Meeting Banner
Abstract #3659

Developing a deep learning model to classify normal bone and metastatic bone disease on Whole-Body Diffusion Weighted Imaging 

Antonio Candito1, Matthew D Blackledge1, Fabio Zugni2, Richard Holbrey1, Sebastian Schäfer3, Matthew R Orton1, Ana Ribeiro4, Matthias Baumhauer3, Nina Tunariu1, and Dow-Mu Koh1
1The Institute of Cancer Research, London, United Kingdom, 2IEO, European Institute of Oncology IRCCS, Milan, Italy, 3Mint Medical, Heidelberg, Germany, 4The Royal Marsden NHS Foundation Trust, London, United Kingdom

We employed a deep transfer-learning model to classify whether images from whole-body diffusion-weighted MRI (WBDWI) contain metastatic bone lesions. Our results demonstrate sensitivity/specificity of 0.87/0.89 on 8 test patients, who were not included in the model training. Such a model may accelerate radiological assessment of disease extent from WBDWI, which currently can be cumbersome to interpret due to the large quantity of data (approximately 200-250 images per patient).

This abstract and the presentation materials are available to members only; a login is required.

Join Here