Spatio-temporal Learning from Longitudinal Data for Multiple Sclerosis Lesion Segmentation
This work addresses monitoring disease progression for Multiple Sclerosis patients, representing an incremental advance in medical image segmentation.
The paper tackles the problem of segmenting Multiple Sclerosis lesions in longitudinal brain MR scans by using spatio-temporal cues to improve accuracy, achieving a 2.6% improvement over the state-of-the-art.
Segmentation of Multiple Sclerosis (MS) lesions in longitudinal brain MR scans is performed for monitoring the progression of MS lesions. We hypothesize that the spatio-temporal cues in longitudinal data can aid the segmentation algorithm. Therefore, we propose a multi-task learning approach by defining an auxiliary self-supervised task of deformable registration between two time-points to guide the neural network toward learning from spatio-temporal changes. We show the efficacy of our method on a clinical dataset comprised of 70 patients with one follow-up study for each patient. Our results show that spatio-temporal information in longitudinal data is a beneficial cue for improving segmentation. We improve the result of current state-of-the-art by 2.6% in terms of overall score (p<0.05). Code is publicly available.