My area of research are statistics, machine learning and computational biology. I have a particular interest for biological applications. Moreover, my research has been mostly focused on applying modern data processing technics to histopathology data. Histopathology data results from skin pieces seen through a very powerful microscope. Histopathology data can be very large (>60 GB per image) and are very complex to analyse due to the high variability in cell shape, type and staining. We wish to discover biologicaly relevant information from histopathological data that is predictive of treatment responses. Currently, I am working on two medical topics:
- The first project, developped with the help of Fabien Reyal group, aims Tripple Negativ Breast Cancer patients, whom undergo chemiotherapy. However patient responses are very different and we wish to find biologicaly relevant patterns or features that could be predictive of patient response to chemiotherapy. This projects bottleneck is nuclei segmentation within histopathology data and is performed with the state of the art deep neural networks. Quantifying patients histopathological data will lead to personnal patient feature, such as proportion of cancerous cells with respect to the normal endothelial cells, moreover we could define feature that take into account spatial arrangements.
- The second project aims colon cancer patient and cancer subtypes. With the same biologicaly relevant data as mentionned in the first project we wish to encover patterns that lead to cancer subgroups with colon cancer.