{"id":16,"date":"2010-12-08T15:40:40","date_gmt":"2010-12-08T15:40:40","guid":{"rendered":"http:\/\/www.creatis.insa-lyon.fr\/~grenier\/?page_id=16"},"modified":"2026-02-16T15:20:35","modified_gmt":"2026-02-16T14:20:35","slug":"research","status":"publish","type":"page","link":"https:\/\/www.creatis.insa-lyon.fr\/~grenier\/?page_id=16","title":{"rendered":"Research"},"content":{"rendered":"\n
\"\"<\/figure>\n\n\n

My research topics primarily focus on the automatic segmentation of multidimensional medical data, with applications in pathology understanding, follow-up, and digital twin development. These topics are part of the team Myriad.<\/a><\/p>\n

A significant part of my work has been dedicated to Mean-shift, which is an exciting approach that does not require assumptions about the data. Mean-shift can be derived in a knowledge discovery<\/em> framework. Extending this framework to spatiotemporal data, scale, and space selections, with the integration of a few prior, constituted my main research. Such methods are motivated by medical challenges ( Multiple sclerosis, stroke, cardiac segmentation…. ).<\/p>\n

Now, I am focusing on approaches based on deep learning for segmentation, filtering, and localization\/detection tasks 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 with experts’ disagreements, explainability, confidence, and trying to train in a playful manner (selection of needed data, continuous learning, …). The applications of such segmentations are: pathologies understanding and quantification, longitudinal analysis (disease evolution, clinical care), and more and more for numerical simulations (CFD, failure load…: digital twin).\u00a0<\/p>\n

For image processing application development, my background is on ITK <\/a>and OpenCV<\/a>, with QTCreator<\/a> and CMake<\/a> for C++, under Windows and Linux. I use more and more Python with conda and really appreciate the jupyter lab<\/em> environment (debuging and contextual help !).<\/p>\n

For deep learning, I mostly use Python with Keras<\/a>\/Tensorflow<\/a> (using conda<\/a>), or MONAI\u00a0<\/a>. For Yolo, I switch from AlexeyAB Darknet<\/a> lib to Ultralytics<\/a> one.<\/p>\n

Topics<\/h3>\n