MyThisYourThat for interpretable identification of systematic bias in federated learning for biomedical images.
Journal
NPJ digital medicine
ISSN: 2398-6352
Titre abrégé: NPJ Digit Med
Pays: England
ID NLM: 101731738
Informations de publication
Date de publication:
07 Sep 2024
07 Sep 2024
Historique:
received:
30
01
2024
accepted:
14
08
2024
medline:
7
9
2024
pubmed:
7
9
2024
entrez:
6
9
2024
Statut:
epublish
Résumé
Distributed collaborative learning is a promising approach for building predictive models for privacy-sensitive biomedical images. Here, several data owners (clients) train a joint model without sharing their original data. However, concealed systematic biases can compromise model performance and fairness. This study presents MyThisYourThat (MyTH) approach, which adapts an interpretable prototypical part learning network to a distributed setting, enabling each client to visualize feature differences learned by others on their own image: comparing one client's 'This' with others' 'That'. Our setting demonstrates four clients collaboratively training two diagnostic classifiers on a benchmark X-ray dataset. Without data bias, the global model reaches 74.14% balanced accuracy for cardiomegaly and 74.08% for pleural effusion. We show that with systematic visual bias in one client, the performance of global models drops to near-random. We demonstrate how differences between local and global prototypes reveal biases and allow their visualization on each client's data without compromising privacy.
Identifiants
pubmed: 39242810
doi: 10.1038/s41746-024-01226-1
pii: 10.1038/s41746-024-01226-1
doi:
Types de publication
Journal Article
Langues
eng
Pagination
238Informations de copyright
© 2024. The Author(s).
Références
Piccialli, F., Di Somma, V., Giampaolo, F., Cuomo, S. & Fortino, G. A survey on deep learning in medicine: Why, how and when? Inf. Fusion 66, 111–137 (2021).
Shen, D., Wu, G. & Suk, H.-I. Deep learning in medical image analysis. Annu. Rev. Biomed. Eng. 19, 221–248 (2017).
doi: 10.1146/annurev-bioeng-071516-044442
pubmed: 28301734
pmcid: 5479722
Landi, I. et al. Deep representation learning of electronic health records to unlock patient stratification at scale. npj Digit. Med. 3, 96 (2020).
doi: 10.1038/s41746-020-0301-z
pubmed: 32699826
pmcid: 7367859
Barnett, A. J. et al. Interpretable deep learning models for better clinician-AI communication in clinical mammography. In Proc. of SPIE Medical Imaging 2022: Image Perception, Observer Performance, and Technology Assessment, SPIE Digital Library (eds. Mello-Thoms, C. R. & Taylor-Phillips, S.), 12035, 1203507 (2022).
McMahan, H. B., Moore, E., Ramage, D., Hampson, S. & Arcas, B. A. Communication-efficient learning of deep networks from decentralized data. In Proc. of the 20th International Conference on Artificial Intelligence and Statistics (AISTATS) (ed. Lawrence, N.), 54, 1273–1282 (JMLR: W&CP, 2017).
Nguyen, D. C. et al. Federated learning for smart healthcare: a survey. ACM Comput. Surv. 55, 1–37 (2022).
doi: 10.1145/3453476
Rieke, N. et al. The future of digital health with federated learning. npj Digit. Med. 3, 1–7 (2020).
doi: 10.1038/s41746-020-00323-1
Nazir, S. & Kaleem, M. Federated learning for medical image analysis with deep neural networks. Diagnostics 13, 1532 (2023).
doi: 10.3390/diagnostics13091532
pubmed: 37174925
pmcid: 10177193
Islam, M., Reza, M. T., Kaosar, M. & Parvez, M. Z. Effectiveness of federated learning and CNN ensemble architectures for identifying brain tumors using MRI images. Neural Process. Lett. 55, 3779–3809 (2023).
doi: 10.1007/s11063-022-11014-1
Ribeiro, M. T., Singh, S. & Guestrin, C. “Why should I trust you?": explaining the predictions of any classifier. In Proc. of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Association for Computing Machinery (eds. Krishnapuram, B., Shah, M., Smola, A. J., Aggarwal, C., Shen D. & Rastogi, R.), 1135–1144 (2016).
