arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.01871eess.IVcs.CV
收藏

用于乳腺密度分类的联邦学习：真实世界的实现

Federated Learning for Breast Density Classification: A Real-World Implementation

NVIDIA（英伟达）；Massachusetts General Hospital（麻省总医院）；Mayo Clinic（梅奥诊所）；Stanford University（斯坦福大学）；American College of Radiology（美国放射学会）；Diagnósticos da América (DASA)（美国诊断公司（DASA））
Holger R. Roth, Ken Chang, Praveer Singh, Nir Neumark, Wenqi Li, Vikash Gupta, Sharut Gupta, Liangqiong Qu, Alvin Ihsani, Bernardo C. Bizzo, Yuhong Wen, Varun B… 展开作者

Holger R. Roth, Ken Chang, Praveer Singh, Nir Neumark, Wenqi Li, Vikash Gupta, Sharut Gupta, Liangqiong Qu, Alvin Ihsani, Bernardo C. Bizzo, Yuhong Wen, Varun Buch, Meesam Shah, Felipe Kitamura, Matheus Mendonça, Vitor Lavor, Ahmed Harouni, Colin Compas, Jesse Tetreault, Prerna Dogra, Yan Cheng, Selnur Erdal, Richard White, Behrooz Hashemian, Thomas Schultz, Miao Zhang, Adam McCarthy, B. Min Yun, Elshaimaa Sharaf, Katharina V. Hoebel, Jay B. Patel, Bryan Chen, Sean Ko, Evan Leibovitz, Etta D. Pisano, Laura Coombs, Daguang Xu, Keith J. Dreyer, Ittai Dayan, Ram C. Naidu, Mona Flores, Daniel Rubin, Jayashree Kalpathy-Cramer

备注：
Accepted at the 1st MICCAI Workshop on "Distributed And Collaborative Learning"; add citation to Fig. 1 & 2 and update Fig. 5; fix typo in affiliations
发表信息：
In: Albarqouni S. et al. (eds) Domain Adaptation and Representation Transfer, and Distributed and Collaborative Learning. DART 2020, DCL 2020. Lecture Notes in Computer Science, vol 12444. Springer, Cham
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

摘要：

构建强大的基于深度学习的模型需要大量不同的训练数据。在本研究中，我们研究了使用联邦学习（FL）在现实世界的协作环境中构建医学成像分类模型。来自世界各地的七家临床机构加入了FL的工作，训练基于乳腺成像、报告和数据系统（BI-RADS）的乳腺密度分类模型。我们表明，尽管来自所有站点的数据集之间存在很大差异（乳腺X射线摄影系统，类分布和数据集大小），并且没有集中数据，但我们可以成功地在联邦中训练AI模型。结果表明，使用FL训练的模型平均比仅使用研究所本地数据训练的模型好6.3%。此外，我们显示了45.8%的相对改善模型的泛化时，其他参与网站的测试数据进行评估。

英文摘要：

Building robust deep learning-based models requires large quantities of diverse training data. In this study, we investigate the use of federated learning (FL) to build medical imaging classification models in a real-world collaborative setting. Seven clinical institutions from across the world joined this FL effort to train a model for breast density classification based on Breast Imaging, Reporting & Data System (BI-RADS). We show that despite substantial differences among the datasets from all sites (mammography system, class distribution, and data set size) and without centralizing data, we can successfully train AI models in federation. The results show that models trained using FL perform 6.3% on average better than their counterparts trained on an institute's local data alone. Furthermore, we show a 45.8% relative improvement in the models' generalizability when evaluated on the other participating sites' testing data.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