CNN for multiple sclerosis lesion segmentation: How many patients for a fully supervised method?

Abstract

HAL is a multi-disciplinary open access archive for the deposit and dissemination of scientific research documents, whether they are published or not. The documents may come from teaching and research institutions in France or abroad, or from public or private research centers. L'archive ouverte pluridisciplinaire HAL, est destinée au dépôt et à la diffusion de documents scientifiques de niveau recherche, publiés ou non, émanant des établissements d'enseignement et de recherche français ou étrangers, des laboratoires publics ou privés.

How far MS lesion detection and segmentation are integrated into the clinical workflow? A systematic review

“… DSC 1st, 2nd ( Zhang et al, 2021b ) multi-centric 200 MS T1-w, T2-w and FLAIR U-Net normalisation DSC, LTPR, LPPV, lesion-wise F1 1st, 2nd ( Abolvardi et al, 2019 ) ISBI 2015 FLAIR U-Net reg. DSC 1st, 2nd ( Fenneteau et al, 2021a ) ISBI 2015, extra 30 MS FLAIR MPU-net skull stripping, z-score normalisation DSC 1st, 2nd ( de Oliveira et al, 2020 ) ISBI 2015, extra 5 MS T1-w and FLAIR CNN skull stripping, b.c. volume of lesions 1st, 2nd ( Yildirim and Dandil, 2021a ) 38 MS T2-w mask R-CNN with ResNet101 as backbone / DSC, volume overlap error, LTPR, LFPR 1st, 2nd ( Tran et al, 2022 ) 30 MS T1-w and FLAIR intensity-based b.c.…”