Abstract
Federated learning (FL), a relatively new area of research in medical image analysis, enables collaborative learning of a federated deep learning model without sharing the data of participating clients. In this paper, we propose FedDropoutAvg, a new federated learning approach for detection of tumor in images of colon tissue slides. The proposed method leverages the power of dropout, a commonly employed scheme to avoid overfitting in neural networks, in both client selection and federated averaging processes. We examine FedDropoutAvg against other FL benchmark algorithms for two different image classification tasks using a publicly available multi-site histopathology image dataset. We train and test the proposed model on a large dataset consisting of 1.2 million image tiles from 21 different sites. For testing the generalization of all models, we select held-out test sets from sites that were not used during training. We show that the proposed approach outperforms other FL methods and reduces the performance gap (to less than 3% in terms of AUC on independent test sites) between FL and a central deep learning model that requires all data to be shared for centralized training, demonstrating the potential of the proposed FedDropoutAvg model to be more generalizable than other state-of-the-art federated models. To the best of our knowledge, ours is the first study to effectively utilize the dropout strategy in a federated setting for tumor detection in histology images.
Similar content being viewed by others
Availability of Data and Materials
This research study was conducted retrospectively using human subject data made available in open access by TCGA Research Network (https://www.cancer.gov/tcga). Ethical approval was not required as confirmed by the license attached with the open-access data.
References
Litjens G, Kooi T, Bejnordi BE, et al (2017) A survey on deep learning in medical image analysis. Medical image analysis 42:60–88
Konečnỳ J, McMahan HB, Ramage D, et al (2016) Federated optimization: Distributed machine learning for on-device intelligence. arXiv preprint arXiv:1610.02527
McMahan B, Moore E, Ramage D, et al (2017) Communication-efficient learning of deep networks from decentralized data. In: Artificial Intelligence and Statistics, PMLR, pp 1273–1282
Kaissis GA, Makowski MR, Rückert D, et al (2020) Secure, privacy-preserving and federated machine learning in medical imaging. Nature Machine Intelligence 2(6):305–311
Li T, Sahu AK, Zaheer M, et al (2018) Federated optimization in heterogeneous networks. arXiv preprint arXiv:1812.06127
Arivazhagan MG, Aggarwal V, Singh AK, et al (2019) Federated learning with personalization layers. arXiv preprint arXiv:1912.00818
Li X, Jiang M, Zhang X, et al (2021) Fedbn: Federated learning on non-iid features via local batch normalization. arXiv preprint arXiv:2102.07623
Sun B, Huo H, Yang Y, et al (2021) Partialfed: Cross-domain personalized federated learning via partial initialization. Advances in Neural Information Processing Systems 34:23,309–23,320
Tan AZ, Yu H, Cui L, et al (2022) Towards personalized federated learning. IEEE Transactions on Neural Networks and Learning Systems
Liu Q, Chen C, Qin J, et al (2021) Feddg: Federated domain generalization on medical image segmentation via episodic learning in continuous frequency space. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pp 1013–1023
Achille A, Soatto S (2018) Information dropout: Learning optimal representations through noisy computation. IEEE transactions on pattern analysis and machine intelligence 40(12):2897–2905
Baldi P, Sadowski P (2014) The dropout learning algorithm. Artificial intelligence 210:78–122
Hinton GE, Srivastava N, Krizhevsky A, et al (2012) Improving neural networks by preventing co-adaptation of feature detectors. arXiv preprint arXiv:1207.0580
Srivastava N, Hinton G, Krizhevsky A, et al (2014) Dropout: a simple way to prevent neural networks from overfitting. The journal of machine learning research 15(1):1929–1958
Bonawitz K, Eichner H, Grieskamp W, et al (2019) Towards federated learning at scale: System design. arXiv preprint arXiv:1902.01046
Li T, Sahu AK, Talwalkar A, et al (2020a) Federated learning: Challenges, methods, and future directions. IEEE Signal Processing Magazine 37(3):50–60
Li X, Huang K, Yang W, et al (2019b) On the convergence of fedavg on non-iid data. arXiv preprint arXiv:1907.02189
Rieke N, Hancox J, Li W, et al (2020) The future of digital health with federated learning. NPJ digital medicine 3(1):1–7
Sheller MJ, Reina GA, Edwards B, et al (2018) Multi-institutional deep learning modeling without sharing patient data: A feasibility study on brain tumor segmentation. In: International MICCAI Brainlesion Workshop, Springer, pp 92–104
Li W, Milletarì F, Xu D, et al (2019a) Privacy-preserving federated brain tumour segmentation. In: International Workshop on Machine Learning in Medical Imaging, Springer, pp 133–141
Li X, Gu Y, Dvornek N, et al (2020b) Multi-site fmri analysis using privacy-preserving federated learning and domain adaptation: Abide results. Medical Image Analysis 65:101,765
Pati S, Baid U, Edwards B, et al (2022) Federated learning enables big data for rare cancer boundary detection. Nature communications 13(1):7346
Roy AG, Siddiqui S, Pölsterl S, et al (2019) Braintorrent: A peer-to-peer environment for decentralized federated learning. arXiv preprint arXiv:1905.06731
Sarhan MH, Navab N, Eslami A, et al (2020) On the fairness of privacy-preserving representations in medical applications. In: Domain Adaptation and Representation Transfer, and Distributed and Collaborative Learning. Springer, p 140–149
Sheller MJ, Edwards B, Reina GA, et al (2020) Federated learning in medicine: facilitating multi-institutional collaborations without sharing patient data. Scientific reports 10(1):12,598
