Multi-institutional Collaborations for Improving Deep Learning-based Magnetic Resonance Image Reconstruction Using Federated Learning.
Multi-institutional Collaborations for Improving Deep Learning-based Magnetic Resonance Image Reconstruction Using Federated Learning.
复制标题
多机构合作改进基于深度学习的联合学习磁共振图像重建。
DOI：
10.1109/cvpr46437.2021.00245
复制
发表时间：
2021-06
期刊：
影响因子：
--
通讯作者：
Patel, Vishal M.
中科院分区：
文献类型：
--
作者：
Guo, Pengfei;Wang, Puyang;Zhou, Jinyuan;Jiang, Shanshan;Patel, Vishal M.
从欠采样数据中快速、准确地重建磁共振(MR)图像在许多临床应用中具有重要意义。近年来，基于深度学习的方法在磁共振图像重建中表现出了优异的性能。然而，这些方法需要大量的数据，由于高昂的获取成本和医疗数据隐私法规，这些数据很难收集和共享。为了克服这一挑战，我们提出了一种基于联合学习(FL)的解决方案，在该方案中，我们利用了不同机构提供的磁共振数据，同时保护了患者的隐私。然而，由于多个机构收集的数据具有不同的传感器、疾病类型和采集协议等原因，使用FL设置训练的模型的泛化能力仍然可能是次优的。为了规避这一挑战，我们提出了一种跨站点的磁共振图像重建建模方法，其中学习到的不同源站点之间的中间潜在特征与目标站点的潜在特征的分布一致。通过大量的实验，为磁共振图像重建提供了关于FL的各种见解。实验结果表明，该框架在不损害患者隐私的情况下，利用多机构数据实现改进的MR图像重建是一个有前途的方向。我们的代码可以在https://github.com/guopengf/FL-MRCM.上找到
Fast and accurate reconstruction of magnetic resonance (MR) images from under-sampled data is important in many clinical applications. In recent years, deep learning-based methods have been shown to produce superior performance on MR image reconstruction. However, these methods require large amounts of data which is difficult to collect and share due to the high cost of acquisition and medical data privacy regulations. In order to overcome this challenge, we propose a federated learning (FL) based solution in which we take advantage of the MR data available at different institutions while preserving patients’ privacy. However, the generalizability of models trained with the FL setting can still be suboptimal due to domain shift, which results from the data collected at multiple institutions with different sensors, disease types, and acquisition protocols, etc. With the motivation of circumventing this challenge, we propose a cross-site modeling for MR image reconstruction in which the learned intermediate latent features among different source sites are aligned with the distribution of the latent features at the target site. Extensive experiments are conducted to provide various insights about FL for MR image reconstruction. Experimental results demonstrate that the proposed framework is a promising direction to utilize multi-institutional data without compromising patients’ privacy for achieving improved MR image reconstruction. Our code is available at https://github.com/guopengf/FL-MRCM.
登录
查看更多内容
DOI：
10.1007/978-3-030-59713-9_11
发表时间：
2020-10
期刊：
Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention
影响因子：
--
作者：
Guo P;Wang P;Zhou J;Patel VM;Jiang S
通讯作者：
Jiang S
DOI：
10.1158/1078-0432.ccr-18-1233
发表时间：
2019-01-15
期刊：
Clinical cancer research : an official journal of the American Association for Cancer Research
影响因子：
--
作者：
Jiang S;Eberhart CG;Lim M;Heo HY;Zhang Y;Blair L;Wen Z;Holdhoff M;Lin D;Huang P;Qin H;Quinones-Hinojosa A;Weingart JD;Barker PB;Pomper MG;Laterra J;van Zijl PCM;Blakeley JO;Zhou J
通讯作者：
Zhou J
影响因子：
2.5
作者：
Candès, EJ;Romberg, J;Tao, T
通讯作者：
Tao, T
影响因子：
10.6
作者：
Han, Yoseob;Sunwoo, Leonard;Ye, Jong Chul
通讯作者：
Ye, Jong Chul
影响因子：
10.9
作者：
Li X;Gu Y;Dvornek N;Staib LH;Ventola P;Duncan JS
通讯作者：
Duncan JS