Contour Transformer Network for One-Shot Segmentation of Anatomical Structures

Accurate segmentation of anatomical structures is vital for medical image analysis. The state-of-the-art accuracy is typically achieved by supervised learning methods, where gathering the requisite expert-labeled image annotations in a scalable manner remains a main obstacle. Therefore, annotation-e...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on medical imaging 2021-10, Vol.40 (10), p.2672-2684
Main Authors: Lu, Yuhang, Zheng, Kang, Li, Weijian, Wang, Yirui, Harrison, Adam P., Lin, Chihung, Wang, Song, Xiao, Jing, Lu, Le, Kuo, Chang-Fu, Miao, Shun
Format: Article
Language:English
Subjects:
Anatomical structure
Anatomy
Biomedical imaging
Contours
Deep learning
Evolution
graph convolutional network
human-in-the-loop
Image analysis
Image annotation
Image processing
Image segmentation
Machine learning
Medical imaging
one-shot segmentation
Production methods
Shape
Task analysis
Teaching methods
Training
Transformers
X-ray imaging
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Accurate segmentation of anatomical structures is vital for medical image analysis. The state-of-the-art accuracy is typically achieved by supervised learning methods, where gathering the requisite expert-labeled image annotations in a scalable manner remains a main obstacle. Therefore, annotation-efficient methods that permit to produce accurate anatomical structure segmentation are highly desirable. In this work, we present Contour Transformer Network (CTN), a one-shot anatomy segmentation method with a naturally built-in human-in-the-loop mechanism. We formulate anatomy segmentation as a contour evolution process and model the evolution behavior by graph convolutional networks (GCNs). Training the CTN model requires only one labeled image exemplar and leverages additional unlabeled data through newly introduced loss functions that measure the global shape and appearance consistency of contours. On segmentation tasks of four different anatomies, we demonstrate that our one-shot learning method significantly outperforms non-learning-based methods and performs competitively to the state-of-the-art fully supervised deep learning methods. With minimal human-in-the-loop editing feedback, the segmentation performance can be further improved to surpass the fully supervised methods.
ISSN:0278-0062
1558-254X
DOI:10.1109/TMI.2020.3043375