Deep learning for clinical image data
Deep learning has become established as the state-of-the-art approach to analysing and classifying images. While best known for powering web image searches, deep learning has the potential to make a major contribution to disease diagnosis and management by performing image classification tasks that are difficult for human experts and/or require reviewing immense numbers of images. However, successful deep learning models are extremely complicated and need to be trained and developed with great care to be transferred to a specific task. This project involves collaboration with colleagues in the breast-cancer screening and gastroenterology departments at St Vincent's Hospital Melbourne to develop deep learning models and software to aid in the efficient and accurate classification of clinical mammogram and endoscopic images. This project would suit a student interested in applying cutting-edge machine learning methods to problems of immediate clinical urgency.
Dr Davis McCarthy
Bioinformatics & cellular genomics
For further information about this project, contact: