Helmholtz Gemeinschaft

Search
Browse
Statistics
Feeds

SynergyNet: a fusion framework for multiple sclerosis brain MRI segmentation with local refinement

Item Type:Conference or Workshop Item
Title:SynergyNet: a fusion framework for multiple sclerosis brain MRI segmentation with local refinement
Creators Name:Vang, Y.S. and Cao, Y. and Chang, P.D. and Chow, D.S. and Brandt, A.U. and Paul, F. and Scheel, M. and Xie, X.
Abstract:The high irregularity of multiple sclerosis (MS) lesions in sizes and numbers often proves difficult for automated systems on the task of MS lesion segmentation. Current Stateof-the-art MS segmentation algorithms employ either only global perspective or just patch-based local perspective segmentation approaches. Although global image segmentation can obtain good segmentation for medium to large lesions, its performance on smaller lesions lags behind. On the other hand, patch-based local segmentation disregards spatial information of the brain. In this work, we propose SynergyNet, a network segmenting MS lesions by fusing data from both global and local perspectives to improve segmentation across different lesion sizes. We achieve global segmentation by leveraging the U-Net architecture and implement the local segmentation by augmenting U-Net with the Mask RCNN framework. The sharing of lower layers between these two branches benefits end-to-end training and proves advantages over simple ensemble of the two frameworks. We evaluated our method on two separate datasets containing 765 and 21 volumes respectively. Our proposed method can improve 2.55% and 5.0% for Dice score and lesion true positive rates respectively while reducing over 20% in false positive rates in the first dataset, and improve in average 10% and 32% for Dice score and lesion true positive rates in the second dataset. Results suggest that our framework for fusing local and global perspectives is beneficial for segmentation of lesions with heterogeneous sizes.
Keywords:Multiple Sclerosis, Deep Learning, MRI
Source:International Symposium on Biomedical Imaging (ISBI)
Title of Book:2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI)
ISSN:1945-8452
ISBN:978-1-5386-9330-8
Publisher:IEEE
Page Range:131-135
Article Number:9098610
Date:22 May 2020
Official Publication:https://doi.org/10.1109/ISBI45749.2020.9098610

Repository Staff Only: item control page

Open Access
MDC Library