When to biopsy Prostate Imaging and Data Reporting System version 2 (PI-RADSv2) assessment category 3 lesions? Use of clinical and imaging variables to predict cancer diagnosis at targeted biopsy

Management Strategy for Prostate Imaging Reporting and Data System Category 3 Lesions

PURPOSE OF REVIEW

Prostate Imaging Reporting and Data System (PI-RADS) category 3 lesions present a clinical dilemma due to their uncertain nature, which complicates the development of a definitive management strategy. These lesions have an incidence rate of approximately 22-32%, with clinically significant prostate cancer (csPCa) accounting for about 10-30%. Therefore, a thorough evaluation is warranted.

RECENT FINDINGS

This review highlights the need for radiology peer review, including the confirmation of dynamic contrast-enhanced (DCE) compliance, as the initial step. Additional MRI models such as VERDICT or Tofts need to be verified. Current evidence shows that imaging and clinical indicators can be used for risk stratification of PI-RADS 3 lesions. For low-risk lesions, a safety net monitoring approach involving annual repeat MRI can be employed. In contrast, lesions deemed potentially risky based on prostate-specific antigen density (PSAD), 68 Ga-PSMA PET/CT, MPS, Proclarix, or AI/machine learning models should undergo biopsy. It is recommended to establish a multidisciplinary team that takes into account factors such as age, PSAD, prostate, and lesion size, as well as previous biopsy pathological findings. Combining expert opinions, clinical-imaging indicators, and emerging methods will contribute to the development of management strategies for PI-RADS 3 lesions.

Machine learning-based radiomics model to predict benign and malignant PI-RADS v2.1 category 3 lesions: a retrospective multi-center study

Purpose

To develop machine learning-based radiomics models derive from different MRI sequences for distinction between benign and malignant PI-RADS 3 lesions before intervention, and to cross-institution validate the generalization ability of the models.

Methods

The pre-biopsy MRI datas of 463 patients classified as PI-RADS 3 lesions were collected from 4 medical institutions retrospectively. 2347 radiomics features were extracted from the VOI of T2WI, DWI and ADC images. The ANOVA feature ranking method and support vector machine classifier were used to construct 3 single-sequence models and 1 integrated model combined with the features of three sequences. All the models were established in the training set and independently verified in the internal test and external validation set. The AUC was used to compared the predictive performance of PSAD with each model. Hosmer–lemeshow test was used to evaluate the degree of fitting between prediction probability and pathological results. Non-inferiority test was used to check generalization performance of the integrated model.

Results

The difference of PSAD between PCa and benign lesions was statistically significant (P = 0.006), with the mean AUC of 0.701 for predicting clinically significant prostate cancer (internal test AUC = 0.709 vs. external validation AUC = 0.692, P = 0.013) and 0.630 for predicting all cancer (internal test AUC = 0.637 vs. external validation AUC = 0.623, P = 0.036). T2WI-model with the mean AUC of 0.717 for predicting csPCa (internal test AUC = 0.738 vs. external validation AUC = 0.695, P = 0.264) and 0.634 for predicting all cancer (internal test AUC = 0.678 vs. external validation AUC = 0.589, P = 0.547). DWI-model with the mean AUC of 0.658 for predicting csPCa (internal test AUC = 0.635 vs. external validation AUC = 0.681, P = 0.086) and 0.655 for predicting all cancer (internal test AUC = 0.712 vs. external validation AUC = 0.598, P = 0.437). ADC-model with the mean AUC of 0.746 for predicting csPCa (internal test AUC = 0.767 vs. external validation AUC = 0.724, P = 0.269) and 0.645 for predicting all cancer (internal test AUC = 0.650 vs. external validation AUC = 0.640, P = 0.848). Integrated model with the mean AUC of 0.803 for predicting csPCa (internal test AUC = 0.804 vs. external validation AUC = 0.801, P = 0.019) and 0.778 for predicting all cancer (internal test AUC = 0.801 vs. external validation AUC = 0.754, P = 0.047).

Conclusions

The radiomics model based on machine learning has the potential to be a non-invasive tool to distinguish cancerous, noncancerous and csPCa in PI-RADS 3 lesions, and has relatively high generalization ability between different date set.

MRI-measured adipose features as predictive factors for detection of prostate cancer in males undergoing systematic prostate biopsy: a retrospective study based on a Chinese population

In this study, we retrospectively evaluated the data of 901 men undergoing ultrasonography-guided systematic prostate biopsy between March 2013 and May 2022. Adipose features, including periprostatic adipose tissue (PPAT) thickness and subcutaneous fat thickness, were measured using MRI before biopsy. Prediction models of all PCa and clinically significant PCa (csPCa) (Gleason score higher than 6) were established based on variables selected by multivariate logistic regression and prediction nomograms were constructed. Patients with PCa had higher PPAT thickness (4.64 [3.65-5.86] vs. 3.54 [2.49-4.51] mm, p < 0.001) and subcutaneous fat thickness (29.19 [23.05-35.95] vs. 27.90 [21.43-33.93] mm, p = 0.013) than those without PCa. Patients with csPCa had higher PPAT thickness (4.78 [3.80-5.88] vs. 4.52 [3.80-5.63] mm, p = 0.041) than those with non-csPCa. Adding adipose features to the prediction models significantly increased the area under the receiver operating characteristics curve for the prediction of all PCa (0.850 vs. 0.819, p < 0.001) and csPCa (0.827 vs. 0.798, p < 0.001). Based on MRI-measured adipose features and clinical parameters, we established two nomograms that were simple to use and could improve patient selection for prostate biopsy in Chinese population.

