Prof. Jérôme Schmid – Geneva School of Health Sciences – HES-SO, Switzerland
Bio: Professor Jérôme Schmid has been working for many years in the field of medical image processing and analysis, focusing on segmentation and registration. He has specialized in physically-based deformable models applied to modeling the human musculoskeletal system. Professor Schmid has also explored the combination of deformable models with machine learning, as well as the use of deep learning for computer-assisted diagnosis, such as the recognition of bone fractures in wrist radiographs, the detection of Parkinson’s disease in SPECT imaging, or the detection of breast lesions in dynamic MRI. The application of artificial intelligence for educational purposes has also been explored by his team in the design of the AIRx training prototype to simulate the realistic generation of radiographs. Since 2011, Professor Schmid and his team at HES-SO have acquired solid expertise in computer-assisted diagnosis and image-guided surgery through several research projects funded by the public and private sectors, including the Swiss National Science Foundation, Innosuisse, and various Swiss foundations.
THE PRESENTATION
Title: Make me smarter: when knowledge improves computer-assisted medical image analysis
Abstract: The use of medical imaging is now a standard practice in clinical settings, resulting in the production of vast quantities of images using various imaging modalities. The computer-assisted analysis of these medical images aids clinicians in numerous ways, including diagnosis, prognosis, and the preparation and execution of medical interventions. A large variety of approaches have been developed for the processing of medical images, and this presentation intends to demonstrate how integrating knowledge into the design of these methodologies can enhance their effectiveness. To illustrate this, several examples from Professor Schmid’s research activities will be presented, showcasing the practical applications and benefits of these knowledge-based computational approaches in medical imaging.