Improving abdominal image segmentation with overcomplete shape priors.
Fiche publication
Date publication
février 2024
Journal
Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society
Auteurs
Membres identifiés du Cancéropôle Est :
Dr NOBLET Vincent
Tous les auteurs :
Sadikine A, Badic B, Tasu JP, Noblet V, Ballet P, Visvikis D, Conze PH
Lien Pubmed
Résumé
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.
Mots clés
Abdominal imaging, Deep learning, Overcomplete representations, Semantic segmentation, Shape priors
Référence
Comput Med Imaging Graph. 2024 02 9;113:102356