Shallow vs deep learning architectures for white matter lesion segmentation in the early stages of multiple sclerosis
This work addresses automated lesion segmentation for early-stage multiple sclerosis patients, which is incremental as it compares and combines existing methods on a new clinical dataset.
The study compared shallow and deep learning architectures for segmenting white matter lesions in early-stage multiple sclerosis MR images, finding that the shallow architecture achieved the best Dice coefficient (63%) and volume difference (19%), while a combination improved lesion-wise true positive rate to 69% and false positive rate to 26%.
In this work, we present a comparison of a shallow and a deep learning architecture for the automated segmentation of white matter lesions in MR images of multiple sclerosis patients. In particular, we train and test both methods on early stage disease patients, to verify their performance in challenging conditions, more similar to a clinical setting than what is typically provided in multiple sclerosis segmentation challenges. Furthermore, we evaluate a prototype naive combination of the two methods, which refines the final segmentation. All methods were trained on 32 patients, and the evaluation was performed on a pure test set of 73 cases. Results show low lesion-wise false positives (30%) for the deep learning architecture, whereas the shallow architecture yields the best Dice coefficient (63%) and volume difference (19%). Combining both shallow and deep architectures further improves the lesion-wise metrics (69% and 26% lesion-wise true and false positive rate, respectively).