Deep Learning for Segmentation of Brain Tumors and Organs at Risk
Medical images, such as MRI or CT scans, are used for diagnosis, therapy planning and monitoring of cancers. Automatic segmentation (contouring) of tumors is a very challenging task, due particularly to the variability of tumor shapes, locations and sizes. With their ability to automatically learn relevant features from images, Convolutional Neural Networks have recently achieved state-of-the-art results in a large variety of recognition tasks in medical imaging. However, current deep learning models for tumor segmentation still struggle with important problems such as high computational costs and the lack of annotated training data. In this work, we propose methods based on supervised and semi-supervised deep learning to address these practical challenges.
Practical aspects of the Coq system: why is it considered a major advance in Computer Science
In 2014, The ACM (Association for Computing Machinery) gave the "Software System Award" to the Coq system. In this talk, we shall explain why this professional access considers that this system is a major advance for the future of computer technology. In practice, we shall show that programs can be described in mathematical and logical terms, that theorems can be stated about programs, and that the proof of these theorems can be verified by computers.
Andrea Castagnetti (Elicie Healthy)
The Ellcie Healthy smart glasses: 23 grams of technology made in France
Ellcie Healthy smart connected glasses (eyewear) have been designed to look after people and prevent risks like drowsiness at the wheel. Fifteen sensors embedded in the frame continuously measure physical, physiological and environmental data that are processed by Ellcie Healthy’s Artificial Intelligence to raise an alert when needed. The first part of the talk will cover the company history and the development of our first commercial product. In the second part of the talk we will present the research and development projects that we are conducting in collaboration with research laboratories to develop new concepts and technologies like sensory substitution devices ("Artefact" project: LEAT, UCA) and fall prevention applications for elderly people (Lamhess, UFR Staps and CHU Nice).