Comparison of quantitative parameters and radiomic features as inputs into machine learning models to predict the Gleason score of prostate cancer lesions

INTRODUCTION

The classification of prostate cancer (PCa) lesions using Prostate Imaging Reporting and Data System (PI-RADS) suffers from poor inter-reader agreement. This study compared quantitative parameters or radiomic features from multiparametric magnetic resonance imaging (mpMRI) or positron emission tomography (PET), as inputs into machine learning (ML) to predict the Gleason scores (GS) of detected lesions for improved PCa lesion classification.

METHODS

20 biopsy-confirmed PCa subjects underwent imaging before radical prostatectomy. A pathologist assigned GS from tumour tissue. Two radiologists and one nuclear medicine physician delineated the lesions on the mpMR and PET images, yielding 45 lesion inputs. Seven quantitative parameters were extracted from the lesions, namely T2-weighted (T2w) image intensity, apparent diffusion coefficient (ADC), transfer constant (K^TRANS), efflux rate constant (K_ep), and extracellular volume ratio (V_e) from mpMR images, and SUV_mean and SUV_max from PET images. Eight radiomic features were selected out of 109 radiomic features from T2w, ADC and PET images. Quantitative parameters or radiomic features, with risk factors of age, prostate-specific antigen (PSA), PSA density and volume, of 45 different lesion inputs were input in different combinations into four ML models - Decision Tree (DT), Support Vector Machine (SVM), k-Nearest-Neighbour (kNN), Ensembles model (EM).

RESULTS

SUV_max yielded the highest accuracy in discriminating detected lesions. Among the 4 ML models, kNN yielded the highest accuracies of 0.929 using either quantitative parameters or radiomic features with risk factors as input.

CONCLUSIONS

ML models' performance is dependent on the input combinations and risk factors further improve ML classification accuracy.

Assessment of tumor blood flow distribution by dynamic contrast-enhanced CT

A distinct feature of the tumor vasculature is its tortuosity and irregular branching of vessels, which can translate to a wider dispersion and higher variability of blood flow in the tumor. To enable tumor blood flow variability to be assessed in vivo by imaging, a tracer kinetic model that accounts for flow dispersion is developed for use with dynamic contrast-enhanced (DCE) CT. The proposed model adopts a multiple-pathway approach and allows for the quantification of relative dispersion in the blood flow distribution, which reflects flow variability in the tumor vasculature. Monte Carlo simulation experiments were performed to study the possibility of reducing the number of model parameters based on the Akaike information criterion approach and to explore possible noise and tissue conditions in which the model might be applicable. The model was used for region-of-interest analysis and to generate perfusion parameter maps for three patient DCE CT cases with cerebral tumors, to illustrate clinical applicability.