arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2108.02559cs.CV
收藏

MS-KD:使用多个二进制标记数据集的多器官分割

MS-KD: Multi-Organ Segmentation with Multiple Binary-Labeled Datasets

Cooperative Medianet Innovation Center, Shanghai Jiao Tong University(上海交通大学媒体网络协同创新中心)

Shixiang Feng, Yuhang Zhou, Xiaoman Zhang, Ya Zhang, Yanfeng Wang

摘要:

在3D医学图像中注释多个器官是耗时且昂贵的。同时,存在许多单器官数据集,其中一个特定的器官注释。本文研究了如何利用一组二进制标记的数据集来学习多器官分割模型。提出了一种新的多教师单学生知识蒸馏(MS-KD)框架,教师模型是预先训练好的单器官分割网络,学生模型是多器官分割网络.考虑到每个教师关注不同的器官,基于区域的监督方法,包括逻辑明智的监督和特征明智的监督,提出。每个教师在两个区域监督学生,器官区域,教师被认为是专家,背景区域,所有教师都同意。在三个公开的单器官数据集和一个多器官数据集上的大量实验证明了所提出的MS-KD框架的有效性。

英文摘要:

Annotating multiple organs in 3D medical images is time-consuming and costly. Meanwhile, there exist many single-organ datasets with one specific organ annotated. This paper investigates how to learn a multi-organ segmentation model leveraging a set of binary-labeled datasets. A novel Multi-teacher Single-student Knowledge Distillation (MS-KD) framework is proposed, where the teacher models are pre-trained single-organ segmentation networks, and the student model is a multi-organ segmentation network. Considering that each teacher focuses on different organs, a region-based supervision method, consisting of logits-wise supervision and feature-wise supervision, is proposed. Each teacher supervises the student in two regions, the organ region where the teacher is considered as an expert and the background region where all teachers agree. Extensive experiments on three public single-organ datasets and a multi-organ dataset have demonstrated the effectiveness of the proposed MS-KD framework.

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。

↑