Description
Date depot: 1 janvier 1900
Titre: From Digital to Computational Pathology for Biomarker Discovery
Directeur de thèse:
Laurent WENDLING (LIPADE)
Directeur de thèse:
Jean-Christophe OLIVO-MARIN (Analyse d'images biologiques)
Encadrante :
Vannary MEAS-YEDID (Institut Pasteur (UMR3691))
Domaine scientifique: Sciences et technologies de l'information et de la communication
Thématique CNRS : Non defini
Resumé:
Aided by advanced image analysis technologies, digital pathology is revolutionizing histopathology by providing objective assessment of cellular components within tissue samples and assisting pathology grading. To date, remarkable progress has been made to obtain clinically relevant quantitative data from pathological samples, including grade-differentiating features in many pathologies. Digital pathology has a unique advantage towards studying the microenvironment in tissue because of its capacity to map the spatial context of interaction of entities of interest (i.e. cell-vessel, cell-tumor, etc.). It makes it possible to explore unexamined relationship between morphology, sub-cellular spatial distribution of proteins and protein-protein interactions.
Technological developments to facilitate automated identification of tissue components and rigorous analysis of their spatial heterogeneity are still in the early stages. Objective and reproducible methods for automated identification and statistical analysis of the spatial distribution of microenvironmental components such as immune cells, fibroblasts and vessels remain an unmet need. Development in this direction will accelerate the rate at which histology data is processed as well as the translation of our knowledge of the microenvironment into biomarkers.
Within this project, generic methodologies will be developed to extract the interesting features from the tissue images (cell, vessel, etc.). These methods should be able to deal with different stainings (chemical or immunohistochemical or fluorescence, etc.) and multiple factors such as tissue handling, section thickness and staining protocols that can contribute to the high variability in pathological samples. Several approaches such as graph algorithms, active contours, convolutional network would be explored by taking into account the spatial context with the quantitative spatial relations, such as force histograms to segment and extract the objects of interest.
Doctorant.e: Gonzalez Obando Daniel Felipe