Machine and Deep Learning Prediction Of Prostate Cancer Aggressiveness Using Multiparametric MRI

Prostate cancer (PCa) is the most frequent male malignancy and the assessment of PCa aggressiveness, for which a biopsy is required, is fundamental for patient management. Currently, multiparametric (mp) MRI is strongly recommended before biopsy. Quantitative assessment of mpMRI might provide the radiologist with an objective and noninvasive tool for supporting the decision-making in clinical practice and decreasing intra- and inter-reader variability. In this view, high dimensional radiomics features and Machine Learning (ML) techniques, along with Deep Learning (DL) methods working on raw images directly, could assist the radiologist in the clinical workflow. The aim of this study was to develop and validate ML/DL frameworks on mpMRI data to characterize PCas according to their aggressiveness. We optimized several ML/DL frameworks on T2w, ADC and T2w+ADC data, using a patient-based nested validation scheme. The dataset was composed of 112 patients (132 peripheral lesions with Prostate Imaging Reporting and Data System (PI-RADS) score ≥ 3) acquired following both PI-RADS 2.0 and 2.1 guidelines. Firstly, ML/DL frameworks trained and validated on PI-RADS 2.0 data were tested on both PI-RADS 2.0 and 2.1 data. Then, we trained, validated and tested ML/DL frameworks on a multi PI-RADS dataset. We reported the performances in terms of Area Under the Receiver Operating curve (AUROC), specificity and sensitivity. The ML/DL frameworks trained on T2w data achieved the overall best performance. Notably, ML and DL frameworks trained and validated on PI-RADS 2.0 data obtained median AUROC values equal to 0.750 and 0.875, respectively, on unseen PI-RADS 2.0 test set. Similarly, ML/DL frameworks trained and validated on multi PI-RADS T2w data showed median AUROC values equal to 0.795 and 0.750, respectively, on unseen multi PI-RADS test set. Conversely, all the ML/DL frameworks trained and validated on PI-RADS 2.0 data, achieved AUROC values no better than the chance level when tested on PI-RADS 2.1 data. Both ML/DL techniques applied on mpMRI seem to be a valid aid in predicting PCa aggressiveness. In particular, ML/DL frameworks fed with T2w images data (objective, fast and non-invasive) show good performances and might support decision-making in patient diagnostic and therapeutic management, reducing intra- and inter-reader variability.

Negative mpMRI Rules Out Extra-Prostatic Extension in Prostate Cancer Before Robot-Assisted Radical Prostatectomy

The accuracy of multi-parametric MRI (mpMRI) in pre-operative staging of prostate cancer (PCa) remains controversial. Objective: To evaluate the ability of mpMRI to accurately predict PCa extra-prostatic extension (EPE) on a side-specific basis using a risk-stratified 5-point Likert scale. This study also aimed to assess the influence of mpMRI scan quality on diagnostic accuracy. Patients and Methods: We included 124 men who underwent robot-assisted RP (RARP) as part of the NeuroSAFE PROOF study at our centre. Three radiologists retrospectively reviewed mpMRI blinded to RP pathology and assigned a Likert score (1-5) for EPE on each side of the prostate. Each scan was also ascribed a Prostate Imaging Quality (PI-QUAL) score for assessing the quality of the mpMRI scan, where 1 represents poorest and 5 represents best diagnostic quality. Outcome measurements and statistical analyses: Diagnostic performance is presented for binary classification of EPE including 95% confidence intervals and area under the receiver operating characteristic curve (AUC). Results: A total of 231 lobes from 121 men (mean age 56.9 years) were evaluated. 39 men (32.2%), or 43 lobes (18.6%) had EPE. Likert score ≥3 had sensitivity (SE), specificity (SP), NPV, PPV of 90.4%, 52.3%, 96%, 29.9%, respectively, and AUC was 0.82 (95% CI: 0.77-0.86). AUC was 0.63 (95% CI: 0.37-0.9), 0.77 (0.71-0.84) and 0.92 (0.88-0.96) for biparametric scans, PI-QUAL 1-3 and PI-QUAL 4-5 scans, respectively. Conclusions: MRI can be used effectively by genitourinary radiologists to rule out EPE and help inform surgical planning for men undergoing RARP. EPE prediction was more reliable when the MRI scan was a) multi-parametric and b) of a higher image quality according to the PI-QUAL scoring system.

