Project description
This project involves the segmentation/contouring of knee bones in knee CT/MRI volumetric image data. Segmentation/contouring of the object-of-interest will be performed automatically using machine learning/deep learning methods. Results will be evaluated using measures such as the Jaccard similarity index, Dice index and Hausdorff distance.
Assumed knowledge
Basic knowledge of probability, linear algebra, statistics, machine learning/deep learning and good programming skills
Industry involvement
Note: You need to register interest in projects from different supervisors (not a number of projects with the one supervisor).
You must also contact each supervisor directly to discuss both the project details and your suitability to undertake the project.