Studentenprojekte

Cardiac Segmentation and Landmark Extraction of CMR images of preclinical animal models

Cardiac anatomy and function can be assessed through the reconstruction of three-dimensional (3D) cardiac geometries derived from cardiac magnetic resonance (CMR) imaging. Accurate image segmentation is a crucial step in this process and can be efficiently achieved using machine learning (ML)-based approaches. While robust segmentation networks have been developed for human CMR data, comparable tools for preclinical animal models remain limited. This project aims to develop and train a deep learning network for automated segmentation of CMR images from preclinical animal models. The project will further include the detection of anatomical landmarks and may be extended toward automated shape fitting and quantitative shape analysis. The developed framework will contribute to improving the efficiency, reproducibility, and scalability of preclinical cardiac image analysis. Details anzeigenaddremove