Segmentation of Liver Lesions in WB-DWI Using Deformable Registration and Machine Learning Techniques
Annemarie Knill1,2, Antonio Candito1, Jessica Winfield1,2, James Larkin1,2, Samra Turajlic2,3, Dow Mu Koh1,2, Christina Messiou1,2, and Matthew Blackledge1
1The Institute of Cancer Research, London, United Kingdom, 2The Royal Marsden NHS Foundation Trust, London, United Kingdom, 3The Francis Crick Institute, London, United Kingdom
We present a proof-of-concept study to assess whether deformable registration followed by tissue classification using machine learning (ML) is an effective method for the delineation of liver metastases in whole-body diffusion-weighted imaging (WB-DWI). Deformable atlas-based registration achieves good quality delineation of the liver (Dice coefficient > 70%) and out of three ML models random forest achieved the best F-1 measure for segmenting disease within the liver.
This abstract and the presentation materials are available to members only;
a login is required.