Lundberg, S. & Lee, S.-I. A unified approach to interpreting model predictions. In Proc. of the 31st International Conference on Neural Information Processing Systems, Curran Associates Inc. (eds. von Luxburg, U., Guyon, I., Bengio, S., Wallach H. & Fergus, R.), 4768–4777 (2017).
Selvaraju, R. R. et al. Grad-CAM: visual explanations from deep networks via gradient-based localization. J. Comput. Vis. 128, 336–359 (2019).
Simonyan, K., Vedaldi, A. & Zisserman, A. Deep inside convolutional networks: visualising image classification models and saliency maps. In Workshop at International Conference on Learning Representations (2014).
Singh, A., Sengupta, S. & Lakshminarayanan, V. Explainable deep learning models in medical image analysis. J. Imaging 6, 52 (2020).
doi: 10.3390/jimaging6060052
pubmed: 34460598
pmcid: 8321083
Shrikumar, A., Greenside, P. & Kundaje, A. Learning important features through propagating activation differences. PMLR 70, 3145–3153 (2017).
Chen, H., Lundberg, S. & Lee, S.-I. Explaining Models by Propagating Shapley Values of Local Components 261–270 (Springer International Publishing, Cham, 2021).
Samek, W., Montavon, G., Vedaldi, A., Hansen, L. K. & Müller, K.-R. Explainable AI: Interpreting, Explaining and Visualizing Deep Learning (Springer, 2019).
Molnar, C. Interpretable Machine Learning (Independently published, 2023).
Adebayo, J. et al. Sanity checks for saliency maps. Adv. Neural Inf. Process. Syst. 31, 9505–9515 (2018).
Rudin, C. et al. Interpretable machine learning: fundamental principles and 10 grand challenges. Stat. Surv. 16, 1–85 (2022).
Sun, S., Woerner, S., Maier, A., Koch, L. M. & Baumgartner, C. F. Inherently interpretable multi-label classification using class-specific counterfactuals. Proc. Mach. Learn. Res. 227, 937–956 (2023).
Chen, C. et al. This looks like that: deep learning for interpretable image recognition. In Proc. of the 33rd International Conference on Neural Information Processing Systems, Curran Associates Inc. (eds. Wallach, H., Larochelle, H., Beygelzimer, A., d'Alché-Buc, F., Fox E. & Garnett, R.), 8930–8941 (2019).
Barnett, A. et al. A case-based interpretable deep learning model for classification of mass lesions in digital mammography. Nat. Mach. Intell. 3, 1067–1070 (2021).
doi: 10.1038/s42256-021-00423-x
Hase, P., Chen, C., Li, O. & Rudin, C. Interpretable image recognition with hierarchical prototypes. In Proc. of the 7th AAAI Conference on Human Computation & Crowdsourcing, PKP:PS (eds. Law, E. & Vaughan, J. W.), 7, 32–40 (2019).
Irvin, J. et al. Chexpert: a large chest radiograph dataset with uncertainty labels and expert comparison. In Proc. of the 33rd AAAI Conference on Artificial Intelligence (AAAI-19) (eds. Van Hentenryck, P. & Zhou, Z.-H.), 33, 590–597 (AAAI Press, 2019).
Jiménez-Sánchez, A., Juodelye, D., Chamberlain, B. & Cheplygina, V. Detecting shortcuts in medical images—a case study in chest X-rays. In Proc. of the IEEE 20th International Symposium on Biomedical Imaging (ISBI), (eds. Salvado, O. & Rittner, L.), 1–5 (IEEE, 2023).
Ser, J. D. et al. On generating trustworthy counterfactual explanations. Inf. Sci. 655, 119898 (2024).
doi: 10.1016/j.ins.2023.119898
Huang, G., Liu, Z., van der Maaten, L. & Weinberger, K. Q. Densely connected convolutional networks. In Proc. of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (ed. O’Conner, L.), 2261–2269 (IEEE, 2017).
Deng, J. et al. ImageNet: a large-scale hierarchical image database. In Proc. of IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (eds. Essa, I., Kang S. B. & Pollefeys, M.), 248–255 (IEEE, 2009).