Interaction of MRI and active surveillance in prostate cancer: Time to re-evaluate the active surveillance inclusion criteria

Beyond Multiparametric MRI and towards Radiomics to Detect Prostate Cancer: A Machine Learning Model to Predict Clinically Significant Lesions

The risk of misclassifying clinically significant prostate cancer (csPCa) by multiparametric magnetic resonance imaging is consistent, also using the updated PIRADS score and although different definitions of csPCa, patients with Gleason Grade group (GG) ≥ 3 have a significantly worse prognosis. This study aims to develop a machine learning model predicting csPCa (i.e., any GG ≥ 3 lesion at target biopsy) by mpMRI radiomic features and analyzing similarities between GG groups. One hundred and two patients with 117 PIRADS ≥ 3 lesions at mpMRI underwent target+systematic biopsy, providing histologic diagnosis of PCa, 61 GG < 3 and 56 GG ≥ 3. Features were generated locally from an apparent diffusion coefficient and selected, using the LASSO method and Wilcoxon rank-sum test (p < 0.001), to achieve only four features. After data augmentation, the features were exploited to train a support vector machine classifier, subsequently validated on a test set. To assess the results, Kruskal−Wallis and Wilcoxon rank-sum tests (p < 0.001) and receiver operating characteristic (ROC)-related metrics were used. GG1 and GG2 were equivalent (p = 0.26), whilst clear separations between either GG[1,2] and GG ≥ 3 exist (p < 10−6). On the test set, the area under the curve = 0.88 (95% CI, 0.68−0.94), with positive and negative predictive values being 84%. The features retain a histological interpretation. Our model hints at GG2 being much more similar to GG1 than GG ≥ 3.

Special Issue "Prostate Cancer: Recent Advances in Diagnostics and Treatment Planning"

This editorial of the Special Issue "Prostate Cancer: Recent Advances in Diagnostics and Treatment Planning" aims to draw more attention to the broad and diverse field of prostate cancer (PCa) diagnosis and the utilization of different diagnostic means to improve clinical decision-making and treatment strategy planning [...].

Adverse upgrading and/or upstaging in contemporary low-risk prostate cancer patients

Background

Upgrading and/or upstaging in low-risk prostate cancer (PCa) patients may represent an indication for active treatment instead of active surveillance (AS). We addressed contemporary upgrading and/or upstaging rates in a large population based-cohort of low-risk PCa patients.

Materials and methods

Whitin the SEER database (2010–2015), NCCN low-risk PCa patients were identified across management modalities: radical prostatectomy (RP), radiotherapy (RT) and non-local treatment (NLT). In RP patients, upgrading and/or upstaging rates were assessed in logistic regression models.

Results

Overall, of 27,901 low-risk PCa patients, 38% underwent RP vs 28% RT vs 34% NLT. RP patients were the youngest and harbored the highest percentage of positive cores and a higher rate of cT2a than NLT. At RP, 46.2% were upgraded to GGG ≥ 2, 6.0% to GGG ≥ 3 and 10.5% harbored nonorgan-confined stage (NOC, pT3-4 or pN1). Of NOC patients, 1.6% harbored GGG ≥ 3, 6.3% harbored GGG2 and 2.6% harbored GGG1. Of pT2 patients, 4.4% harbored GGG ≥ 3, 33.9% harbored GGG2 and 51.3% harbored GGG1. Age, PSA, percentage of positive cores and number of positive cores independently predicted the presence of NOC and/or GGG ≥ 3, but with low accuracy (63.9%).

Conclusions

In low-risk PCa, critical changes between tumor grade and stage at biopsy vs RP may be expected in very few patients: NOC with GGG ≥ 3 in 1.6% and NOC with GGG2 in 6.3%. Other patients with upgrading and/or upstaging combinations will invariably harbor either pT2 or GGG1 that far less critically affect PCa prognosis.