Using Separated Inputs for Multimodal Brain Tumor Segmentation with 3D U-Net-like Architectures - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Using Separated Inputs for Multimodal Brain Tumor Segmentation with 3D U-Net-like Architectures

N. Boutry
E. Puybareau
G. Tochon

Résumé

The work presented in this paper addresses the MICCAI BraTS 2019 challenge devoted to brain tumor segmentation using magnetic resonance images. For each task of the challenge, we proposed and submitted for evaluation an original method. For the tumor segmentation task (Task 1), our convolutional neural network is based on a variant of the U-Net architecture of Ronneberger et al. with two modifications: first, we separate the four convolution parts to decorrelate the weights corresponding to each modality, and second, we provide volumes of size as inputs in these convolution parts. This way, we profit of the 3D aspect of the input signal, and we do not use the same weights for separate inputs. For the overall survival task (Task 2), we compute explainable features and use a kernel PCA embedding followed by a Random Forest classifier to build a predictor with very few training samples. For the uncertainty estimation task (Task 3), we introduce and compare lightweight methods based on simple principles which can be applied to any segmentation approach. The overall performance of each of our contribution is honorable given the low computational requirements they have both for training and testing.
Fichier principal
Vignette du fichier
boutry.20.brainles.pdf (924.02 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04580407 , version 1 (22-05-2024)

Identifiants

Citer

N. Boutry, J. Chazalon, E. Puybareau, G. Tochon, Hugues Talbot, et al.. Using Separated Inputs for Multimodal Brain Tumor Segmentation with 3D U-Net-like Architectures. Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries: 5th International Workshop,, Oct 2010, Shenzhen, China. pp.187-199, ⟨10.1007/978-3-030-46640-4_18⟩. ⟨hal-04580407⟩
44 Consultations
7 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More