Faculty of Mathematics, Physics
and Informatics
Comenius University Bratislava

Doctoral colloquium - Fatana Jafari (22.4.2024)

Monday 22.4.2024 at 13:10, Lecture room I/9

17. 04. 2024 16.02 hod.
By: Damas Gruska

Fatana Jafari:
Classification and Detection of Multiple Sclerosis
White Matter Lesions in Brain MR Images
Using Deep Learning and Explainable AI Methods

Multiple sclerosis (MS) white matter lesions in brain is an immunological illness affecting the central nervous system of the body. This condition causes damaging symptoms to the body, such as blurred eyesight, pain, exhaustion and imbalanced muscles. The physical effects of multiple sclerosis in brain have caused people to lose their ability to function in daily life. So, early diagnosis is the sole action that we can do to prevent MS from progressing. Many researches have already done to detect MS in brain using DL and ML algorithms. However, the decision-making processes within these systems often resemble "black boxes," where the logic and reasoning behind their outputs remain ambiguous for the end-users. This lack of transparency raises significant practical concerns. That is why, In this research we propose an interpretable Multiple sclerosis white matter lesion classification and diagnostic system using DL model and MRI datasets. The primary goal of our research project is not only classification and precise diagnosis with high accuracy of MS in brain, but also its explainability. We aim to integrate two most popular XAI approaches with DL model such as SHAP (SHapley Additive Explanations) values and LIME (Local Interpretable Model Agnostic Explanations ) to provide explanations for the predictions provided by Blackbox models. As a result,these approaches increases the confidence and trustworthy in the black-box model’s decision to be employed in crucial applications under the supervision of human specialists.

Index Terms—Multiple sclerosis ,Explainable AI, Deep learning, SHAP, LIME