ssVERDICT: Self-Supervised VERDICT-MRI for Enhanced Prostate Tumour Characterisation

TL;DR

This paper introduces ssVERDICT, a self-supervised neural network that accurately fits the VERDICT MRI model for prostate tissue characterization without needing training data, outperforming traditional methods in simulations and clinical data.

Contribution

The paper presents the first self-supervised approach for fitting a complex biophysical MRI model, eliminating the need for labeled training data and improving accuracy over existing methods.

Findings

ssVERDICT outperforms baseline methods in simulations.

It provides stronger lesion contrast in vivo.

It improves benign vs. cancer tissue discrimination.

Abstract

Purpose: Demonstrating and assessing self-supervised machine learning fitting of the VERDICT (Vascular, Extracellular and Restricted DIffusion for Cytometry in Tumours) model for prostate. Methods: We derive a self-supervised neural network for fitting VERDICT (ssVERDICT) that estimates parameter maps without training data. We compare the performance of ssVERDICT to two established baseline methods for fitting diffusion MRI models: conventional nonlinear least squares (NLLS) and supervised deep learning. We do this quantitatively on simulated data, by comparing the Pearson's correlation coefficient, mean-squared error (MSE), bias, and variance with respect to the simulated ground truth. We also calculate in vivo parameter maps on a cohort of 20 prostate cancer patients and compare the methods' performance in discriminating benign from cancerous tissue via Wilcoxon's signed-rank test. Results: In simulations, ssVERDICT outperforms the baseline methods (NLLS and supervised DL) in estimating all the parameters from the VERDICT prostate model in terms of Pearson's correlation coefficient, bias, and MSE. In vivo, ssVERDICT shows stronger lesion conspicuity across all parameter maps, and improves discrimination between benign and cancerous tissue over the baseline methods. Conclusion: ssVERDICT significantly outperforms state-of-the-art methods for VERDICT model fitting, and shows for the first time, fitting of a complex three-compartment biophysical model with machine learning without the requirement of explicit training labels.