Kerol Djoumessi

Kerol Djoumessi
Kerol Djoumessi designs deep learning models for medical image analysis that are interpretable by design, with applications in ophthalmology. He is a PhD student in the Department of Data Science and an IMPRS-IS scholar. In the past, he has studied several topics including software design and dynamic resource allocation in virtual networks. His current focus is on the design of interpretable/explainable deep learning models for clinical diagnosis. In addition to interpretability, he is interested in clinical ethics, resource-efficient deep learning models, and the deployment of deep learning models.
My best motivation is when I don't understand something or when something goes wrong.
01
02
Djoumessi, K., Huang, Z., Kühlewein, L., Rickmann, A., Simon, N., Koch, L. M., & Berens, P.

An inherently interpretable AI model improves screening speed and accuracy for early diabetic retinopathy

May 12, 2025 | PLOS Digital Health
03
Gervelmeyer, J., Müller, S., Djoumessi, K., Merle, D., Clark, S. J., Koch, L., & Berens, P.

Interpretable-by-design Deep Survival Analysis for Disease Progression Modeling

Oct 06, 2024 | MICCAI 2024