Novel image-derived AI-based methods to support reproductive medicine

Programme

FTI Dissertation

Project coordination

Danube Private University, Ass.-Prof. Dr. Sepideh Hatamikia 

Project Partners

• Austrian Center for Medical Innovation and Technology (ACMIT)
• Medical University of Vienna 

Researchers involved at DPU 

• Mehran Ahmad

Abstract

Reproductive medicine encompasses a wide range of diagnostic and therapeutic approaches aimed at understanding and treating fertility-related conditions. A key challenge in this field is the accurate prediction and management of individual patient responses to treatment. To date, many clinical decisions particularly those related to ovarian function and hormonal interventions have relied heavily on clinician experience rather than comprehensive data-driven evidence. Patient responses remain highly variable, and current approaches often follow generalized protocols that do not fully account for individual variability. To achieve optimal outcomes, more personalized and data-driven strategies are required. Recently, artificial intelligence (AI) has shown significant potential in supporting decision-making processes in reproductive medicine. However, current evaluations often rely on limited numerical indicators, thereby underutilizing the richness of available multi-modal data. 

This project aims to comprehensively analyze the diverse data generated in reproductive medicine by integrating imaging, clinical, and other patient-specific data sources. By leveraging AI, including both classical machine learning and deep learning approaches, we aim to extract maximal information from these heterogeneous data sources and evaluate their combined predictive value.