Accuracy and agreement of PIRADSv2 for prostate cancer mpMRI: A multireader study

Predictors of Contralateral Disease in Men with Unilateral Lesions on Multiparametric MRI

OBJECTIVE

To evaluate predictors of contralateral clinically significant prostate cancer (csPCa) in men with biopsy proven unilateral lesions on magnetic resonance imaging (MRI).

METHODS

We retrospectively identified men with no prior diagnosis of PCa with unilateral biopsy confirmed csPCa PI-RADS 2-5 lesions within our institutional biopsy database. Multivariate logistic regression was used to identify clinical predictors of contralateral disease.

RESULTS

Four hundred ninety men met study inclusion criteria, of which 385 men (78.6%) had no contralateral csPCa and 105 men (21.4%) had contralateral csPCa. (Figure 1). Prior negative biopsy (OR 0.34 [0.14, 0.75], p = 0.012), PSA density (OR 18.8 [2.77, 249], p = 0.017), and tumor location in the transverse plane ("Posterior": OR 1.93 [1.02, 3.87], p =0.048; "Throughout Transverse Plane": OR 6.56 [2.26, 19.6], p <0.001) were significantly associated with contralateral csPCa in multivariate logistic regression models. However, there appear to be no attributes within the MRI-targeted tumor that reliably predict contralateral csPCa (Table 2).

CONCLUSIONS

Approximately 20% of men with unilateral MRI findings and csPCa on targeted-biopsy were found to have contralateral csPCa. Prior negative biopsy was associated with a decreased odds of contralateral csPCa. PSA density and tumor in the posterior aspect of or throughout the transverse plane were associated with increased odds of contralateral csPCA. Consideration of these clinical factors may afford an opportunity to only use SB in cases in which the odds of contralateral csPCa are high.

Perspectives on technology: Prostate Imaging-Reporting and Data System (PI-RADS) interobserver variability

OBJECTIVES

To explore the topic of Prostate Imaging-Reporting and Data System (PI-RADS) interobserver variability, including a discussion of major sources, mitigation approaches, and future directions.

METHODS

A narrative review of PI-RADS interobserver variability.

RESULTS

PI-RADS was developed in 2012 to set technical standards for prostate magnetic resonance imaging (MRI), reduce interobserver variability at interpretation, and improve diagnostic accuracy in the MRI-directed diagnostic pathway for detection of clinically significant prostate cancer. While PI-RADS has been validated in selected research cohorts with prostate cancer imaging experts, subsequent prospective studies in routine clinical practice demonstrate wide variability in diagnostic performance. Radiologist and biopsy operator experience are the most important contributing drivers of high-quality care among multiple interrelated factors including variability in MRI hardware and technique, image quality, and population and patient-specific factors such as prostate cancer disease prevalence. Iterative improvements in PI-RADS have helped flatten the curve for novice readers and reduce variability. Innovations in image quality reporting, administrative and organisational workflows, and artificial intelligence hold promise in improving variability even further.

CONCLUSION

Continued research into PI-RADS is needed to facilitate benchmark creation, reader certification, and independent accreditation, which are systems-level interventions needed to uphold and maintain high-quality prostate MRI across entire populations.

A novel model incorporating quantitative contrast-enhanced ultrasound into PI-RADSv2-based nomogram detecting clinically significant prostate cancer

The diagnostic accuracy of clinically significant prostate cancer (csPCa) of Prostate Imaging Reporting and Data System version 2 (PI-RADSv2) is limited by subjectivity in result interpretation and the false positive results from certain similar anatomic structures. We aimed to establish a new model combining quantitative contrast-enhanced ultrasound, PI-RADSv2, clinical parameters to optimize the PI-RADSv2-based model. The analysis was conducted based on a data set of 151 patients from 2019 to 2022, multiple regression analysis showed that prostate specific antigen density, age, PI-RADSv2, quantitative parameters (rush time, wash-out area under the curve) were independent predictors. Based on these predictors, we established a new predictive model, the AUCs of the model were 0.910 and 0.879 in training and validation cohort, which were higher than those of PI-RADSv2-based model (0.865 and 0.821 in training and validation cohort). Net Reclassification Index analysis indicated that the new predictive model improved the classification of patients. Decision curve analysis showed that in most risk probabilities, the new predictive model improved the clinical utility of PI-RADSv2-based model. Generally, this new predictive model showed that quantitative parameters from contrast enhanced ultrasound could help to improve the diagnostic performance of PI-RADSv2 based model in detecting csPCa.

Added value of randomised biopsy to multiparametric magnetic resonance imaging-targeted biopsy of the prostate in a contemporary cohort

OBJECTIVE

To assess the added value of concurrent systematic randomised ultrasonography-guided biopsy (SBx) to multiparametric magnetic resonance imaging (mpMRI)-targeted biopsy and the additional rate of overdiagnosis of clinically insignificant prostate cancer (ciPCa) by SBx in a large contemporary, real-world cohort.

