Radiomics in PI-RADS 3 Multiparametric MRI for Prostate Cancer Identification: Literature Models Re-Implementation and Proposal of a Clinical–Radiological Model

Abstract

PI-RADS 3 prostate lesions clinical management is still debated, with high variability among different centers. Identifying clinically significant tumors among PI-RADS 3 is crucial. Radiomics applied to multiparametric MR (mpMR) seems promising. Nevertheless, reproducibility assessment by external validation is required. We retrospectively included all patients with at least one PI-RADS 3 lesion (PI-RADS v2.1) detected on a 3T prostate MRI scan at our Institution (June 2016–March 2021). An MRI-targeted biopsy was used as ground truth. We assessed reproducible mpMRI radiomic features found in the literature. Then, we proposed a new model combining PSA density and two radiomic features (texture regularity (T2) and size zone heterogeneity (ADC)). All models were trained/assessed through 100-repetitions 5-fold cross-validation. Eighty patients were included (26 with GS ≥ 7). In total, 9/20 T2 features (Hector’s model) and 1 T2 feature (Jin’s model) significantly correlated to biopsy on our dataset. PSA density alone predicted clinically significant tumors (sensitivity: 66%; specificity: 71%). Our model obtained a sensitivity of 80% and a specificity of 76%. Standard-compliant works with detailed methodologies achieve comparable radiomic feature sets. Therefore, efforts to facilitate reproducibility are needed, while complex models and imaging protocols seem not, since our model combining PSA density and two radiomic features from routinely performed sequences appeared to differentiate clinically significant cancers.

Phytotherapy Might Have a Role in Reducing Unnecessary Prostate Biopsies: Results from an Exploratory, Randomized Controlled Trial of Two Different Phytotherapeutic Agents

“…We found that only three patients in the Prostaflog ® group showed a significant reduction in total PSA value while having positive mpMRI findings (6%), compared with nine in the Serenoa Repens group (19.5%) (p < 0.001), thereby showing that the risk of lowering PSA caused by prostate cancer by means of a hormonal pathway is very low. After the introduction of mpMRI, the number of unnecessary prostate biopsies has decreased and the role of PSA as diagnostic marker of prostate cancer has been reduced [2,3,31]. However, the use of mpMRI is not yet widespread in all countries, and we therefore still need tools that enable us to differentiate if an elevated PSA is due to prostate cancer or inflammation [32].…”

Phytotherapy Might Have a Role in Reducing Unnecessary Prostate Biopsies: Results From an Exploratory Randomized Controlled Trial of Two Different Phytotherapeutic Agents

“…We found that only 3 patients in the Prostaflog ® group showed a significant reduction of total PSA value while having positive findings at mpMRI (6%) compared with 9 in the Serenoa Repens group (19.5%) (p<0.001), thereby showing that the risk of lowering PSA caused by prostate cancer by means of a hormonal pathway, is very low. After the introduction of mpMRI the number of unnecessary prostate biopsies have decreased and the role of PSA as diagnostic marker of prostate cancer is reduced [2,3,20]. However, the use of mpMRI is not yet widespread in all countries and we therefore still need tools that enable us to differentiate if an elevated PSA is due to prostate cancer or inflammation [21].…”

Towards the Definition of Radiomic Features and Clinical Indices to Enhance the Diagnosis of Clinically Significant Cancers in PI-RADS 4 and 5 Lesions

“…In this work, we explored the putative role of mpMRI radiomics in downgrading non-csPC PI-RADS 4/5 lesions. Many authors have focused on mpMRI radiomics to upgrade PI-RADS 3 lesions [26][27][28]. Nevertheless, to the best of our knowledge, only two studies have tried to apply MRI texture feature analysis to distinguish csPC in lesions scored as PI-RADS 4 and 5.…”