Segmentation of new multiple sclerosis lesions on FLAIR MRI using online hard example mining - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2021

Segmentation of new multiple sclerosis lesions on FLAIR MRI using online hard example mining

Résumé

This paper summarizes our contribution to the MSSEG-II MICCAI 2021 challenge. The aim is to segment new multiple sclerosis (MS) lesions using pairs of FLAIR MR images. Our approach is based on a 3D U-Net applied patch-wise to the images. In order to take into account both time-points, we simply concatenate the images along the channel axis before passing them to the 3D U-Net. The strong imbalance between positive and negative voxels, exhibited by the challenge data, makes training deep learning model di cult. Instead of using handcrafted priors like brain masks or multi-stage methods, we experiment with a novel modification to online hard example mining (OHEM), where we use an exponential moving average (i.e., its weights are updated with momentum) of our 3D U-Net to mine hard examples. Using a moving average instead of the raw model should allow smoothing its predictions and allowing it to give more consistent feedback for OHEM.
Fichier principal
Vignette du fichier
marius_MSSEG2.pdf (2.17 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03826787 , version 1 (24-10-2022)

Identifiants

  • HAL Id : hal-03826787 , version 1

Citer

Marius Schmidt-Mengin, Arya Yazdan-Panah, Théodore Soulier, Mariem Hamzaoui, Nicholas Ayache, et al.. Segmentation of new multiple sclerosis lesions on FLAIR MRI using online hard example mining. MICCAI-MSSEG-2 - 25th International Conference on Medical Image Computing and Computer Assisted Intervention - challenge on multiple sclerosis new lesions segmentation challenge using a data management and processing infrastructure, Sep 2021, Strasbourg, France. ⟨hal-03826787⟩
57 Consultations
55 Téléchargements

Partager

Gmail Facebook X LinkedIn More