e-Health Application for Detecting Chronic Cardiovascular Diseases: Ischemic Heart Disease

In this project, students will develop an AI model for detecting ischemic heart disease (IHD) from medical images, potentially including both cardiac magnetics resonance images (CMR) and contrast computed tomography (CCT) of the chest, heart, and/or coronary vessels. The exact nature of the imaging to be included will be determined at project start.

This project is derived from the EU-funded SEARCH project (https://ihi-search.eu), which aims to develop trustworthy synthetic medical data to support AI research in healthcare. One major aspect of SEARCH is the testing and use of high-quality biomedical imaging
data, including cardiac MRI (CMR).

In this project, students will develop an AI model for detecting ischemic heart disease (IHD) from medical images, potentially including both cardiac magnetics resonance images (CMR) and contrast computed tomography (CCT) of the chest, heart, and/or coronary vessels. The exact nature of the imaging to be included will be determined at project start.

The project emphasizes the development of machine learning (ML) models for use in e-Health and Clinical Decision Support (CDS) systems. Using publicly available or simulated (synthetic) imaging datasets, students will train and evaluate deep learning models (e.g., CNN, RNN, MLP) to classify images as normal or IHD-affected.

Additionally, the project may explore explainable AI (XAI) methods to interpret the model’s predictions and to ensure transparency, which is crucial for medical applications.

Goals / learning outcomes

Students will:

• Use open imaging datasets (e.g., the Cardiac Atlas Project, the NotIs CMR database, the SCMR Registry) and/or synthetic images of normal and IHD hearts/vessels.
• Train baseline deep learning models (e.g., CNN) for binary classification (IHD vs normal).
• Evaluate model performance using clinical metric (e.g., sensitivity, specificity, AUROC).
• Investigate interpretability using XAI tools (e.g. saliency methods).
• Potentially, explore multi-label classification scenarios involving co-existing conditions like atrial fibrillation (AF).

This project contributes to SEARCH’s broader goal of developing realistic and privacy-preserving synthetic data for safe and effective AI applications in cardiology.

Medical signal data is critical for developing AI tools, yet often inaccessible due to privacy concerns. This project enables students to use and to evaluate the efficacy of synthetic cardiac MRI data to address this limitation, with direct relevance to cardiac diagnostics in ischemic heart disease.

Requirements

• Basic understanding of machine and deep learning
• Familiarity with convolutional neural networks and Python programming
• Experience with image processing or evaluation metrics is a plus

Students will use publicly available datasets and synthetic data provided. Ethical handling of data and reproducible code practices are required, aligning with the open science goals of the SEARCH project.

Supervisors

• Vajira Thambawita
• Molly Maleckar
• Pål Halvorsen

Collaboration partners

This project is part of SEARCH (Synthetic hEalthcare dAta goveRnanCe Hub), a multi-disciplinary initiative focused on creating synthetic healthcare data and facilitating secure data sharing across the biomedical ecosystem. Read more about SEARCH here.