Affordable Access

A study on loss functions and decision thresholds for the segmentation of multiple sclerosis lesions on spinal cord MRI

Authors
  • Hussein, Burhan Rashid
  • Meurée, Cédric
  • Gaubert, Malo
  • Masson, Arthur
  • Kerbrat, Anne
  • Combès, Benoît
  • Galassi, Francesca
Publication Date
Nov 22, 2022
Source
HAL
Keywords
Language
English
License
Unknown
External links

Abstract

Multiple sclerosis (MS) patients often present hyper-intense T2-w lesions in the spinal cord. The severe imbalance between background and lesion classes poses a major challenge to Deep Learning segmentation approaches, requiring for ad hoc strategies. Careful selection of the loss function and adjustment of the conventional 0.5-thresholding may help mitigating this issue. Our results show the performance advantages of loss functions based on the Tversky Index and the benefits of threshold tuning over more standard settings and the state-of-the-art model for MS lesion segmentation on spinal cord MRI.

Report this publication

Statistics

Seen <100 times