Lymphoma segmentation from 3D PET-CT images using a deep evidential network - Archive ouverte HAL Access content directly
Journal Articles International Journal of Approximate Reasoning Year : 2022

Lymphoma segmentation from 3D PET-CT images using a deep evidential network

(1, 2) , (2) , (3) , (1, 4)
1
2
3
4

Abstract

An automatic evidential segmentation method based on Dempster-Shafer theory and deep learning is proposed to segment lymphomas from three-dimensional Positron Emission Tomography (PET) and Computed Tomography (CT) images. The architecture is composed of a deep feature-extraction module and an evidential layer. The feature extraction module uses an encoder-decoder framework to extract semantic feature vectors from 3D inputs. The evidential layer then uses prototypes in the feature space to compute a belief function at each voxel quantifying the uncertainty about the presence or absence of a lymphoma at this location. Two evidential layers are compared, based on different ways of using distances to prototypes for computing mass functions. The whole model is trained end-to-end by minimizing the Dice loss function. The proposed combination of deep feature extraction and evidential segmentation is shown to outperform the baseline UNet model as well as three other state-of-the-art models on a dataset of 173 patients.
Fichier principal
Vignette du fichier
ES-Unet_v2 clean.pdf (2.72 Mo) Télécharger le fichier
Origin : Files produced by the author(s)

Dates and versions

hal-03766589 , version 1 (01-09-2022)

Identifiers

Cite

Ling Huang, Su Ruan, Pierre Decazes, Thierry Denœux. Lymphoma segmentation from 3D PET-CT images using a deep evidential network. International Journal of Approximate Reasoning, 2022, 149, pp.39-60. ⟨10.1016/j.ijar.2022.06.007⟩. ⟨hal-03766589⟩
13 View
4 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More