journal article·2022-07-02Open access

Semi-Supervised Medical Image Classification Based on Attention and Intrinsic Features of Samples

Zhuohao Zhou, Chunyue Lu, Wenchao Wang, Wenhao Dang, Ke Gong

Applied Sciences· Volume 12· Issue 13

Abstract

The training of deep neural networks usually requires a lot of high-quality data with good annotations to obtain good performance. However, in clinical medicine, obtaining high-quality marker data is laborious and expensive because it requires the professional skill of clinicians. In this paper, based on the consistency strategy, we propose a new semi-supervised model for medical image classification which introduces a self-attention mechanism into the backbone network to learn more meaningful features in image classification tasks and uses the improved version of focal loss at the supervision loss to reduce the misclassification of samples. Finally, we add a consistency loss similar to the unsupervised consistency loss to encourage the model to learn more about the internal features of unlabeled samples. Our method achieved 94.02% AUC and 72.03% Sensitivity on the ISIC 2018 dataset and 79.74% AUC on the ChestX-ray14 dataset. These results show the effectiveness of our method in single-label and multi-label classification.
Source: crossref · Quality: baseline

Research context

OpenAlex topics: COVID-19 diagnosis using AI · AI in cancer detection · Radiomics and Machine Learning in Medical Imaging

SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.

Affiliations

Digital Design and Intelligent Manufacturing Laboratory, North University of China, Taiyuan 030051, China

References (42)

