Comparative performance of MRI-derived PRECISE scores and delta-radiomics models for the prediction of prostate cancer progression in patients on active surveillance

Abstract

Objectives To compare the performance of the PRECISE scoring system against several MRI-derived delta-radiomics models for predicting histopathological prostate cancer (PCa) progression in patients on active surveillance (AS). Methods The study included AS patients with biopsy-proven PCa with a minimum follow-up of 2 years and at least one repeat targeted biopsy. Histopathological progression was defined as grade group progression from diagnostic biopsy. The control group included patients with both radiologically and histopathologically stable disease. PRECISE scores were applied prospectively by four uro-radiologists with 5–16 years’ experience. T2WI- and ADC-derived delta-radiomics features were computed using baseline and latest available MRI scans, with the predictive modelling performed using the parenclitic networks (PN), least absolute shrinkage and selection operator (LASSO) logistic regression, and random forests (RF) algorithms. Standard measures of discrimination and areas under the ROC curve (AUCs) were calculated, with AUCs compared using DeLong’s test. Results The study included 64 patients (27 progressors and 37 non-progressors) with a median follow-up of 46 months. PRECISE scores had the highest specificity (94.7%) and positive predictive value (90.9%), whilst RF had the highest sensitivity (92.6%) and negative predictive value (92.6%) for predicting disease progression. The AUC for PRECISE (84.4%) was non-significantly higher than AUCs of 81.5%, 78.0%, and 80.9% for PN, LASSO regression, and RF, respectively (p = 0.64, 0.43, and 0.57, respectively). No significant differences were observed between AUCs of the three delta-radiomics models (p-value range 0.34–0.77). Conclusions PRECISE and delta-radiomics models achieved comparably good performance for predicting PCa progression in AS patients. Key Points • The observed high specificity and PPV of PRECISE are complemented by the high sensitivity and NPV of delta-radiomics, suggesting a possible synergy between the two image assessment approaches. • The comparable performance of delta-radiomics to PRECISE scores applied by expert readers highlights the prospective use of the former as an objective and standardisable quantitative tool for MRI-guided AS follow-up. • The marginally superior performance of parenclitic networks compared to conventional machine learning algorithms warrants its further use in radiomics research.

AI-assisted biparametric MRI surveillance of prostate cancer: feasibility study

“…Only one other study, by Sushentsev et al (2021), investigated the use of AI for automatic detection of csPCa on sequential prostate MRI scans. They used changes in radiomics features for the similar task of detecting pathological grade progression in an AS cohort [24]. Their best performing AI model achieved an AUC of 0.82, which is similar to the performance achieved in the present study.…”

Radiomics in prostate cancer: an up-to-date review

“… 186 RF compared with SVM leads to reduced training and testing costs and in the same time performance is comparable. 187 Following the same line, another study, 188 showed that RFs have the best performance with the highest sensitivity (92.6%) and negative predictive value (92.6%). RF method compiles a high number of regression trees (RTs) to build a forest, to address the instability of the classification, and RT.…”

“…The PRECISE scoring system studied in PCa, with medical images from MRI, compared the performance with parenclitic networks, LASSO regression, and RFs ML methods, and had better results. 188 A recent meta-analysis showed that there are no differences in heterogeneity, performance, sensitivity, and specificity among different ML algorithms used in PCa radiomics studies. 206 In DL studies, heterogeneity was higher than among the studies employing other ML approaches to detect PCa.…”

Assessing the impact of MRI based diagnostics on pre-treatment disease classification and prognostic model performance in men diagnosed with new prostate cancer from an unscreened population

“…A number of groups are now also exploring using MRI in screening trials although at this juncture it is unclear if MRI will pass the Wilson and Jungner criteria to reduce mortality or perhaps only in helping reduce the harms of screening [27,28]. At a more immediate level MRI is being proposed as a useful adjunct to risk stratification in decision making albeit with surrogate markers of outcome such as adverse pathology, biochemical relapse free survival or progression rates on Active Surveillance [29][30][31][32]. In contrast there is uncertainty on whether MRI will actually improve long-term survival outcomes [10,13,33].Modelling studies so far have found little evidence for this and MRI may in fact contribute to over-diagnosis and over-treatment [10].…”