A Federated Hybrid-Supervised Learning for Medical Image Segmentation With Heterogeneous Annotation Guidance
Shenhai Zheng, Sian Wen, Congyu Li, Weisheng Li, Xinbo Gao, Patrick S. P. Wang, Laquan Li
Chongqing University of Posts and Telecommunications Northeastern University
阅读操作
确认中在文库中上传 PDF 后可生成中文音频讲解。
摘要与影响
Federated Learning (FL) is an advanced technology that tackles the challenge of blocked data arising from privacy concerns, enabling the training of deep learning models without the need for data sharing. However, FL faces difficulties with heterogeneous data and limited annotations in medical image segmentation. Motivated by this discovery, this study proposes a novelFederated Hybrid-SupervisedLearning with HeterogeneousAnnotationGuidance (FedSLAG) that explores various types of annotations in medical image segmentation. To focus more on the weakly-supervised and unsupervised scenarios in hybrid-supervised learning, a federated Gaussian enhancement module was proposed for heterogeneous annotations (e.g., point-level labels and scribble-level labels). The feature extraction module combines the features of multiple weakly-supervised clients and establishes the correlation of similar pixels, thus making up for the deficiency of scarce annotations and the insufficient feature extraction capability of a single machine. Then, a two-stage broadcast mechanism based on supervision sparsity was proposed to alleviate optimization deviation in local models. Experiments on breast tumor and skin lesion segmentation tasks demonstrate significant efficiency gains as well as highly competitive segmentation accuracy in many hybrid-supervised situations.
逐年被引趋势
暂无年度引用数据
关键指标
同类平均 = 1
同领域 · 同年份 · 同类型
Google Scholar 与 OpenAlex 的被引统计范围不同,数值存在差异属正常。
AI 辅助阅读
依据:摘要
可就本文提问;依据不足时会说明。
学术脉络
学科主题
计算机 / AIMedical Image Segmentation Techniques
Privacy-Preserving Technologies in Data · Domain Adaptation and Few-Shot Learning