PATIENTS AND METHODS

A total of 1552 patients with positive mpMRI and consecutive mpMRI-targeted biopsy and SBx were enrolled. Added value and the rate of overdiagnosis by SBx was evaluated.

PRIMARY OUTCOME

added value of SBx, defined as detection rate of clinically significant PCa (csPCa; International Society of Urological Pathology [ISUP] Grade ≥2) by SBx, while mpMRI-targeted biopsy was negative or showed ciPCa (ISUP Grade 1).

SECONDARY OUTCOME

rate of overdiagnosis by SBx, defined as detection of ciPCa in patients with negative mpMRI-targeted biopsy and PSA level of <10 ng/mL.

RESULTS

Detection rate of csPCa by mpMRI-targeted biopsy and/or SBx was 753/1552 (49%). Added value of SBx was 145/944 (15%). Rate of overdiagnosis by SBx was 146/656 (22%). Added value of SBx did not change when comparing patients with previous prostate biopsy and biopsy naïve patients. In multivariable analysis, a Prostate Imaging-Reporting and Data System (PI-RADS) 4 index lesion (odds ratio [OR] 3.19, 95% confidence interval [CI] 1.66-6.78; P = 0.001), a PI-RADS 5 index lesion (OR 2.89, 95% CI 1.39-6.46; P = 0.006) and age (OR 1.05, 95% CI 1.03-1.08; P < 0.001) were independently associated with added value of SBx.

CONCLUSIONS

In our real-world analysis, we saw a significant impact on added value and added rate of overdiagnosis by SBx. Subgroup analysis showed no significant decrease of added value in any evaluated risk group. Therefore, we do not endorse omitting concurrent SBx to mpMRI-guided biopsy of the prostate.

Diagnostic Utility of Artificial Intelligence-assisted Transperineal Biopsy Planning in Prostate Cancer Suspected Men: A Prospective Cohort Study

BACKGROUND AND OBJECTIVE

Accurate magnetic resonance imaging (MRI) reporting is essential for transperineal prostate biopsy (TPB) planning. Although approved computer-aided diagnosis (CAD) tools may assist urologists in this task, evidence of improved clinically significant prostate cancer (csPCa) detection is lacking. Therefore, we aimed to document the diagnostic utility of using Prostate Imaging Reporting and Data System (PI-RADS) and CAD for biopsy planning compared with PI-RADS alone.

METHODS

A total of 262 consecutive men scheduled for TPB at our referral centre were analysed. Reported PI-RADS lesions and an US Food and Drug Administration-cleared CAD tool were used for TPB planning. PI-RADS and CAD lesions were targeted on TPB, while four (interquartile range: 2-5) systematic biopsies were taken. The outcomes were the (1) proportion of csPCa (grade group ≥2) and (2) number of targeted lesions and false-positive rate. Performance was tested using free-response receiver operating characteristic curves and the exact Fisher-Yates test.

KEY FINDINGS AND LIMITATIONS

Overall, csPCa was detected in 56% (146/262) of men, with sensitivity of 92% and 97% (p = 0.007) for PI-RADS- and CAD-directed TPB, respectively. In 4% (10/262), csPCa was detected solely by CAD-directed biopsies; in 8% (22/262), additional csPCa lesions were detected. However, the number of targeted lesions increased by 54% (518 vs 336) and the false-positive rate doubled (0.66 vs 1.39; p = 0.009). Limitations include biopsies only for men at clinical/radiological suspicion and no multidisciplinary review of MRI before biopsy.

CONCLUSIONS AND CLINICAL IMPLICATIONS

The tested CAD tool for TPB planning improves csPCa detection at the cost of an increased number of lesions sampled and false positives. This may enable more personalised biopsy planning depending on urological and patient preferences.

PATIENT SUMMARY

The computer-aided diagnosis tool tested for transperineal prostate biopsy planning improves the detection of clinically significant prostate cancer at the cost of an increased number of lesions sampled and false positives. This may enable more personalised biopsy planning depending on urological and patient preferences.

Weakly Supervised MRI Slice-Level Deep Learning Classification of Prostate Cancer Approximates Full Voxel- and Slice-Level Annotation: Effect of Increasing Training Set Size

BACKGROUND

Weakly supervised learning promises reduced annotation effort while maintaining performance.

PURPOSE

To compare weakly supervised training with full slice-wise annotated training of a deep convolutional classification network (CNN) for prostate cancer (PC).

STUDY TYPE

Retrospective.

