Scanner Invariant Multiple Sclerosis Lesion Segmentation from MRI
- Resource Type
- Conference
- Authors
- Aslani, Shahab; Murino, Vittorio; Dayan, Michael; Tam, Roger; Sona, Diego; Hamarneh, Ghassan
- Source
- 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI) Biomedical Imaging (ISBI), 2020 IEEE 17th International Symposium on. :781-785 Apr, 2020
- Subject
- Bioengineering
Computing and Processing
Photonics and Electrooptics
Signal Processing and Analysis
Image segmentation
Magnetic resonance imaging
Training
Biomedical imaging
Correlation
Lesions
Three-dimensional displays
Magnetic Resonance Imaging
Multiple Sclerosis
Lesion Segmentation
Domain Generalization
- Language
- ISSN
- 1945-8452
This paper presents a simple and effective generalization method for magnetic resonance imaging (MRI) segmentation when data is collected from multiple MRI scanning sites and as a consequence is affected by (site-)domain shifts. We propose to integrate a traditional encoder-decoder network with a regularization network. This added network includes an auxiliary loss term which is responsible for the reduction of the domain shift problem and for the resulting improved generalization. The proposed method was evaluated on multiple sclerosis lesion segmentation from MRI data. We tested the proposed model on an in-house clinical dataset including 117 patients from 56 different scanning sites. In the experiments, our method showed better generalization performance than other baseline networks.