Titre :

Stacking denoising auto-encoders in a deep network to segment the brainstem on MRI in brain cancer patients: a clinical study

Auteur(s) :

Dolz, Jose [Auteur]
Thérapies Assistées par Lasers et Immunothérapies pour l'Oncologie - U 1189 [OncoThAI]
Betrouni, Nacim [Auteur]
Thérapies Assistées par Lasers et Immunothérapies pour l'Oncologie - U 1189 [OncoThAI]
Quidet, Mathilde [Auteur]
Thérapies Assistées par Lasers et Immunothérapies pour l'Oncologie - U 1189 [OncoThAI]
Kharroubi, Dris [Auteur]
Thérapies Assistées par Lasers et Immunothérapies pour l'Oncologie - U 1189 [OncoThAI]
Leroy, Henri A. [Auteur]
Centre Hospitalier Régional Universitaire [CHU Lille] [CHRU Lille]
Thérapies Assistées par Lasers et Immunothérapies pour l'Oncologie - U 1189 [OncoThAI]
Reyns, Nicolas [Auteur]
Centre Hospitalier Régional Universitaire [CHU Lille] [CHRU Lille]
Thérapies Assistées par Lasers et Immunothérapies pour l'Oncologie - U 1189 [OncoThAI]
Massoptier, Laurent [Auteur]
Vermandel, Maximilien [Auteur]
Centre Hospitalier Régional Universitaire [CHU Lille] [CHRU Lille]
Thérapies Assistées par Lasers et Immunothérapies pour l'Oncologie - U 1189 [OncoThAI]

Titre de la revue :

Computerized Medical Imaging and Graphics

Éditeur :

Elsevier

Date de publication :

2016

ISSN :

0895-6111

Mot(s)-clé(s) en anglais :

deep learning
MRI segmentation
brain cancer
machine learning

Discipline(s) HAL :

Sciences du Vivant [q-bio]/Ingénierie biomédicale/Imagerie

Résumé en anglais : [en]

Delineation of organs at risk (OARs) is a crucial step in surgical and treatment planning in brain cancer, where precise OARs volume delineation is required. However, this task is still often manually performed, which is ...
Lire la suite >Delineation of organs at risk (OARs) is a crucial step in surgical and treatment planning in brain cancer, where precise OARs volume delineation is required. However, this task is still often manually performed, which is time-consuming and prone to observer variability. To tackle these issues a deep learning approach based on stacking denoising auto-encoders has been proposed to segment the brainstem on magnetic resonance images in brain cancer context. Additionally to classical features used in machine learning to segment brain structures, two new features are suggested. Four experts participated in this study by segmenting the brainstem on 9 patients who underwent radiosurgery. Analysis of variance on shape and volume similarity metrics indicated that there were significant differences (p<0.05) between the groups of manual annotations and automatic segmentations. Experimental evaluation also showed an overlapping higher than 90% with respect to the ground truth. These results are comparable , and often higher, to those of the state of the art segmentation methods but with a considerably reduction of the segmentation time.Lire moins >

Langue :

Anglais

Vulgarisation :

Non

Collections :

• Thérapies Lasers Assistées par l'Image pour l'Oncologie (ONCO-THAI) - U1189

Source :

Harvested from HAL