ssVERDICT: Self-Supervised VERDICT-MRI for Enhanced Prostate Tumour Characterisation
This addresses the challenge of accurate prostate cancer diagnosis using MRI without needing costly labeled data, though it appears incremental as it applies self-supervised learning to an existing medical imaging model.
The researchers tackled the problem of fitting the VERDICT-MRI model for prostate tumor characterization without requiring labeled training data by developing a self-supervised neural network (ssVERDICT). The method outperformed conventional nonlinear least squares and supervised deep learning in simulations (higher Pearson's correlation, lower bias and MSE) and in vivo with 20 patients (stronger lesion conspicuity and improved discrimination between benign and cancerous tissue).
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.