Research

I am currently engaged in research focused on the Application of Explanation and Interpretation Methods for Deep Neural Network Models in Heart Segmentation, supervised by Dr. Gábor Hullám. This research investigates the interpretability of deep learning models applied to medical imaging, particularly CT and X-ray scans, with an emphasis on heart segmentation tasks.

The objective is to explore and evaluate various explanation techniques to better understand model behavior, decision-making processes, and reliability. Methods under consideration include popular interpretation frameworks such as Grad-CAM, SHAP, LIME, and attention-based approaches, with the goal of identifying those that offer the most meaningful insights for this specific domain. The study aims to contribute to the development of more transparent and trustworthy AI systems in medical diagnostics.