Utility of machine learning of apparent diffusion coefficient (ADC) and T2-weighted (T2W) radiomic features in PI-RADS version 2.1 category 3 lesions to predict prostate cancer diagnosis

PURPOSE

To evaluate if machine learning (ML) of radiomic features extracted from apparent diffusion coefficient (ADC) and T2-weighted (T2W) MRI can predict prostate cancer (PCa) diagnosis in Prostate Imaging-Reporting and Data System (PI-RADS) version 2.1 category 3 lesions.

METHODS

This multi-institutional review board-approved retrospective case-control study evaluated 158 men with 160 PI-RADS category 3 lesions (79 peripheral zone, 81 transition zone) diagnosed at 3-Tesla MRI with histopathology diagnosis by MRI-TRUS-guided targeted biopsy. A blinded radiologist confirmed PI-RADS v2.1 score and segmented lesions on axial T2W and ADC images using 3D Slicer, extracting radiomic features with an open-source software (Pyradiomics). Diagnostic accuracy for (1) any PCa and (2) clinically significant (CS; International Society of Urogenital Pathology Grade Group ≥ 2) PCa was assessed using XGBoost with tenfold cross -validation.

RESULTS

From 160 PI-RADS 3 lesions, there were 50.0% (80/160) PCa, including 36.3% (29/80) CS-PCa (63.8% [51/80] ISUP 1, 23.8% [19/80] ISUP 2, 8.8% [7/80] ISUP 3, 3.8% [3/80] ISUP 4). The remaining 50.0% (80/160) lesions were benign. ML of all radiomic features from T2W and ADC achieved area under receiver operating characteristic curve (AUC) for diagnosis of (1) CS-PCa 0.547 (95% Confidence Intervals 0.510-0.584) for T2W and 0.684 (CI 0.652-0.715) for ADC and (2) any PCa 0.608 (CI 0.579-0.636) for T2W and 0.642 (CI 0.614-0.0.670) for ADC.

CONCLUSION

Our results indicate ML of radiomic features extracted from T2W and ADC achieved at best moderate accuracy for determining which PI-RADS category 3 lesions represent PCa.

Pharmacokinetic modeling of dynamic contrast-enhanced (DCE)-MRI in PI-RADS category 3 peripheral zone lesions: preliminary study evaluating DCE-MRI as an imaging biomarker for detection of clinically significant prostate cancers

PURPOSE

To determine if pharmacokinetic modeling of DCE-MRI can diagnose CS-PCa in PI-RADS category 3 PZ lesions with subjective negative DCE-MRI.

MATERIALS AND METHODS

In the present IRB approved, bi-institutional, retrospective, case-control study, we identified 73 men with 73 PZ PI-RADS version 2.1 category 3 lesions with MRI-directed-TRUS-guided targeted biopsy yielding: 12 PZ CS-PCa (ISUP Grade Group 2; N = 9, ISUP 3; N = 3), 27 ISUP 1 PCa and 34 benign lesions. An expert blinded radiologist segmented lesions on ADC and DCE images; segmentations were overlayed onto pharmacokinetic DCE-MRI maps. Mean values were compared between groups using univariate analysis. Diagnostic accuracy was assessed by ROC.

RESULTS

There were no differences in age, PSA, PSAD or clinical stage between groups (p = 0.265-0.645). Mean and 10th percentile ADC did not differ comparing CS-PCa to ISUP 1 PCa and benign lesions (p = 0.376 and 0.598) but was lower comparing ISUP ≥ 1 PCa to benign lesions (p < 0.001). Mean Ktrans (p = 0.003), Ve (p = 0.003) but not Kep (p = 0.387) were higher in CS-PCa compared to ISUP 1 PCa and benign lesions. There were no differences in DCE-MRI metrics comparing ISUP ≥ 1 PCa and benign lesions (p > 0.05). AUC for diagnosis of CS-PCa using Ktrans and Ve were: 0.69 (95% CI 0.52-0.87) and 0.69 (0.49-0.88).

CONCLUSION

Pharmacokinetic modeling of DCE-MRI parameters in PI-RADS category 3 lesions with subjectively negative DCE-MRI show significant differences comparing CS-PCa to ISUP 1 PCa and benign lesions, in this study outperforming ADC. Studies are required to further evaluate these parameters to determine which patients should undergo targeted biopsy for PI-RADS 3 lesions.