Meeting Banner
Abstract #1839

Detection of prostate cancer in the peripheral zone using machine learning and multiparametic MRI

Neda Gholizadeh1, John Simpson1,2, Saadallah Ramadan1,3, Peter Lau2,3, and Peter B Greer1,2

1The University of Newcastle, Newcastle, Australia, 2Calvary Mater Newcastle, Newcastle, Australia, 3Hunter Medical Research Institute (HMRI), Newcastle, Australia

The aim of this study is to provide a non-invasive voxel based malignant lesion detection tool and probability map for the peripheral zone (PZ) using multi parametric magnetic resonance imaging incorporating DTI as well as standard sequences. A combination of radiomics features extracted from MRI and DTI and supervised machine learning was to develop a tool for cancer detection. Our results demonstrated DTI, when used within the framework of supervised classification, can play a role in the prostate cancer detection. In addition, the posterior probability provide useful information about tumor heterogeneity and may offer better detection of PZ prostate cancer.

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

Join Here