AI in Medicine

This repository contains selected projects from my graduate studies in Artificial Intelligence in Medicine, with a focus on medical image analysis, machine learning, deep learning, radiomics, and quantitative imaging. My primary research interest is the development of AI methods for medical imaging, particularly retinal imaging, with the long-term goal of improving cardiovascular risk prediction and early disease detection.

Research Interests

• Artificial Intelligence in Medicine
• Medical Image Analysis
• Retinal Fundus and OCT/OCTA Imaging
• Cardiovascular Risk Prediction
• Explainable AI
• Radiomics
• Machine Learning and Deep Learning
• Image Segmentation and Feature Extraction

Projects:

Retinal Image Analysis Quantitative analysis of retinal structures and vascular features from ophthalmic images.

OCTA Vessel Enhancement and Segmentation Image-processing pipelines for enhancement and segmentation of retinal microvasculature.

Brain MRI Segmentation Segmentation and quantitative analysis of brain MRI using computational image-processing methods.

CT Image Enhancement and Segmentation Filtering, enhancement, and segmentation techniques applied to CT images.

Machine Learning vs. Deep Learning Comparison of classical machine-learning and deep-learning approaches for medical image classification.

Current Research Direction:

Explainable AI for Cardiovascular Risk Prediction Using Retinal Vascular Biomarkers Extracted from Fundus Photographs The goal is to investigate whether quantitative retinal vascular biomarkers combined with machine-learning and XAI methods can contribute to cardiovascular risk assessment.

Tools & Technologies: Python • MATLAB • Machine Learning • Deep Learning • Medical Image Processing • Radiomics • Statistical Analysis