Laboratoire d'Informatique Médicale et d'Ingénierie des Connaissances en e-Santé

UMRS_1142

Logo Tremplin Carnot
FR EN
Logo INSERM
Logo UPMC Logo université Paris 13

Évènements

Image décorative

Bridging the semantic gap between diagnostic histopathology and image analysis

ii340y35wzs4w4wg448k.png

Lamine Traoré

Le 26/06/2017 de 09:45 à 11:00

Description :

Recently, histopathology has seen the introduction of several new tools such as slide scanners and virtual slide technologies creating the right conditions for broader adoption of computer assisted diagnosis based on images to reduce observation variability between experts[1].During this talk, we will present a number of scientific challenges related to the management of the semantics associated to histopathology and image analysis. Then we will propose a sustainable way to bridge the content, features, performance and usability gaps [2][3] between the two domains.In both histopathology and imaging approaches, a semi-automatic annotation process was used to label the quantitative parameters and relevant terms with codes from predefined reference semantic resources. Based on NCBO Bioportal and UMLS semantic types, the concepts and metadata generated represent a sustainable vocabulary, dedicated to histopathology, being able to effectively support daily work on WSI. This research work is a step forward to organized, cross-disciplinary, information-driven collaborations in the histopathological imaging field.Future works should focus on further development toward realizing our longer term goals of advancing interoperability of histopathological imaging systems and reproducibility of histopathological imaging assays

Traitement en cours ...