SUBJECTS

One thousand four hundred eighty-nine consecutive institutional prostate MRI examinations from men with suspicion for PC (65 ± 8 years) between January 2015 and November 2020 were split into training (N = 794, enriched with 204 PROSTATEx examinations) and test set (N = 695).

FIELD STRENGTH/SEQUENCE

1.5 and 3T, T2-weighted turbo-spin-echo and diffusion-weighted echo-planar imaging.

ASSESSMENT

Histopathological ground truth was provided by targeted and extended systematic biopsy. Reference training was performed using slice-level annotation (SLA) and compared to iterative training utilizing patient-level annotations (PLAs) with supervised feedback of CNN estimates into the next training iteration at three incremental training set sizes (N = 200, 500, 998). Model performance was assessed by comparing specificity at fixed sensitivity of 0.97 [254/262] emulating PI-RADS ≥ 3, and 0.88-0.90 [231-236/262] emulating PI-RADS ≥ 4 decisions.

STATISTICAL TESTS

Receiver operating characteristic (ROC) and area under the curve (AUC) was compared using DeLong and Obuchowski test. Sensitivity and specificity were compared using McNemar test. Statistical significance threshold was P = 0.05.

RESULTS

Test set (N = 695) ROC-AUC performance of SLA (trained with 200/500/998 exams) was 0.75/0.80/0.83, respectively. PLA achieved lower ROC-AUC of 0.64/0.72/0.78. Both increased performance significantly with increasing training set size. ROC-AUC for SLA at 500 exams was comparable to PLA at 998 exams (P = 0.28). ROC-AUC was significantly different between SLA and PLA at same training set sizes, however the ROC-AUC difference decreased significantly from 200 to 998 training exams. Emulating PI-RADS ≥ 3 decisions, difference between PLA specificity of 0.12 [51/433] and SLA specificity of 0.13 [55/433] became undetectable (P = 1.0) at 998 exams. Emulating PI-RADS ≥ 4 decisions, at 998 exams, SLA specificity of 0.51 [221/433] remained higher than PLA specificity at 0.39 [170/433]. However, PLA specificity at 998 exams became comparable to SLA specificity of 0.37 [159/433] at 200 exams (P = 0.70).

DATA CONCLUSION

Weakly supervised training of a classification CNN using patient-level-only annotation had lower performance compared to training with slice-wise annotations, but improved significantly faster with additional training data.

EVIDENCE LEVEL

3 TECHNICAL EFFICACY: Stage 2.

Evaluating Diagnostic Accuracy and Inter-reader Agreement of the Prostate Imaging After Focal Ablation Scoring System

Background and objective

Focal therapy (FT) is increasingly recognized as a promising approach for managing localized prostate cancer (PCa), notably reducing treatment-related morbidities. However, post-treatment anatomical changes present significant challenges for surveillance using current imaging techniques. This study aimed to evaluate the inter-reader agreement and efficacy of the Prostate Imaging after Focal Ablation (PI-FAB) scoring system in detecting clinically significant prostate cancer (csPCa) on post-FT multiparametric magnetic resonance imaging (mpMRI).

Methods

A retrospective cohort study was conducted involving patients who underwent primary FT for localized csPCa between 2013 and 2023, followed by post-FT mpMRI and a prostate biopsy. Two expert genitourinary radiologists retrospectively evaluated post-FT mpMRI using PI-FAB. The key measures included inter-reader agreement of PI-FAB scores, assessed by quadratic weighted Cohen's kappa (κ), and the system's efficacy in predicting in-field recurrence of csPCa, with a PI-FAB score cutoff of 3. Additional diagnostic metrics including sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), and overall accuracy were also evaluated.

Key findings and limitations

Scans from 38 patients were analyzed, revealing a moderate level of agreement in PI-FAB scoring (κ = 0.56). Both radiologists achieved sensitivity of 93% in detecting csPCa, although specificity, PPVs, NPVs, and accuracy varied.

Conclusions and clinical implications

The PI-FAB scoring system exhibited high sensitivity with moderate inter-reader agreement in detecting in-field recurrence of csPCa. Despite promising results, its low specificity and PPV necessitate further refinement. These findings underscore the need for larger studies to validate the clinical utility of PI-FAB, potentially aiding in standardizing post-treatment surveillance.

Patient summary

Focal therapy has emerged as a promising approach for managing localized prostate cancer, but limitations in current imaging techniques present significant challenges for post-treatment surveillance. The Prostate Imaging after Focal Ablation (PI-FAB) scoring system showed high sensitivity for detecting in-field recurrence of clinically significant prostate cancer. However, its low specificity and positive predictive value necessitate further refinement. Larger, more comprehensive studies are needed to fully validate its clinical utility.

