IRUS Total

Enhancing MR image segmentation with realistic adversarial data augmentation

File Description SizeFormat 
1-s2.0-S1361841522002304-main.pdfPublished version3.01 MBAdobe PDFView/Open
Title: Enhancing MR image segmentation with realistic adversarial data augmentation
Authors: Chen, C
Qin, C
Ouyang, C
Li, Z
Wang, S
Qiu, H
Chen, L
Tarroni, G
Bai, W
Rueckert, D
Item Type: Journal Article
Abstract: The success of neural networks on medical image segmentation tasks typically relies on large labeled datasets for model training. However, acquiring and manually labeling a large medical image set is resource-intensive, expensive, and sometimes impractical due to data sharing and privacy issues. To address this challenge, we propose AdvChain, a generic adversarial data augmentation framework, aiming at improving both the diversity and effectiveness of training data for medical image segmentation tasks. AdvChain augments data with dynamic data augmentation, generating randomly chained photo-metric and geometric transformations to resemble realistic yet challenging imaging variations to expand training data. By jointly optimizing the data augmentation model and a segmentation network during training, challenging examples are generated to enhance network generalizability for the downstream task. The proposed adversarial data augmentation does not rely on generative networks and can be used as a plug-in module in general segmentation networks. It is computationally efficient and applicable for both low-shot supervised and semi-supervised learning. We analyze and evaluate the method on two MR image segmentation tasks: cardiac segmentation and prostate segmentation with limited labeled data. Results show that the proposed approach can alleviate the need for labeled data while improving model generalization ability, indicating its practical value in medical imaging applications.
Issue Date: Nov-2022
Date of Acceptance: 19-Aug-2022
URI: http://hdl.handle.net/10044/1/98087
DOI: 10.1016/j.media.2022.102597
ISSN: 1361-8415
Publisher: Elsevier
Start Page: 1
End Page: 15
Journal / Book Title: Medical Image Analysis
Volume: 82
Copyright Statement: © 2022 The Author(s). Published by Elsevier B.V. This is an open access article under the CC BY license (http://creativecommons.org/licenses/by/4.0/).
Sponsor/Funder: Engineering and Physical Sciences Research Council
Engineering & Physical Science Research Council (E
Funder's Grant Number: EP/W01842X/1
Keywords: Adversarial data augmentation
Adversarial training
Data augmentation
MR image segmentation
Model generalization
09 Engineering
11 Medical and Health Sciences
Nuclear Medicine & Medical Imaging
Notes: Under review. 23 pages
Publication Status: Published
Open Access location: https://arxiv.org/pdf/2108.03429.pdf
Online Publication Date: 2022-08-28
Appears in Collections:Computing
Electrical and Electronic Engineering
Faculty of Medicine
Department of Brain Sciences
Faculty of Engineering

This item is licensed under a Creative Commons License Creative Commons