Imperial College London
Alternate

Professor Paul M. Matthews

Faculty of Medicine, Department of Brain Sciences

Edmond and Lily Safra Chair, Head of Department
 
 
 
//

Contact

 

+44 (0)20 7594 2855p.matthews

 
 
//

Assistant

 

Ms Siobhan Dillon +44 (0)20 7594 2855

 
//

Location

 

E502Burlington DanesHammersmith Campus

//

Summary

 

Publications

Citation

BibTex format

@article{Basaran:2022:10.3389/fnins.2022.1007453,
author = {Basaran, B and Matthews, PM and Bai, W},
doi = {10.3389/fnins.2022.1007453},
journal = {Frontiers in Neuroscience},
title = {New lesion segmentation for multiple sclerosis brain images with imaging and lesion-aware augmentation},
url = {http://dx.doi.org/10.3389/fnins.2022.1007453},
volume = {16},
year = {2022}
}
Download

RIS format (EndNote, RefMan)

TY  - JOUR
AB  - Multiple sclerosis (MS) is an inflammatory and demyelinating neurological disease of the central nervous system. Image-based biomarkers, such as lesions defined on magnetic resonance imaging (MRI), play an important role in MS diagnosis and patient monitoring. The detection of newly formed lesions provides crucial information for assessing disease progression and treatment outcome. Here, we propose a deep learning-based pipeline for new MS lesion detection and segmentation, which is built upon the nnU-Net framework. In addition to conventional data augmentation, we employ imaging and lesion-aware data augmentation methods, axial subsampling and CarveMix, to generate diverse samples and improve segmentation performance. The proposed pipeline is evaluated on the MICCAI 2021 MS new lesion segmentation challenge (MSSEG-2) dataset. It achieves an average Dice score of 0.510 and F1 score of 0.552 on cases with new lesions, and an average false positive lesion number nFP of 0.036 and false positive lesion volume VFP of 0.192 mm3 on cases with no new lesions. Our method outperforms other participating methods in the challenge and several state-of-the-art network architectures.
AU  - Basaran,B
AU  - Matthews,PM
AU  - Bai,W
DO  - 10.3389/fnins.2022.1007453
PY  - 2022///
SN  - 1662-453X
TI  - New lesion segmentation for multiple sclerosis brain images with imaging and lesion-aware augmentation
T2  - Frontiers in Neuroscience
UR  - http://dx.doi.org/10.3389/fnins.2022.1007453
UR  - http://hdl.handle.net/10044/1/100429
VL  - 16
ER  -
Download