Subject-specific lesion generation and pseudo-healthy synthesis for multiple sclerosis brain images

File Description SizeFormat 
paper003.pdfFile embargoed for 12 months after publication date 1.66 MBAdobe PDF    Request a copy
Title: Subject-specific lesion generation and pseudo-healthy synthesis for multiple sclerosis brain images
Authors: Basaran, BD
Qiao, M
Matthews, P
Bai, W
Item Type: Conference Paper
Abstract: Understanding the intensity characteristics of brain lesions is key for defining image-based biomarkers in neurological studies and for predicting disease burden and outcome. In this work, we present a novel foreground-based generative method for modelling the local lesion characteristics that can both generate synthetic lesions on healthy images and synthesize subject-specific pseudo-healthy images from pathological images. Furthermore, the proposed method can be used as a data augmentation module to generate synthetic images for training brain image segmentation networks. Experiments on multiple sclerosis (MS) brain images acquired on magnetic resonance imaging (MRI) demonstrate that the proposed method can generate highly realistic pseudo-healthy and pseudo-pathological brain images. Data augmentation using the synthetic images improves the brain image segmentation performance compared to traditional data augmentation methods as well as a recent lesion-aware data augmentation technique, CarveMix. The code will be released at
Date of Acceptance: 23-Jul-2022
ISSN: 0302-9743
Publisher: Springer
Journal / Book Title: Lecture Notes in Computer Science
Copyright Statement: Subject to copyright. All rights reserved.
Sponsor/Funder: Engineering and Physical Sciences Research Council
Funder's Grant Number: EP/S023283/1
Conference Name: SASHIMI: Simulation and Synthesis in Medical Imaging
Keywords: Artificial Intelligence & Image Processing
Publication Status: Accepted
Start Date: 2022-09-18
Conference Place: Singapore
Embargo Date: Embargoed for 12 months after publication date
Appears in Collections:Computing
Faculty of Medicine
Department of Brain Sciences