Show source-provided references
1. Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012). Imagenet classification with deep convolutional neural networks. Adv. Neural Inf. Process. Syst., 25.
2. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 27–30). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.10.1109/CVPR.2016.90 ↗
3. Ren, S., He, K., Girshick, R., and Sun, J. (2015). Faster r-cnn: Towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst., 28.
4. Sedai, S., Mahapatra, D., Hewavitharanage, S., Maetschke, S., and Garnavi, R. (2017, January 11–13). Semi-supervised segmentation of optic cup in retinal fundus images using variational autoencoder. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Quebec City, QC, Canada.10.1007/978-3-319-66185-8_9 ↗
5. Su, H., Shi, X., Cai, J., and Yang, L. (2019, January 13–17). Local and global consistency regularized mean teacher for semi-supervised nuclei classification. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Shenzhen, China.10.1007/978-3-030-32239-7_62 ↗
6. Feng, X., Yang, J., Laine, A.F., and Angelini, E.D. (2017, January 11–13). Discriminative localization in CNNs for weakly-supervised segmentation of pulmonary nodules. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Quebec City, QC, Canada.10.1007/978-3-319-66179-7_65 ↗
7. Kamnitsas, K., Baumgartner, C., Ledig, C., Newcombe, V., Simpson, J., Kane, A., Menon, D., Nori, A., Criminisi, A., and Rueckert, D. (2017, January 25–30). Unsupervised domain adaptation in brain lesion segmentation with adversarial networks. Proceedings of the International Conference on Information Processing in Medical Imaging, Boone, NC, USA.10.1007/978-3-319-59050-9_47 ↗
8. Bai, W., Oktay, O., Sinclair, M., Suzuki, H., Rajchl, M., Tarroni, G., Glocker, B., King, A., Matthews, P.M., and Rueckert, D. (2017, January 11–13). Semi-supervised learning for network-based cardiac MR image segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Quebec City, QC, Canada.10.1007/978-3-319-66185-8_29 ↗
9. Jin, Y., Cheng, K., Dou, Q., and Heng, P.A. (2019, January 13–17). Incorporating temporal prior from motion flow for instrument segmentation in minimally invasive surgery video. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Shenzhen, China.10.1007/978-3-030-32254-0_49 ↗
10. Virtual adversarial training: A regularization method for supervised and semi-supervised learning10.1109/TPAMI.2018.2858821 ↗
11. Chartsias, A., Joyce, T., Papanastasiou, G., Semple, S., Williams, M., Newby, D., Dharmakumar, R., and Tsaftaris, S.A. (2018, January 16–20). Factorised spatial representation learning: Application in semi-supervised myocardial segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Strasbourg, France.10.1007/978-3-030-00934-2_55 ↗
12. Nie, D., Gao, Y., Wang, L., and Shen, D. (2018, January 16–20). ASDNet: Attention based semi-supervised deep networks for medical image segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Strasbourg, France.10.1007/978-3-030-00937-3_43 ↗
13. Dong, N., Kampffmeyer, M., Liang, X., Wang, Z., Dai, W., and Xing, E. (2018, January 16–20). Unsupervised domain adaptation for automatic estimation of cardiothoracic ratio. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Strasbourg, France.10.1007/978-3-030-00934-2_61 ↗
14. Retinal image synthesis and semi-supervised learning for glaucoma assessment10.1109/TMI.2019.2903434 ↗
15. Aviles-Rivero, A.I., Papadakis, N., Li, R., Sellars, P., Fan, Q., Tan, R.T., and Schönlieb, C.B. (2019, January 13–17). GraphXNET—Chest X-Ray Classification under Extreme Minimal Supervision. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Shenzhen, China.
16. Transformation-consistent self-ensembling model for semisupervised medical image segmentation10.1109/TNNLS.2020.2995319 ↗
17. Li, X., Yu, L., Chen, H., Fu, C.W., and Heng, P.A. (2018). Semi-supervised skin lesion segmentation via transformation consistent self-ensembling model. arXiv.
18. Laine, S., and Aila, T. (2016). Temporal ensembling for semi-supervised learning. arXiv.
19. Cui, W., Liu, Y., Li, Y., Guo, M., Li, Y., Li, X., Wang, T., Zeng, X., and Ye, C. (2019, January 2–7). Semi-supervised brain lesion segmentation with an adapted mean teacher model. Proceedings of the International Conference on Information Processing in Medical Imaging, Hong Kong, China.10.1007/978-3-030-20351-1_43 ↗
20. Yu, L., Wang, S., Li, X., Fu, C.W., and Heng, P.A. (2019, January 13–17). Uncertainty-aware self-ensembling model for semi-supervised 3D left atrium segmentation. Proceedings of the International Conference on Medical Image Computing and Computer-Assisted Intervention, Shenzhen, China.10.1007/978-3-030-32245-8_67 ↗
21. Deep learning ensembles for melanoma recognition in dermoscopy images10.1147/JRD.2017.2708299 ↗
22. Automated melanoma recognition in dermoscopy images via very deep residual networks10.1109/TMI.2016.2642839 ↗
23. Attention residual learning for skin lesion classification10.1109/TMI.2019.2893944 ↗
24. Wang, X., Peng, Y., Lu, L., Lu, Z., Bagheri, M., and Summers, R.M. (2017, January 21–26). Chestx-ray8: Hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.369 ↗
25. Automated melanoma recognition10.1109/42.918473 ↗
26. Irvin, J., Rajpurkar, P., Ko, M., Yu, Y., Ciurea-Ilcus, S., Chute, C., Marklund, H., Haghgoo, B., Ball, R., and Shpanskaya, K. (February, January 27). Chexpert: A large chest radiograph dataset with uncertainty labels and expert comparison. Proceedings of the AAAI Conference on Artificial Intelligence, Honolulu, HI, USA.
27. Rajpurkar, P., Irvin, J., Zhu, K., Yang, B., Mehta, H., Duan, T., Ding, D., Bagul, A., Langlotz, C., and Shpanskaya, K. (2017). Chexnet: Radiologist-level pneumonia detection on chest x-rays with deep learning. arXiv.
28. Aviles-Rivero, A.I., Papadakis, N., Li, R., Sellars, P., Alsaleh, S.M., Tan, R.T., and Schönlieb, C.-B. (2019). Energy Models for Better Pseudo-Labels: Improving Semi-Supervised Classification with the 1-Laplacian Graph Energy. arXiv.
29. Tarvainen, A., and Valpola, H. (2017). Mean teachers are better role models: Weight-averaged consistency targets improve semi-supervised deep learning results. Adv. Neural Inf. Process. Syst., 30.
30. Park, J., Woo, S., Lee, J.Y., and Kweon, I.S. (2018). Bam: Bottleneck attention module. arXiv.
31. Lin, T.Y., Goyal, P., Girshick, R., He, K., and Dollar, P. (2017, January 22–29). Focal loss for dense object detection. Proceedings of the IEEE International Conference on Computer Vision, Venice, Italy.10.1109/ICCV.2017.324 ↗
32. Semi-supervised adversarial model for benign–malignant lung nodule classification on chest CT10.1016/j.media.2019.07.004 ↗
33. Yun, S., Han, D., Oh, S.J., Chun, S., Choe, J., and Yoo, Y. (November, January 27). Cutmix: Regularization strategy to train strong classifiers with localizable features. Proceedings of the IEEE/CVF International Conference on Computer Vision, Seoul, Korea.
34. French, G., Oliver, A., and Salimans, T. (2020). Milking cowmask for semi-supervised image classification. arXiv.
35. Certainty driven consistency loss on multi-teacher networks for semi-supervised learning10.1016/j.patcog.2021.108140 ↗
36. Semi-supervised medical image classification with relation-driven self-ensembling model10.1109/TMI.2020.2995518 ↗
37. Hu, J., Shen, L., and Sun, G. (2018, January 18–22). Squeeze-and-excitation networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA.10.1109/CVPR.2018.00745 ↗
38. Woo, S., Park, J., Lee, J.Y., and Kweon, S. (2018, January 8–14). Cbam: Convolutional block attention module. Proceedings of the European Conference on Computer Vision (ECCV), Munich, Germany.10.1007/978-3-030-01234-2_1 ↗
39. A tutorial on the cross-entropy method10.1007/s10479-005-5724-z ↗
40. Sergievskiy, N., and Ponamarev, A. (2019). Reduced focal loss: 1st place solution to xview object detection in satellite imagery. arXiv.
41. Huang, G., Liu, Z., Van Der Maaten, L., and Weinberger, K.Q. (2017, January 21–26). Densely connected convolutional networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Honolulu, HI, USA.10.1109/CVPR.2017.243 ↗
42. Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv.