Abstract #4815

Automatic classification of benign and malignant prostate lesions: A comparison using VERDICT DW-MRI and ADC maps

Eleni Chiou^1,2, Edward Johnston³, Francesco Giganti^4,5, Elisenda Bonet-Carne¹, Shonit Punwani³, Iasonas Kokkinos², and Eleftheria Panagiotaki^1,2

¹UCL Centre for Medical Image Computing, Department of Computer Science, University College London, London, United Kingdom, ²Department of Computer Science, University College London, London, United Kingdom, ³UCL Centre for Medical Imaging, Division of Medicine, University College London, London, United Kingdom, ⁴Department of Radiology, UCLH NHS Foundation Trust, University College London, London, United Kingdom, ⁵Division of Surgery & Interventional Science, University College London, London, United Kingdom

Currently, many studies exploit deep learning and mp-MRI data to enhance the diagnostic accuracy of prostate cancer characterisation. In this study, we focus on VERDICT DW-MRI data and compare its diagnostic performance to those of the ADC map and the raw DW-MRI from the mp-MRI. Specifically, we compare the performance obtained by a fully convolutional neural network (CNN) when training and test is performed on the raw VERDICT DW-MRI, the ADC maps and the DW-MRI data from the mp-MRI acquisition. The results indicate that the CNN performs better when it is trained and tested on VERDICT DW-MRI.

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

Join Here