Distributed contrastive learning for medical image segmentation
Distributed contrastive learning for medical image segmentation
复制标题
用于医学图像分割的分布式对比学习
DOI：
10.1016/j.media.2022.102564
复制
发表时间：
2022
影响因子：
10.9
通讯作者：
Hu, Jingtong
中科院分区：
文献类型：
--
作者：
Wu, Yawen;Zeng, Dewen;Wang, Zhepeng;Shi, Yiyu;Hu, Jingtong
有监督的深度学习需要大量的标记数据才能实现高性能。然而，在医学影像分析中，每个站点可能只有有限的数据和标签，这使得学习效率低下。联邦学习（FL）可以从分散的数据中学习共享模型。但传统的 FL 需要完全标记的数据进行训练，获取成本非常昂贵。自监督对比学习（CL）可以从未标记的数据中学习进行预训练，然后使用有限的注释进行微调。然而，当在 FL 中采用 CL 时，每个站点上有限的数据多样性使得联邦对比学习（FCL）无效。在这项工作中，我们提出了两个联合自监督学习框架，用于具有有限注释的体积医学图像分割。第一个具有高精度，适合具有高速连接的高性能服务器。第二种特点是通信成本较低，适合移动设备。在第一个框架中，在 FCL 期间交换特征，为每个站点提供不同的对比数据，以实现有效的本地 CL，同时保持原始数据的私密性。全局结构匹配将本地和远程特征对齐，以在不同站点之间形成统一的特征空间。在第二个框架中，为了减少特征交换的通信成本，我们提出了一种不依赖负样本的优化方法 FCLOpt。为了减少模型下载的通信，我们提出了预测目标网络参数的预测目标网络更新（PTNU）。基于PTNU，我们提出距离预测（DP）来删除目标网络的大部分上传。心脏 MRI 数据集的实验表明，与最先进的技术相比，所提出的两个框架显着提高了分割和泛化性能。
Supervised deep learning needs a large amount of labeled data to achieve high performance. However, in medical imaging analysis, each site may only have a limited amount of data and labels, which makes learning ineffective. Federated learning (FL) can learn a shared model from decentralized data. But traditional FL requires fully-labeled data for training, which is very expensive to obtain. Self-supervised contrastive learning (CL) can learn from unlabeled data for pre-training, followed by fine-tuning with limited annotations. However, when adopting CL in FL, the limited data diversity on each site makes federated contrastive learning (FCL) ineffective. In this work, we propose two federated self-supervised learning frameworks for volumetric medical image segmentation with limited annotations. The first one features high accuracy and fits high-performance servers with high-speed connections. The second one features lower communication costs, suitable for mobile devices. In the first framework, features are exchanged during FCL to provide diverse contrastive data to each site for effective local CL while keeping raw data private. Global structural matching aligns local and remote features for a unified feature space among different sites. In the second framework, to reduce the communication cost for feature exchanging, we propose an optimized method FCLOpt that does not rely on negative samples. To reduce the communications of model download, we propose the predictive target network update (PTNU) that predicts the parameters of the target network. Based on PTNU, we propose the distance prediction (DP) to remove most of the uploads of the target network. Experiments on a cardiac MRI dataset show the proposed two frameworks substantially improve the segmentation and generalization performance compared with state-of-the-art techniques.