Semi-Supervised 3D Medical Image Segmentation Via Boundary-Aware Consistent Hidden Representation Learning
Lists
Only you see this
Abstract
This paper proposes a novel Boundary-aware Consistent Hidden Representation Learning Network (BA-CHRLN), which contains two branches for semi-supervised 3D medical image segmentation. Inspired by the contrastive learning, the two branches share the same encoder and each has its individual decoder, namely supervised decoder and unsupervised one. A stop-gradient operation is also utilized to prevent collapsing of solutions. Taking the unlabeled images as references, BA-CHRLN imposes the consistency by applying a perturbation on the high-level hidden feature representations, which significantly improves the encoder’s representation and the network’s robustness. A boundary-aware map is further introduced to capture the organ’s boundary without any prior knowledge and additional parameters. Experiments on the Left Atrium (LA) benchmark dataset demonstrate the effectiveness of the BA-CHRLN.
BibTeX
@inproceedings{liu2022semi,
author = {Linhu Liu and Jiang Tian and Xiangqian Cheng and Zhongchao Shi and Jianping Fan and Yong Rui},
title = {{Semi-Supervised 3D Medical Image Segmentation Via Boundary-Aware Consistent Hidden Representation Learning}},
booktitle = {ICIP},
year = {2022},
url = {https://openreview.net/forum?id=eSUvDitIEU},
}Loading related content...