ssVERDICT: Self-supervised VERDICT-MRI for enhanced prostate tumor characterization.

• DOI: 10.48550/arxiv.2309.06268
• Publication Date: 2024-06-09
• Authors: Snigdha Sen; Saurabh Singh; Hayley Pye; Caroline M. Moore; Hayley C. Whitaker; Shonit Punwani; David Atkinson; Eleftheria Panagi...; Paddy J. Slator
• Keywords: Male; FOS: Computer and information sciences; Computer Science - Machine Learning; Machine Learning (cs.LG); 03 medical and health sciences; Deep Learning; 0302 clinical medicine; Image Interpretation, Computer-Assisted; Image Processing, Computer-Assisted; FOS: Electrical engineering, electronic engineering, information engineering; Humans; Computer Simulation; Least-Squares Analysis; Image and Video Processing (eess.IV); Prostate; Prostatic Neoplasms; Electrical Engineering and Systems Science - Image and Video Processing; Middle Aged; Magnetic Resonance Imaging; 3. Good health; Diffusion Magnetic Resonance Imaging; Neural Networks, Computer; Supervised Machine Learning; Algorithms

AbstractPurposeDemonstrating and assessing self‐supervised machine‐learning fitting of the VERDICT (vascular, extracellular and restricted diffusion for cytometry in tumors) model for prostate cancer.MethodsWe 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 and supervised deep learning. We do this quantitatively on simulated data by comparing the Pearson's correlation coefficient, mean‐squared error, 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.ResultsIn simulations, ssVERDICT outperforms the baseline methods (nonlinear least squares and supervised deep learning) in estimating all the parameters from the VERDICT prostate model in terms of Pearson's correlation coefficient, bias, and mean‐squared error. In vivo, ssVERDICT shows stronger lesion conspicuity across all parameter maps, and improves discrimination between benign and cancerous tissue over the baseline methods.ConclusionssVERDICT significantly outperforms state‐of‐the‐art methods for VERDICT model fitting and shows, for the first time, fitting of a detailed multicompartment biophysical diffusion MRI model with machine learning without the requirement of explicit training labels.