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

@inproceedings{Ruijsink:2020:10.1007/978-3-030-68107-4_10,
author = {Ruijsink, B and Puyol-Antón, E and Li, Y and Bai, W and Kerfoot, E and Razavi, R and King, AP},
doi = {10.1007/978-3-030-68107-4_10},
pages = {97--107},
title = {Quality-aware semi-supervised learning for CMR segmentation.},
url = {http://dx.doi.org/10.1007/978-3-030-68107-4_10},
year = {2020}
}
Download

RIS format (EndNote, RefMan)

TY  - CPAPER
AB  - One of the challenges in developing deep learning algorithms for medical image segmentation is the scarcity of annotated training data. To overcome this limitation, data augmentation and semi-supervised learning (SSL) methods have been developed. However, these methods have limited effectiveness as they either exploit the existing data set only (data augmentation) or risk negative impact by adding poor training examples (SSL). Segmentations are rarely the final product of medical image analysis -they are typically used in downstream tasks to infer higher-order patterns to evaluate diseases. Clinicians take into account a wealth of prior knowledge on biophysics and physiology when evaluating image analysis results. We have used these clinical assessments in previous works to create robust quality-control (QC) classifiers for automated cardiac magnetic resonance (CMR) analysis. In this paper, we propose a novel scheme that uses QC of the downstream task to identify high quality outputs of CMR segmentation networks, that are subsequently utilised for further network training. In essence, this provides quality-aware augmentation of training data in a variant of SSL for segmentation networks (semiQCSeg). We evaluate our approach in two CMR segmentation tasks (aortic and short axis cardiac volume segmentation) using UK Biobank data and two commonly used network architectures (U-net and a Fully Convolutional Network) and compare against supervised and SSL strategies. We show that semiQCSeg improves training of the segmentation networks. It decreases the need for labelled data, while outperforming the other methods in terms of Dice and clinical metrics. SemiQCSeg can be an efficient approach for training segmentation networks for medical image data when labelled datasets are scarce.
AU  - Ruijsink,B
AU  - Puyol-Antón,E
AU  - Li,Y
AU  - Bai,W
AU  - Kerfoot,E
AU  - Razavi,R
AU  - King,AP
DO  - 10.1007/978-3-030-68107-4_10
EP  - 107
PY  - 2020///
SP  - 97
TI  - Quality-aware semi-supervised learning for CMR segmentation.
UR  - http://dx.doi.org/10.1007/978-3-030-68107-4_10
UR  - https://www.ncbi.nlm.nih.gov/pubmed/34286332
ER  -
Download