Using an artificial intelligence model to detect and localize visible clinically significant prostate cancer in prostate magnetic resonance imaging: a multicenter external validation study

Background

An increasing number of patients with suspected clinically significant prostate cancer (csPCa) are undergoing prostate multiparametric magnetic resonance imaging (mpMRI). The role of artificial intelligence (AI) algorithms in interpreting prostate mpMRI needs to be tested with multicenter external data. This study aimed to investigate the diagnostic efficacy of an AI model in detecting and localizing visible csPCa on mpMRI a multicenter external data set.

Methods

The data of 2,105 patients suspected of having prostate cancer from four hospitals were retrospectively collected to develop an AI model to detect and localize suspicious csPCa. The lesions were annotated based on pathology records by two radiologists. Diffusion-weighted imaging (DWI) and apparent diffusion coefficient (ADC) values were used as the input for the three-dimensional U-Net framework. Subsequently, the model was validated using an external data set comprising the data of 557 patients from three hospitals. Sensitivity, specificity, and accuracy were employed to evaluate the diagnostic efficacy of the model.

Results

At the lesion level, the model had a sensitivity of 0.654. At the overall sextant level, the model had a sensitivity, specificity, and accuracy of 0.846, 0.884, and 0.874, respectively. At the patient level, the model had a sensitivity, specificity, and accuracy of 0.943, 0.776, and 0.849, respectively. The AI-predicted accuracy for the csPCa patients (231/245, 0.943) was significantly higher than that for the non-csPCa patients (242/312, 0.776) (P<0.001). The lesion number and tumor volume were greater in the correctly diagnosed patients than the incorrectly diagnosed patients (both P<0.001). Among the positive patients, those with lower average ADC values had a higher rate of correct diagnosis than those with higher average ADC values (P=0.01).

Conclusions

The AI model exhibited acceptable accuracy in detecting and localizing visible csPCa at the patient and sextant levels. However, further improvements need to be made to enhance the sensitivity of the model at the lesion level.

Optimal size threshold for PIRADSv2 category 5 upgrade and its positive predictive value: is it predictive of "very high" likelihood of clinically-significant cancer?

AIM

To identify the optimal size metric and threshold for Prostate Imaging Reporting and Data System (PIRADS) 5 upgrade, calculate its positive predictive value (PPV) for clinically-significant prostate cancer (csPCA), and determine if it is indicative of a "very high" likelihood of csPCA.

MATERIALS AND METHODS

One hundred and forty-three PIRADS 4 or 5 lesions were evaluated. Lesion diameters were used to calculate lesion volume (LV). Pearson correlation between maximum lesion diameter (MLD) and LV was calculated. Area under the curve (AUC) for discriminating csPCA (Gleason grade ≥ 3 + 4) was calculated using MLD and LV. Optimal size thresholds (using Youden index) and highly predictive size thresholds were identified for the whole prostate (WP), peripheral zone (PZ), and transitional zone (TZ).

RESULTS

There was high correlation between MLD and LV (r=0.77-0.81), with comparable AUCs for MLD and LV in the identification of csPCA in the WP (0.73, 0.72), PZ (0.73, 0.73), and TZ (0.79, 0.75). Optimal MLD thresholds were 1.4, 1.4, and 1.6 cm in the WP, PZ, and TZ respectively, with PPVs of 76%, 81%, and 69%, respectively. An MLD threshold of 2.7 cm would be needed in the WP to achieve a PPV approaching 90%, with sensitivity decreasing to 10%.

CONCLUSIONS

There is high correlation between MLD and LV with comparable discrimination of csPCA using each. PIRADSv2's 1.5 cm MLD threshold is near the optimal threshold for PIRADS 5 upgrade but has moderate PPV. A much higher threshold would be needed to increase its PPV, with significant sacrifice in sensitivity.

Computed Tomography-Guided Prostate Sampling and Fiducial Marker Insertion in Patients With Absent Rectums

OBJECTIVES

We aimed to present our experience and the outcomes of a novel technique, computed tomography (CT)-guided prostate biopsy and fiducial marker insertion in patients with absent rectums.

METHODS

Patients who underwent CT-guided prostate biopsy at a single institution from November 2010 to November 2022 were retrospectively reviewed. Patients were included if they had a clinical suspicion of prostate cancer and had absent rectums from previous surgical resection. Contrast-enhanced CT scan was used to perform transgluteal prostate biopsy. Patient demographics, multiparametric magnetic resonance imaging, and biopsy details were recorded.

RESULTS

Thirteen biopsy procedures and 1 CT-guided fiducial marker insertion were performed on 12 unique patients. The reasons for the absence of rectums included surgical resection for rectal cancer (n = 10) and surgical resection for inflammatory bowel disease (n = 2). Clinically significant cancer was found in 7 of 13 biopsy results (52.8%), clinically insignificant cancer in 3 of 13 (23.1%), and benign cancer in 3 of 13 (23.1%). No complications were recorded.

