Meeting Banner
Abstract #3483

Machine learning for prostate cancer Gleason score prediction using radiomics of T2-weighted imaging, diffusion weighted imaging and T2-mapping

Jussi Toivonen1,2, Ileana Montoya Perez1,2, Parisa Movahedi1,2, Harri Merisaari1,2, Janne Verho2, Pekka Taimen3, Peter J Boström4, Tapio Pahikkala1, Hannu J Aronen2, and Ivan Jambor1,2

1Department of Future Technologies, University of Turku, Turku, Finland, 2Department of Diagnostic Radiology, University of Turku, Turku, Finland, 3Department of Pathology, University of Turku, Turku, Finland, 4Department of Urology, Turku University Hospital, Turku, Finland

We extensively evaluated large number radiomics of prostate T2-weighted imaging, diffusion weighted imaging and T2-mapping. The highest overall performance estimate (AUC = 0.88) we obtained for the model utilizing a small subset of texture features from the ADCm, K, and T2w parameters. These features included texture descriptors based on gray-level co-occurrence matrix, Gabor transform, and the Zernike and Hu moments.

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

Join Here