Delineating regions of interest in MRI/S prostate scans for cancer diagnosis

Andrew Nightingale


Supervised by Frank C Langbein; Moderated by Alexia Zoumpoulaki

Prostate cancer is the second most common cancer in men worldwide. Earlier diagnosis combined with better staging and treatment has lead to a decrease in death rates for most developed countries. Magnetic resonance imaging and spectroscopy (MRI/S) plays an important role in differentiating malignant from benign prostate tissue. We are working on a project utilising machine learning techniques to devise an assistant to the radiologist to help in this differentiation.

In an undergraduate project, we have developed an initial version of a tool to browse and manually delineate regions of interest in dicom images. The aim of this project is to extend this tool to include additional functionality. This includes advanced editing and extending the tool to enable incorporating the regions of interest determined by an AI and enable adjustment/correction of these regions of interest by the radiologist to feed this back to the AI. Moreover, integration with a decentralised database, holding the dicoms, lesions/delineations, PIRADS scores, etc. would be useful. There is also potential to consider extending the tool for training or interactions between radiologists to check their diagnosis, etc.

You must have excellent programming skills (largely python) for this project with a focus on UIs and graphics/image processing, and databases.

Final Report (23/09/2020) [Zip Archive]

Publication Form