Scanner Invariant Multiple Sclerosis Lesion Segmentation from MRI
- Resource Type
- Authors
- Michael Dayan; Ghassan Hamarneh; Diego Sona; Roger Tam; Vittorio Murino; Shahab Aslani
- Source
- ISBI
- Subject
- FOS: Computer and information sciences
Scanner
medicine.diagnostic_test
Computer science
business.industry
Computer Vision and Pattern Recognition (cs.CV)
Image and Video Processing (eess.IV)
Computer Science - Computer Vision and Pattern Recognition
ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION
Magnetic resonance imaging
Pattern recognition
Electrical Engineering and Systems Science - Image and Video Processing
Regularization (mathematics)
030218 nuclear medicine & medical imaging
03 medical and health sciences
0302 clinical medicine
medicine
FOS: Electrical engineering, electronic engineering, information engineering
Segmentation
Artificial intelligence
Invariant (mathematics)
business
Multiple sclerosis lesion
030217 neurology & neurosurgery
- Language
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.