My research topics mainly focus on the automatic segmentation of multi-dimensional medical data. These topics are parts of the team Myriad.
An important part of my work has been dedicated to Mean-shift which is an exciting approach when no assumptions are made about the data. Mean-shift can be derived in a knowledge discovery framework. Extending this framework to spatiotemporal data, scale, and space selections, with the integration of a few prior, consisted of my main research. Such methods are motivated by medical challenges ( Multiple sclerosis, stroke, cardiac segmentation…. ).
Now, I am focussing on deep learning segmentation, filtering, and localization approach that can provide better and more robust results than many conventional approaches. The main challenges are the use of semi- and weakly- supervised methods, dealing when experts disagree, and trying to train in a playful manner (selection of needed data, continuous learning, …)
For image processing application development, I use ITK and OpenCV with QTCreator and CMake for C++, under Windows and Linux (Fedora and Ubuntu). I use more and more python with conda and appreciate jupyter lab environment (debug !).
For deep learning, I mostly use python with Keras/Tensorflow (using conda) or AlexeyAB Darknet lib.