CONCLUSIONS

Our data support CT-guided prostate biopsy as an accurate and effective technique for investigating prostate cancer that requires tissue sampling in patients with absent rectums.

Contemporary Approach to Prostate Imaging and Data Reporting System Score 3 Lesions

The aim of this article is to review the technical and clinical considerations encountered with PI-RADS 3 lesions, which are equivocal for clinically significant Prostate Cancer (csPCa) with detection rates ranging between 10% and 35%. The number of PI-RADS 3 lesions reported vary according to several factors including MRI quality and radiologist training/expertise among the most influential. PI-RADS v.2.1 updated definitions for scores 2 and 3 in the PZ and scores 1 and 2 in the TZ is reviewed. The role of DWI role is highlighted in the assessment of the TZ with the possibility of upgrading score 2 lesions to score 3 based on DWI score. Given the increased utilization for prostate MRI, biparametric MRI can be considered as an alternative for low-risk patients where there is a need to rule out csPCa acknowledging this technique may increase the number of indeterminate cases going for biopsies. Management of patients with equivocal lesions at mpMRI and factors influencing biopsy decision process remain as an unmet need and additional studies using molecular/imaging markers as well as artificial intelligence tools are needed to further address their role in proper patient selection for biopsy.

Effect of preoperative PI-RADS assessment on pathological outcomes in patients who underwent radical prostatectomy

OBJECTIVE

To assess the effect of preoperative MRI with standardized Prostate Imaging-Reporting and Data System (PI-RADS) assessment on pathological outcomes in prostate cancer (PCa) patients who underwent radical prostatectomy (RP).

PATIENTS AND METHODS

This retrospective cohort study included patients who had undergone prostate MRI and subsequent RP for PCa between January 2017 and December 2022. The patients were divided into the PI-RADS group and the non-PI-RADS group according to evaluation scheme of presurgery MRI. The preoperative characteristics and postoperative outcomes were retrieved and analyzed. The pathological outcomes included pathological T stage (pT2 vs. pT3-4) and positive surgical margins (PSMs). Patients were further stratified according to statistically significant preoperative variables to assess the difference in pathological outcomes. A propensity score matching based on the above preoperative characteristics was additionally performed.

RESULTS

A total of 380 patients were included in this study, with 201 patients in the PI-RADS group and 179 in the non-PI-RADS group. The two groups had similar preoperative characteristics, except for clinical T stage (cT). As for pathological outcomes, the PI-RADS group showed a significantly lower percentage of pT3-4 (21.4% vs. 48.0%, p < 0.001), a lower percentage of PSMs (31.3% vs. 40.9%, p = 0.055), and a higher concordance between the cT and pT (79.1% vs. 64.8%, p = 0.003). The PI-RADS group also showed a lower proportion of pT3-4 (p < 0.001) in the cT1-2 subgroup and the cohort after propensity score matching. The PSM rate of cT3 patients was reduced by 39.2% in the PI-RADS group but without statistical significance (p = 0.089).

CONCLUSIONS

Preoperative MRI with standardized PI-RADS assessment could benefit the decision-making of patients by reducing the rate of pathologically confirmed non-organ-confined PCa after RP and slightly reducing the PSM rate compared with non-PI-RADS assessment.

A Brief Review of Artificial Intelligence in Genitourinary Oncological Imaging

Genitourinary (GU) system is among the most commonly involved malignancy sites in the human body. Imaging plays a crucial role not only in diagnosis of cancer but also in disease management and its prognosis. However, interpretation of conventional imaging methods such as CT or MR imaging (MRI) usually demonstrates variability across different readers and institutions. Artificial intelligence (AI) has emerged as a promising technology that could improve the patient care by providing helpful input to human readers through lesion detection algorithms and lesion classification systems. Moreover, the robustness of these models may be valuable in automating time-consuming tasks such as organ and lesion segmentations. Herein, we review the current state of imaging and existing challenges in GU malignancies, particularly for cancers of prostate, kidney and bladder; and briefly summarize the recent AI-based solutions to these challenges.

Texture analysis of multiparametric magnetic resonance imaging for differentiating clinically significant prostate cancer in the peripheral zone

BACKGROUND

Texture analysis (TA) provides additional tissue heterogeneity data that may assist in differentiating peripheral zone(PZ) lesions in multiparametric magnetic resonance imaging (mpMRI). This study investigates the role of magnetic resonance imaging texture analysis (MRTA) in detecting clinically significant prostate cancer (csPCa) in the PZ.

