Team : DECISION
Departure date : 06/30/2014
: Patrick BRÉZILLON
Design and Implementation of a Context-based Consultant. Application on histopathology for breast cancer gradation.
Breast cancer diagnosis is a human activity that is context-dependent. The context contains a large number of elements that limits strongly any possibility de complete automation. Recently, digitization of slides (reasoning support) prompted pathologists to migrate from slide analysis under microscope to slide image analysis on the screen. This migration offers a possibility of partial proceduralization of their analysis methods. In this thesis, we are interested on the activity of slide image analysis by a pathologist that is modeled in the Contextual-Graphs formalism with the goal to propose a solution to support pathologists in their diagnosis. Our Consultant belongs to the class of Context based Intelligent Assistant Systems. The main tool of the consultant is based on the simulation of expert practices described in a contextual graph. Starting from an image to analyze, the simulator will develop a practice that is the most adapted to the working context. The output of the simulation is the resulting practice and ll information about its development. The consultant proposes to the user a visualization of the different results for analysis and comparison.
: 06/13/2014 - 14h30 - Site Jussieu 26-00/124Jury members
Racoceanu Daniel Professeur à l'UPMC
Brézillon Patrick Professeur à l'UPMC
Adam Frédéric Professeur à l'Université College Cork (rapporteur)
Zerhouni Noureddine Professeur à l'Université de Besançon (rapporteur)