Thesis of Thomas Ranvier

Deep multi-view learning for immunotherapy post-treatment of cancer patients


This thesis is part of the European project Qualitop, which aims to improve the quality of life of cancer patients treated with immunotherapy.
The objective of the thesis will be to predict the side effects that a patient is most likely to develop upon starting an immunotherapy treatment.
We are exploring and employing deep machine learning to complement the health data collected for the project, we wish to explore the possibilities of data augmentation and balancing using GANs, and finally, to design an original prediction approach effective in the health domain.

Advisor: Khalid Benabdeslem
Coadvisor: Emmanuel Coquery, Haytham Elghazel