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

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...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Feng, Shixiang, Zhou, Yuhang, Zhang, Xiaoman, Zhang, Ya, Wang, Yanfeng
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 05.08.2021
Subjects
Datasets
Distillation
Image segmentation
Medical imaging
Organs
Supervision
Teachers
Online AccessGet full text

Cover

More Information
Summary: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.
ISSN:2331-8422