METHODS

This retrospective study included 80 consecutive patients who had an mpMRI and a prostate biopsy for suspected prostate cancer. Two radiologists in consensus interpreted mpMRI and performed texture analysis based on their histopathology. The first-, second-, and higher-order texture parameters were extracted from mpMRI and were compared between groups. Univariate and multivariate logistic regression analyses were performed using the texture parameters to determine the independent predictors of csPCa. Receiver operating characteristic (ROC) curve analysis was conducted to assess the diagnostic performance of the texture parameters.

RESULTS

: In the periferal zone, 39 men had csPCa, while 41 had benign lesions or clinically insignificant prostate cancer (cisPCa). Themajority of texture parameters showed statistically significant differences between the groups. Univariate ROC analysis showed that the ADC mean and ADC median were the best variables in differentiating csPCa (p < 0.001). The first-order logistic regression model (mean + entropy) based on the ADC maps had a higher AUC value (0.996; 95% CI: 0.989-1) than other texture-based logistic regression models (p < 0.001).

DISCUSSION

MRTA is useful in differentiating csPCa from other lesions in the PZ. Consequently, the first-order multivariate regressionmodel based on ADC maps had the highest diagnostic performance in differentiating csPCa.

Detection Rate of Prostate Cancer in Repeat Biopsy after an Initial Negative Magnetic Resonance Imaging/Ultrasound-Guided Biopsy

A negative multiparametric magnetic resonance imaging (mpMRI)-guided prostate biopsy in patients with suspected prostate cancer (PC) results in clinical uncertainty, as the biopsy can be false negative. The clinical challenge is to determine the optimal follow-up and to select patients who will benefit from repeat biopsy. In this study, we evaluated the rate of significant PC (sPC, Gleason score ≥7) and PC detection in patients who received a follow-up mpMRI/ultrasound-guided biopsy for persistent PC suspicion after a negative mpMRI/ultrasound-guided biopsy. We identified 58 patients at our institution that underwent repeat targeted biopsy in case of PI-RADS lesions and systematic saturation biopsy between 2014 and 2022. At the initial biopsy, the median age was 59 years, and the median prostate specific antigen level was 6.7 ng/mL. Repeat biopsy after a median of 18 months detected sPC in 3/58 (5%) patients and Gleason score 6 PC in 11/58 (19%). Among 19 patients with a downgraded PI-RADS score at the follow-up mpMRI, none had sPC. In conclusion, men with an initial negative mpMRI/ultrasound-guided biopsy had a high likelihood of not harboring sPC at repeat biopsy (95%). Due to the small size of the study, further research is recommended.

[Common errors, pitfalls, and management of complications of prostate biopsy : The most common diagnostic and procedural challenges of transrectal fusion prostate biopsy in the initial diagnosis of clinically significant prostate cancer]

BACKGROUND

Transrectal (TR) prostate biopsy is the gold standard in diagnosis of prostate cancer (PC). It requires a precise and safe technique for sample acquisition.

OBJECTIVE

Several approaches will be discussed to avoid overdiagnosis, false-negative results, and complications of the procedure.

MATERIALS AND METHODS

We analyzed national and European guidelines, systematic reviews, meta-analyses, as well as prospective and retrospective studies to describe current trends in indication and performance of biopsies.

RESULTS

Incorporation of risk calculators and magnetic resonance imaging (MRI) into daily routine reduces biopsy rates and results in a more precise diagnosis of clinically significant prostate cancer (csPC). Combination of random- and MRI-fusion guided biopsy-but also extending the radius of sampling by 10 mm beyond the MRI lesion and a transperineal (TP) sampling approach - lead to a higher tumor-detection rate. Bleeding is the most common complication after prostate biopsy and is usually self-limiting. Postbiopsy infection rates can be reduced through TP biopsy.

CONCLUSION

TR MRI-fusion guided biopsy is a widely acknowledged tool in primary diagnostics of csPC. Higher detection rates and safety can be achieved through a TP sampling approach.

Making an art into a science: a mathematical "Likert tool" can change PI-RADS (v2) scores into Likert scores when reporting multiparametric MRI for prostate cancer

BACKGROUND

When reporting multiparametric magnetic resonance imaging (mpMRI) for prostate cancer, UK national guidelines recommend allocating both Likert and PI-RAD scores. Likert scores have been shown to better predict clinically significant cancer (csPCa) but are subjective and lack standardization.

PURPOSE

To compare differences in outcomes between the scoring systems and create a mathematical tool that can help to objectively allocate Likert scores.

MATERIAL AND METHODS

A total of 791 patients referred with query prostate cancer between 2017 and 2019 were prospectively allocated PI-RADS and Likert scores by a single experienced reporter. Histology results were used to compare the predictive accuracy of both scoring systems. A "Likert tool" was created based on a logistic regression of features found to be predictors of csPCa in a cohort of 2018-2019 patients (n = 411). Its performance was evaluated.

