Smart Atlas for Supporting the Interpretation of needle-based Confocal Laser Endomicroscopy (nCLE) of Pancreatic Cysts: First Classification Results of a Computer-Aided Diagnosis Software based on Image Recognition
Résumé
nCLE enables microscopic imaging of pancreatic cysts, in vivo and in real time, during an EUS-FNA procedure. Diferentiating branch duct-type Intraductal Papillary Mucinous Neoplasm (IPMN) and Serous Cystadenoma (SCA) of the pancreas can be difcult, especially in case of a solitary lesion without clear communication with the pancreatic duct. Recent studies (Konda et al., Endoscopy 2013; Napoléon et al., DDW 2013) have identifed reliable nCLE descriptive features (superfcial vascular network in SCA; fngerlike projections in IPMN), allowing endoscopists to discriminate between SCA and IPMN. In parallel, a computer-aided diagnosis software called Smart Atlas has been developed to assist endoscopists with the interpretation of nCLE video sequences. This study aims at evaluating the performance of this software for the diferentiation of SCA and IPMN cases.
Domaines
Imagerie médicale
Origine : Fichiers produits par l'(les) auteur(s)