show the full text. Read it at PubMed Central:

References 25

1. 1.

   Commission, C. Q. Queen Alexandra hospital quality report. Available at, https://www.cqc.org.uk/location/RHU03 (2017).

   Not in our library

2. 2.

   Krizhevsky, A., Sutskever, I. & Hinton, G. E. Imagenet classification with deep convolutional neural networks. In Advances in neural information processing systems, 1097–1105 (2012).

   Not in our library

3. 3.

   Szegedy, C. et al. Going deeper with convolutions. In 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 1–9, 10.1109/CVPR.2015.7298594 (2015).

   Not in our library

4. 4.

   Simonyan, K. & Zisserman, A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014).

   Not in our library

5. 5.

   He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770–778, 10.1109/CVPR.2016.90 (2016).

   Not in our library

6. 6.

   Bar, Y. et al. Chest pathology detection using deep learning with non-medical training. In 2015 IEEE 12th International Symposium on Biomedical Imaging (ISBI), 294–297 (Citeseer, 2015).

   Not in our library

7. 7.

   Demner-Fushman D, et al. Preparing a collection of radiology examinations for distribution and retrieval. J. Am. Med. Informatics Assoc. 2015;23:304-310.

   Not in our library10.1093/jamia/ocv080

8. 8.

   Wang, X. et al. Chestx-ray8: Hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 3462–3471, 10.1109/CVPR.2017.369 (2017).

   Not in our library

9. 9.

   Yao, L. et al. Learning to diagnose from scratch by exploiting dependencies among labels. arXiv preprint arXiv:1710.10501 (2017).

   Not in our library

10. 10.

    Huang, G., Liu, Z., v. d. Maaten, L. & Weinberger, K. Q. Densely connected convolutional networks. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2261–2269, 10.1109/CVPR.2017.243 (2017).

    Not in our library

11. 11.

    Li, Z. et al. Thoracic disease identification and localization with limited supervision. In 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, 8290–8299, 10.1109/CVPR.2018.00865 (2018).

    Not in our library

12. 12.

    Rajpurkar, P. et al. Chexnet: Radiologist-level pneumonia detection on chest x-rays with deep learning. arXiv preprint arXiv:1711.05225 (2017).

    Not in our library

13. 13.

    Yao, L., Prosky, J., Poblenz, E., Covington, B. & Lyman, K. Weakly supervised medical diagnosis and localization from multiple resolutions. arXiv preprint arXiv:1803.07703 (2018).

    Not in our library

14. 14.

    Guendel, S. et al. Learning to recognize abnormalities in chest x-rays with location-aware dense networks. arXiv preprint arXiv:1803.04565 (2018).

    Not in our library

15. 15.

    He, K., Zhang, X., Ren, S. & Sun, J. Identity mappings in deep residual networks. In Computer Vision – ECCV 2016, 630–645 (Springer International Publishing, 2016).

    Not in our library

16. 16.

    Pan SJ, Yang Q. A survey on transfer learning. IEEE Transactions on Knowl. Data Eng. 2010;22:1345-1359.

    Not in our library10.1109/tkde.2009.191

17. 17.

    Yosinski, J., Clune, J., Bengio, Y. & Lipson, H. How transferable are features in deep neural networks? In Advances in neural information processing systems, 3320–3328 (2014).

    Not in our library

18. 18.

    Razavian, A. S., Azizpour, H., Sullivan, J. & Carlsson, S. Cnn features off-the-shelf: An astounding baseline for recognition. In 2014 IEEE Conference on Computer Vision and Pattern Recognition Workshops, 512–519, 10.1109/CVPRW.2014.131 (2014).

    Not in our library

19. 19.

    Russakovsky O, et al. Imagenet large scale visual recognition challenge. Int. J. Comput. Vis. 2015;115:211-252.

    Not in our library10.1007/s11263-015-0816-y

20. 20.

    Molinaro AM, Simon R, Pfeiffer RM. Prediction error estimation: a comparison of resampling methods. Bioinforma. 2005;21:3301-3307.

    Not in our library10.1093/bioinformatics/bti499

21. 21.

    Srivastava N, Hinton G, Krizhevsky A, Sutskever I, Salakhutdinov R. Dropout: A simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 2014;15:1929-1958.

    Not in our library

22. 22.

    Kingma, D. P. & Ba, J. L. Adam: A method for stochastic optimization. In International Conference on Learning Representations (ICLR) (2015).

    Not in our library

23. 23.

    Selvaraju, R. R. et al. Grad-cam: Visual explanations from deep networks via gradient-based localization. In 2017 IEEE International Conference on Computer Vision (ICCV), 618–626, 10.1109/ICCV.2017.74 (2017).

    Not in our library

24. 24.

    Oakden-Rayner, L. Exploring the ChestXray14 dataset: Problems. Available at, https://lukeoakdenrayner.wordpress.com/2017/12/18/ (2017).

    Not in our library

25. 25.

    Gohagan JK, Prorok PC, Hayes RB, Kramer B-S. The prostate, lung, colorectal and ovarian (PLCO) cancer screening trial of the national cancer institute: history, organization, and status. Control. clinical trials. 2000;21:251S-272S.

    Not in our library10.1016/s0197-2456(00)00097-0

Cited by papers we hold 1

• MRI-Based Brain Tumor Classification Using Ensemble of Deep Features and Machine Learning Classifiers · 2021
  No notice

Reads

A person counts once a day per paper. We keep no cookie and no address: a reader is a hash that changes every day. Any month under five reads shows no number.