Client-Side Application of Deep Learning Models through Teleradiology Passed
Wednesday May 24, 2023 14:30 - 14:45 G4
Lecturer: Sébastien Jodogne
Track: MIE: Sensors, signals and Imaging Informatics
Deep learning models for radiology are typically deployed either through cloud-based platforms, through on-premises infrastructures, or though heavyweight viewers. This tends to restrict the audience of deep learning models to radiologists working in state-of-the-art hospitals, which raises concerns about the democratization of deep learning for medical imaging, most notably in the context of research and education. We show that complex deep learning models can be applied directly inside Web browsers, without resorting to any external computation infrastructure, thanks to the use of WebAssembly, and we release our code as free and open-source software. This opens the path to the use of teleradiology solutions as an effective way to distribute, teach, and evaluate deep learning architectures.
Language
English
Seminar type
On site only
Level of knowledge
Advanced
Conference
MIE
Authors
Sébastien Jodogne
Lecturers
Sébastien Jodogne Lecturer
Assistant Professor
UCLouvain
Sébastien Jodogne was born in 1979 in Oupeye (Belgium). He earned his Master's and Ph.D. degrees in computer science from the University of Liège (Belgium), respectively in 2001 and 2006. Between 2007 and 2011, he worked on research projects about high-performance image processing algorithms for machine vision, closed-circuit television, and broadcasting in private companies. He then served as a research engineer at the radiology, radiotherapy and nuclear medicine departments of the University Hospital of Liège between 2011 and 2016, where he designed the free and open-source Orthanc ecosystem for medical imaging. For his work on Orthanc, he received the 2014 Award for the Advancement of Free Software from the Free Software Foundation (FSF). Sébastien Jodogne now works as full-time Assistant Professor in the ICTEAM research institute of UCLouvain, in the field of computer science applied to life sciences. His research interests include health informatics, artificial intelligence, medical imaging, computer vision, and software engineering.
Homepage: https://www.info.ucl.ac.be/~sjodogne/
LinkedIn: https://www.linkedin.com/in/jodogne/