Imperial College London
Portrait Picture

DrWenjiaBai

Faculty of Medicine, Department of Brain Sciences

Senior Lecturer
 
 
 
//

Contact

 

+44 (0)20 7594 8291w.bai Website

 
 
//

Location

 

Room 212, Data Science InstituteWilliam Penney LaboratorySouth Kensington Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Chen:2022:10.1016/j.media.2022.102597,
author = {Chen, C and Qin, C and Ouyang, C and Li, Z and Wang, S and Qiu, H and Chen, L and Tarroni, G and Bai, W and Rueckert, D},
doi = {10.1016/j.media.2022.102597},
journal = {Medical Image Analysis},
pages = {1--15},
title = {Enhancing MR image segmentation with realistic adversarial data augmentation},
url = {http://dx.doi.org/10.1016/j.media.2022.102597},
volume = {82},
year = {2022}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - The success of neural networks on medical image segmentation tasks typicallyrelies on large labeled datasets for model training. However, acquiring andmanually labeling a large medical image set is resource-intensive, expensive,and sometimes impractical due to data sharing and privacy issues. To addressthis challenge, we propose AdvChain, a generic adversarial data augmentationframework, aiming at improving both the diversity and effectiveness of trainingdata for medical image segmentation tasks. AdvChain augments data with dynamicdata augmentation, generating randomly chained photo-metric and geometrictransformations to resemble realistic yet challenging imaging variations toexpand training data. By jointly optimizing the data augmentation model and asegmentation network during training, challenging examples are generated toenhance network generalizability for the downstream task. The proposedadversarial data augmentation does not rely on generative networks and can beused as a plug-in module in general segmentation networks. It iscomputationally efficient and applicable for both low-shot supervised andsemi-supervised learning. We analyze and evaluate the method on two MR imagesegmentation tasks: cardiac segmentation and prostate segmentation with limitedlabeled data. Results show that the proposed approach can alleviate the needfor labeled data while improving model generalization ability, indicating itspractical value in medical imaging applications.
AU  - Chen,C
AU  - Qin,C
AU  - Ouyang,C
AU  - Li,Z
AU  - Wang,S
AU  - Qiu,H
AU  - Chen,L
AU  - Tarroni,G
AU  - Bai,W
AU  - Rueckert,D
DO  - 10.1016/j.media.2022.102597
EP  - 15
PY  - 2022///
SN  - 1361-8415
SP  - 1
TI  - Enhancing MR image segmentation with realistic adversarial data augmentation
T2  - Medical Image Analysis
UR  - http://dx.doi.org/10.1016/j.media.2022.102597
UR  - http://arxiv.org/abs/2108.03429v2
UR  - https://www.sciencedirect.com/science/article/pii/S1361841522002304?via%3Dihub
UR  - http://hdl.handle.net/10044/1/98087
VL  - 82
ER  -
Download