Considering Predictive Factors in the Diagnosis of Clinically Significant Prostate Cancer in Patients with PI-RADS 3 Lesions

The use of multi-parametric magnetic resonance imaging (mpMRI) in conjunction with the Prostate Imaging Reporting and Data System (PI-RADS) is standard practice in the diagnosis, surveillance, and staging of prostate cancer. The risk associated with lesions graded at a PI-RADS score of 3 is ambiguous. Further characterization of the risk associated with PI-RADS 3 lesions would be useful in guiding further work-up and intervention. This study aims to better characterize the utility of PI-RADS 3 and associated risk factors in detecting clinically significant prostate cancer. From a prospectively maintained IRB-approved dataset of all veterans undergoing mpMRI fusion biopsy at the Southeastern Louisiana Veterans Healthcare System, we identified a cohort of 230 PI-RADS 3 lesions from a dataset of 283 consecutive UroNav-guided biopsies in 263 patients from October 2017 to July 2020. Clinically significant prostate cancer (Gleason Grade ≥ 2) was detected in 18 of the biopsied PI-RADS 3 lesions, representing 7.8% of the overall sample. Based on binomial analysis, PSA densities of 0.15 or greater were predictive of clinically significant disease, as was PSA. The location of the lesion within the prostate was not shown to be a statistically significant predictor of prostate cancer overall (p = 0.87), or of clinically significant disease (p = 0.16). The majority of PI-RADS 3 lesions do not represent clinically significant disease; therefore, it is possible to reduce morbidity through biopsy. PSA density is a potential adjunctive factor in deciding which patients with PI-RADS 3 lesions require biopsy. Furthermore, while the risk of prostate cancer for African-American men has been debated in the literature, our findings indicate that race is not predictive of identifying prostate cancer, with comparable Gleason grade distributions on histology between races.

PI-RADS version 2.1 for the evaluation of transition zone lesions: a practical guide for radiologists

Multiparametric magnetic resonance imaging has been established as the most accurate non-invasive diagnostic imaging tool for detecting prostate cancer (PCa) in both the peripheral zone and the transition zone (TZ) using the PI-RADS (Prostate Imaging Reporting and Data System) version 2.1 released in 2019 as a guideline to reporting. Transition zone PCa remains the most difficult to diagnose due to a markedly heterogeneous background and a wide variety of atypical imaging presentations as well as other anatomical and pathological processes mimicking PCa. The aim of this paper was to present a spectrum of PCa in the TZ, as a guide for radiologists.

Overview of radiomics in prostate imaging and future directions

Recent advancements in imaging technology and analysis methods have led to an analytic framework known as radiomics. This framework extracts comprehensive high-dimensional features from imaging data and performs data mining to build analytical models for improved decision support. Its features include many categories spanning texture and shape; thus, it can provide abundant information for precision medicine. Many studies of prostate radiomics have shown promising results in the assessment of pathological features, prediction of treatment response, and stratification of risk groups. Herein, we aimed to provide a general overview of radiomics procedures, discuss technical issues, explain various clinical applications, and suggest future research directions, especially for prostate imaging.

