Improving abdominal image segmentation with overcomplete shape priors - Archive ouverte du site Alsace Access content directly
Journal Articles Computerized Medical Imaging and Graphics Year : 2024

Improving abdominal image segmentation with overcomplete shape priors

Abstract

The extraction of abdominal structures using deep learning has recently experienced a widespread interest in medical image analysis. Automatic abdominal organ and vessel segmentation is highly desirable to guide clinicians in computer-assisted diagnosis, therapy, or surgical planning. Despite a good ability to extract large organs, the capacity of U-Net inspired architectures to automatically delineate smaller structures remains a major issue, especially given the increase in receptive field size as we go deeper into the network. To deal with various abdominal structure sizes while exploiting efficient geometric constraints, we present a novel approach that integrates into deep segmentation shape priors from a semi-overcomplete convolutional auto-encoder (S-OCAE) embedding. Compared to standard convolutional auto-encoders (CAE), it exploits an over-complete branch that projects data onto higher dimensions to better characterize anatomical structures with a small spatial extent. Experiments on abdominal organs and vessel delineation performed on various publicly available datasets highlight the effectiveness of our method compared to state-of-the-art, including U-Net trained without and with shape priors from a traditional CAE. Exploiting a semi-overcomplete convolutional auto-encoder embedding as shape priors improves the ability of deep segmentation models to provide realistic and accurate abdominal structure contours.
Fichier principal
Vignette du fichier
1-s2.0-S0895611124000338-main.pdf (3.56 Mo) Télécharger le fichier
Origin : Publisher files allowed on an open archive
licence : CC BY NC ND - Attribution - NonCommercial - NoDerivatives

Dates and versions

hal-04443431 , version 1 (27-02-2024)

Licence

Attribution - NonCommercial - NoDerivatives

Identifiers

Cite

Amine Sadikine, Bogdan Badic, Jean-Pierre Tasu, Vincent Noblet, Pascal Ballet, et al.. Improving abdominal image segmentation with overcomplete shape priors. Computerized Medical Imaging and Graphics, 2024, 113 (April), pp.102356. ⟨10.1016/j.compmedimag.2024.102356⟩. ⟨hal-04443431⟩
24 View
2 Download

Altmetric

Share

Gmail Facebook X LinkedIn More