AUTHOR=Midya Abhishek , Hiremath Amogh , Huber Jacob , Sankar Viswanathan Vidya , Omil-Lima Danly , Mahran Amr , Bittencourt Leonardo K. , Harsha Tirumani Sree , Ponsky Lee , Shiradkar Rakesh , Madabhushi Anant 

TITLE=Delta radiomic patterns on serial bi-parametric MRI are associated with pathologic upgrading in prostate cancer patients on active surveillance: preliminary findings

JOURNAL=Frontiers in Oncology

VOLUME=13

YEAR=2023

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2023.1166047

DOI=10.3389/fonc.2023.1166047

ISSN=2234-943X

ABSTRACT=<sec><title>Objective</title><p>The aim of this study was to quantify radiomic changes in prostate cancer (PCa) progression on serial MRI among patients on active surveillance (AS) and evaluate their association with pathologic progression on biopsy.</p></sec><sec><title>Methods</title><p>This retrospective study comprised <italic>N</italic> = 121 biopsy-proven PCa patients on AS at a single institution, of whom <italic>N</italic> = 50 at baseline conformed to the inclusion criteria. ISUP Gleason Grade Groups (GGG) were obtained from 12-core TRUS-guided systematic biopsies at baseline and follow-up. A biopsy upgrade (AS+) was defined as an increase in GGG (or in number of positive cores) and no upgrade (AS−) was defined when GGG remained the same during a median period of 18 months. Of <italic>N</italic> = 50 patients at baseline, <italic>N</italic> = 30 had MRI scans available at follow-up (median interval = 18 months) and were included for delta radiomic analysis. A total of 252 radiomic features were extracted from the PCa region of interest identified by board-certified radiologists on 3T bi-parametric MRI [T2-weighted (T2W) and apparent diffusion coefficient (ADC)]. Delta radiomic features were computed as the difference of radiomic feature between baseline and follow-up scans. The association of AS+ with age, prostate-specific antigen (PSA), Prostate Imaging Reporting and Data System (PIRADS v2.1) score, and tumor size was evaluated at baseline and follow-up. Various prediction models were built using random forest (RF) classifier within a threefold cross-validation framework leveraging baseline radiomics (<italic>C<sub>br</sub></italic>), baseline radiomics + baseline clinical (<italic>C<sub>brbcl</sub></italic>), delta radiomics (<italic>C<sub>Δr</sub></italic>), delta radiomics + baseline clinical (<italic>C<sub>Δrbcl</sub></italic>), and delta radiomics + delta clinical (<italic>C<sub>ΔrΔcl</sub></italic>).</p></sec><sec><title>Results</title><p>An AUC of 0.64 ± 0.09 was obtained for <italic>C<sub>br</sub></italic>, which increased to 0.70 ± 0.18 with the integration of clinical variables (<italic>C<sub>brbcl</sub></italic>). <italic>C<sub>Δr</sub></italic> yielded an AUC of 0.74 ± 0.15. Integrating delta radiomics with baseline clinical variables yielded an AUC of 0.77 ± 0.23. <italic>C<sub>ΔrΔcl</sub></italic>resulted in the best AUC of 0.84 ± 0.20 (<italic>p</italic> &lt; 0.05) among all combinations.</p></sec><sec><title>Conclusion</title><p>Our preliminary findings suggest that delta radiomics were more strongly associated with upgrade events compared to PIRADS and other clinical variables. Delta radiomics on serial MRI in combination with changes in clinical variables (PSA and tumor volume) between baseline and follow-up showed the strongest association with biopsy upgrade in PCa patients on AS. Further independent multi-site validation of these preliminary findings is warranted.</p></sec>