Silva S, Altmann A, Gutman B, et al (2020) Fed-biomed: A general open-source frontend framework for federated learning in healthcare. In: Domain Adaptation and Representation Transfer, and Distributed and Collaborative Learning. Springer, p 201–210
Remedios SW, Butman JA, Landman BA, et al (2020) Federated gradient averaging for multi-site training with momentum-based optimizers. In: Domain Adaptation and Representation Transfer, and Distributed and Collaborative Learning. Springer, p 170–180
Muthukrishnan R, Heyler A, Katti K, et al (2022) Mammodl: mammographic breast density estimation using federated learning. arXiv preprint arXiv:2206.05575
Roth HR, Chang K, Singh P, et al (2020) Federated learning for breast density classification: A real-world implementation. In: Domain Adaptation and Representation Transfer, and Distributed and Collaborative Learning. Springer, p 181–191
Wang P, Shen C, Roth HR, et al (2020) Automated pancreas segmentation using multi-institutional collaborative deep learning. In: Domain Adaptation and Representation Transfer, and Distributed and Collaborative Learning. Springer, p 192–200
Andreux M, du Terrail JO, Beguier C, et al (2020) Siloed federated learning for multi-centric histopathology datasets. In: Domain Adaptation and Representation Transfer, and Distributed and Collaborative Learning. Springer, p 129–139
Lu MY, Kong D, Lipkova J, et al (2020) Federated learning for computational pathology on gigapixel whole slide images. arXiv preprint arXiv:2009.10190
Baid U, Pati S, Kurc TM, et al (2022) Federated learning for the classification of tumor infiltrating lymphocytes. arXiv preprint arXiv:2203.16622
Foley P, Sheller MJ, Edwards B, et al (2022) Openfl: the open federated learning library. Physics in Medicine & Biology 67(21):214,001
Karargyris A, Umeton R, Sheller MJ, et al (2021) Medperf: open benchmarking platform for medical artificial intelligence using federated evaluation. arXiv preprint arXiv:2110.01406
Pati S, Baid U, Zenk M, et al (2021) The federated tumor segmentation (fets) challenge. arXiv preprint arXiv:2105.05874
Xi Y, Xu P (2021) Global colorectal cancer burden in 2020 and projections to 2040. Translational Oncology 14(10):101,174
Bilal M, Tsang YW, Ali M, et al (2022) Ai based pre-screening of large bowel cancer via weakly supervised learning of colorectal biopsy histology images. medRxiv
Kather JN, Pearson AT, Halama N, et al (2019) Deep learning can predict microsatellite instability directly from histology in gastrointestinal cancer. Nature medicine 25(7):1054–1056
Skrede OJ, De Raedt S, Kleppe A, et al (2020) Deep learning for prediction of colorectal cancer outcome: a discovery and validation study. The Lancet 395(10221):350–360
Wang KS, Yu G, Xu C, et al (2021) Accurate diagnosis of colorectal cancer based on histopathology images using artificial intelligence. BMC medicine 19(1):1–12
Bilal M, Raza SEA, Azam A, et al (2021) Development and validation of a weakly supervised deep learning framework to predict the status of molecular pathways and key mutations in colorectal cancer from routine histology images: a retrospective study. The Lancet Digital Health 3(12):e763–e772
Sinicrope FA, Sargent DJ (2012) Molecular pathways: microsatellite instability in colorectal cancer: prognostic, predictive, and therapeutic implications. Clinical cancer research 18(6):1506–1512
Otsu N (1979) A Threshold Selection Method from Gray-level Histograms. IEEE Trans on Systems, Man and Cybernetics 9(1):62–66. https://doi.org/10.1109/TSMC.1979.4310076, http://dx.doi.org/10.1109/TSMC.1979.4310076
He K, Zhang X, Ren S, et al (2016) Deep residual learning for image recognition. In: The IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), pp 770–778
Shaban M, Awan R, Fraz MM, et al (2020) Context-aware convolutional neural network for grading of colorectal cancer histology images. IEEE Trans on Med Imag pp 1–1. https://warwick.ac.uk/fac/sci/dcs/research/tia/data/extended_crc_grading/
Wu Y, He K (2018) Group normalization. In: Proc. of the European Conf. on Computer Vision (ECCV), pp 3–19
Hsieh K, Phanishayee A, Mutlu O, et al (2020) The non-iid data quagmire of decentralized machine learning. In: International Conference on Machine Learning, PMLR, pp 4387–4398
Bouacida N, Hou J, Zang H, et al (2021) Adaptive federated dropout: Improving communication efficiency and generalization for federated learning. In: IEEE INFOCOM 2021 - IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS), pp 1–6, https://doi.org/10.1109/INFOCOMWKSHPS51825.2021.9484526
Caldas S, Konečny J, McMahan HB, et al (2018) Expanding the reach of federated learning by reducing client resource requirements. arXiv preprint arXiv:1812.07210
Funding
This work was partly supported by the Department of Computer Science, University of Warwick, and partly by GSK.
Author information
Authors and Affiliations
Contributions
All authors conceptualized the study. GG was responsible for the drafting and final manuscript preparation, the software, the analysis of the results, and the preparation of figures and tables. NR designed the overall study setting with GG. MB contributed to data preparation. All analyzed, interpreted and helped to communicate the results. All provided significant writing, reviewing, and editing of all versions.
Corresponding authors
Ethics declarations
Competing Interests
NR is a Director and CSO of Histofy Ltd. NR declares that he is in receipt of research funding from AstraZeneca and GlaxoSmithKline (GSK) and is also a GSK Chair of Computational Pathology at the University of Warwick, UK. All other authors declare no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Gunesli, G., Bilal, M., Raza, S. et al. A Federated Learning Approach to Tumor Detection in Colon Histology Images. J Med Syst 47, 99 (2023). https://doi.org/10.1007/s10916-023-01994-5
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s10916-023-01994-5