Deep learning–assisted prostate cancer detection on bi-parametric MRI: minimum training data size requirements and effect of prior knowledge

Objectives To assess Prostate Imaging Reporting and Data System (PI-RADS)–trained deep learning (DL) algorithm performance and to investigate the effect of data size and prior knowledge on the detection of clinically significant prostate cancer (csPCa) in biopsy-naïve men with a suspicion of PCa. Methods Multi-institution data included 2734 consecutive biopsy-naïve men with elevated PSA levels (≥ 3 ng/mL) that underwent multi-parametric MRI (mpMRI). mpMRI exams were prospectively reported using PI-RADS v2 by expert radiologists. A DL framework was designed and trained on center 1 data (n = 1952) to predict PI-RADS ≥ 4 (n = 1092) lesions from bi-parametric MRI (bpMRI). Experiments included varying the number of cases and the use of automatic zonal segmentation as a DL prior. Independent center 2 cases (n = 296) that included pathology outcome (systematic and MRI targeted biopsy) were used to compute performance for radiologists and DL. The performance of detecting PI-RADS 4–5 and Gleason > 6 lesions was assessed on 782 unseen cases (486 center 1, 296 center 2) using free-response ROC (FROC) and ROC analysis. Results The DL sensitivity for detecting PI-RADS ≥ 4 lesions was 87% (193/223, 95% CI: 82–91) at an average of 1 false positive (FP) per patient, and an AUC of 0.88 (95% CI: 0.84–0.91). The DL sensitivity for the detection of Gleason > 6 lesions was 85% (79/93, 95% CI: 77–83) @ 1 FP compared to 91% (85/93, 95% CI: 84–96) @ 0.3 FP for a consensus panel of expert radiologists. Data size and prior zonal knowledge significantly affected performance (4%, $$p<0.05$$ p < 0.05 ). Conclusion PI-RADS-trained DL can accurately detect and localize Gleason > 6 lesions. DL could reach expert performance using substantially more than 2000 training cases, and DL zonal segmentation. Key Points • AI for prostate MRI analysis depends strongly on data size and prior zonal knowledge. • AI needs substantially more than 2000 training cases to achieve expert performance.

Comparison of different thresholds of PSA density for risk stratification of PI-RADSv2.1 categories on prostate MRI

Objectives: To compare the effect of different PSA density (PSAD) thresholds on the accuracy for clinically significant prostate cancer (csPCa) of the Prostate Imaging Reporting And Data System v.2.1 (PI-RADSv2.1). Methods: We retrospectively included 123 biopsy-naïve men who underwent multiparametric magnetic resonance imaging (mpMRI) and transperineal mpMRI-targeted and systematic prostate biopsy between April 2019 and October 2020. mpMRI, obtained on a 3.0T magnet with a PI-RADSv2.1-compliant protocol, was read by two radiologists (>1500/>500 mpMRI examinations). csPCa was defined as International Society of Urogenital Pathology grading group ≥2. Receiver operating characteristic analysis was used to calculate per-index lesion sensitivity, specificity, and area under the curve (AUC) of PI-RADSv.2.1 categories after adjusting for PSAD ≥0.10,≥0.15, and ≥0.20 ng/mL ml−1. Per-adjusted category cancer detection rate (CDR) was calculated, and decision analysis performed to compare PSAD-adjusted PI-RADSv.2.1 categories as a biopsy trigger. Results: csPCa prevalence was 43.9%. PSAD-adjustment increased the CDR of PI-RADSv2.1 category 4. Sensitivity/specificity/AUC were 92.6%/53.6%/0.82 for unadjusted PI-RADS, and 85.2%/72.4%/0.84, 62.9%/85.5%/0.83, and 92.4%/53.6%/0.82 when adjusting PI-RADS categories for a 0.10, 0.15, and 0.20 ng/ml ml−1 PSAD threshold, respectively. Triggering biopsy for PI-RADS four lesions and PSAD ≥0.10 ng/mL ml−1 was the strategy with greatest net benefit at 30 and 40% risk probability (0.307 and 0.271, respectively). Conclusions: PI-RADSv2.1 category four with PSAD ≥0.10 ng/mL ml−1 was the biopsy-triggering cut-off with the highest net benefit in the range of expected prevalence for csPCa. Advances in knowledge: 0.10 ng/mL ml−1 is the PSAD threshold with higher clinical utility in stratifying the risk for prostate cancer of PI-RADSv.2.1 categories.