RESULTS

Assuming a policy whereby patients with a PI-RADS/Likert score of ≥3 are biopsied, Likert scoring (sensitivity 0.92, specificity 0.77) would have resulted in 107 fewer biopsies and 20.3% higher cancer yields than the PI-RADS score (sensitivity 0.99, specificity 0.43). Thirteen patients would have avoided over-diagnosis of clinically insignificant prostate cancer (iPCa). Similar outcomes (111 fewer biopsies, 22.3% increase in cancer yield, iPCa diagnosis avoided in 16 patients) could be seen when the "Likert tool" was applied to the same patient cohort (sensitivity 0.93, specificity 0.79) and to a separate cohort (n = 380).

CONCLUSION

PI-RADS and Likert scores are different. A "Likert tool" could reduce inter-reporter variability, decrease the number of patients unnecessarily biopsied, increase csPCa yield, and decrease over-diagnosis of iPCa.

Intraobserver and Interobserver Agreement between Six Radiologists Describing mpMRI Features of Prostate Cancer Using a PI-RADS 2.1 Structured Reporting Scheme

Clinical practice has revealed ambiguities in PI-RADS v2.1 scoring, but a limited number of studies are available that validate the interreader and intrareader reproducibility of the mpMRI PI-RADS lexicon. We decomposed the PI-RADS rules into a set of common data elements to evaluate the inter- and intraobserver agreement in assessing the individual features included in the PI-RADS lexicon. Six radiologists (three highly experienced, three less experienced) in two sessions independently read thirty-two lesions in the peripheral and transition zone using the structured reporting tool, blinded to clinical MRI indication. The highest agreement between radiologists was observed for the abnormality detection, the evaluation of the type of signal intensity, and the characteristic of benign prostatic hyperplasia. Moderate agreement was reported for dynamic contrast-enhanced images. This resulted in a decrease in abnormality detection (PA = 76.5%) and enhancement indication (PA = 77.3%). The lowest agreement was observed for highly subjective features: shape, signal intensity level, and type of lesion margins. The results indicate the limitations of the PI-RADS v2.1 lexicon in relation to interreader and intrareader reproducibility. We have demonstrated that it is possible to develop structured reporting systems standardized according to the PI-RADS lexicon.

Joint Cancer Segmentation and PI-RADS Classification on Multiparametric MRI Using MiniSegCaps Network

MRI is the primary imaging approach for diagnosing prostate cancer. Prostate Imaging Reporting and Data System (PI-RADS) on multiparametric MRI (mpMRI) provides fundamental MRI interpretation guidelines but suffers from inter-reader variability. Deep learning networks show great promise in automatic lesion segmentation and classification, which help to ease the burden on radiologists and reduce inter-reader variability. In this study, we proposed a novel multi-branch network, MiniSegCaps, for prostate cancer segmentation and PI-RADS classification on mpMRI. MiniSeg branch outputted the segmentation in conjunction with PI-RADS prediction, guided by the attention map from the CapsuleNet. CapsuleNet branch exploited the relative spatial information of prostate cancer to anatomical structures, such as the zonal location of the lesion, which also reduced the sample size requirement in training due to its equivariance properties. In addition, a gated recurrent unit (GRU) is adopted to exploit spatial knowledge across slices, improving through-plane consistency. Based on the clinical reports, we established a prostate mpMRI database from 462 patients paired with radiologically estimated annotations. MiniSegCaps was trained and evaluated with fivefold cross-validation. On 93 testing cases, our model achieved a 0.712 dice coefficient on lesion segmentation, 89.18% accuracy, and 92.52% sensitivity on PI-RADS classification (PI-RADS ≥ 4) in patient-level evaluation, significantly outperforming existing methods. In addition, a graphical user interface (GUI) integrated into the clinical workflow can automatically produce diagnosis reports based on the results from MiniSegCaps.

Landmarks in the evolution of prostate biopsy

Approaches and techniques used for diagnostic prostate biopsy have undergone considerable evolution over the past few decades: from the original finger-guided techniques to the latest MRI-directed strategies, from aspiration cytology to tissue core sampling, and from transrectal to transperineal approaches. In particular, increased adoption of transperineal biopsy approaches have led to reduced infectious complications and improved antibiotic stewardship. Furthermore, as image fusion has become integral, these novel techniques could be incorporated into prostate biopsy methods in the future, enabling 3D-ultrasonography fusion reconstruction, molecular targeting based on PET imaging and autonomous robotic-assisted biopsy.

Temporal changes of PIRADS scoring by radiologists and correlation to radical prostatectomy pathological outcomes

Purpose

To assess temporal improvement of prostate image reporting and data system (PIRADS) 3-5 lesion correlation to histopathologic findings from radical prostatectomy (RP) in prostate cancer (PCa).

Materials and methods

A total of 1481 patients who underwent RP for biopsy-proven PCa between 2015 and 2019 were divided into 14 groups of 100 sequential readings for the evaluation of histopathological correlation with PIRADS readings. Temporal trends of PIRADS distribution and predictive performance for RP pathology were evaluated to assess underlying changes in prostate magnetic resonance imaging (MRI) interpretation by radiologists.

Results

PIRADS 4-5 lesions were significantly correlated with the increasing rates of Gleason Group (GG) upgrade (p = 0.044) and decreasing rate of GG downgrade (p = 0.016) over time. PIRADS ≥3 lesions read after median 2 years of experience were shown to independently predict intermediate-high-risk (GG ≥ 3) PCa (odds ratio 2.93, 95% confidence interval 1.00-8.54; P= 0.049) in RP pathology. Preoperative GG ≥ 3 biopsy lesions with PIRADS 4-5 lesions were significantly more susceptible to GG upgrade (P= 0.035) and GG ≥ 4 RP pathology (p = 0.003) in experienced reads, in contrast to insignificant findings in early readings (p = 0.588 and 0.248, respectively).

Conclusion

Preoperative MRI reports matched with RP pathology suggest an improved prediction of adverse pathology in PIRADS 3-5 lesions over time, suggesting a temporal change in PIRADS interpretation and predictive accuracy. Institutions with low volume experience should use caution in solely relying on MRI for predicting tumor characteristics. Future prospective trials and larger scale assessments are required to further validate our results.

Artificial Intelligence for Clinical Diagnosis and Treatment of Prostate Cancer

As medical science and technology progress towards the era of "big data", a multi-dimensional dataset pertaining to medical diagnosis and treatment is becoming accessible for mathematical modelling. However, these datasets are frequently inconsistent, noisy, and often characterized by a significant degree of redundancy. Thus, extensive data processing is widely advised to clean the dataset before feeding it into the mathematical model. In this context, Artificial intelligence (AI) techniques, including machine learning (ML) and deep learning (DL) algorithms based on artificial neural networks (ANNs) and their types, are being used to produce a precise and cross-sectional illustration of clinical data. For prostate cancer patients, datasets derived from the prostate-specific antigen (PSA), MRI-guided biopsies, genetic biomarkers, and the Gleason grading are primarily used for diagnosis, risk stratification, and patient monitoring. However, recording diagnoses and further stratifying risks based on such diagnostic data frequently involves much subjectivity. Thus, implementing an AI algorithm on a PC's diagnostic data can reduce the subjectivity of the process and assist in decision making. In addition, AI is used to cut down the processing time and help with early detection, which provides a superior outcome in critical cases of prostate cancer. Furthermore, this also facilitates offering the service at a lower cost by reducing the amount of human labor. Herein, the prime objective of this review is to provide a deep analysis encompassing the existing AI algorithms that are being deployed in the field of prostate cancer (PC) for diagnosis and treatment. Based on the available literature, AI-powered technology has the potential for extensive growth and penetration in PC diagnosis and treatment to ease and expedite the existing medical process.

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

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.

Antibiotic prophylaxis versus no antibiotic prophylaxis in transperineal prostate biopsies (NORAPP): a randomised, open-label, non-inferiority trial

BACKGROUND

The benefit of antibiotic prophylaxis is uncertain when performing transperineal prostate biopsies. Judicious use of antibiotics is required as antimicrobial resistance increases worldwide. We aimed to assess whether antibiotic prophylaxis can be omitted when performing transperineal prostate biopsies under local anaesthesia as an outpatient procedure.

METHODS

In this randomised, open-label, non-inferiority trial, we aimed to enrol all patients with a suspicion of prostate cancer undergoing transperineal prostate biopsies at two hospitals in Norway and Germany. Patients with a high risk of infection or ongoing infection were excluded. Patients were randomised (1:1) to receive intramuscular (in Norway) or intravenous (in Germany) 1·5 g cefuroxime antibiotic prophylaxis or not. Follow-up assessments were done after 2 weeks and 2 months. The primary outcome was rate of sepsis or urinary tract infections requiring hospitalisation within 2 months. The secondary outcome was the rate of urinary tract infections not requiring hospitalisation. These outcomes were assessed in all eligible randomly allocated participants with a prespecified non-inferiority margin of 4%. Biopsies were performed using an MRI-transrectal ultrasound fusion transperineal technique under local anaesthesia. Patients with a positive MRI underwent 2-4 biopsies per target; in addition, 8-12 systematic biopsies were performed in biopsy naive and MRI-negative patients. This study is registered with ClinicalTrials.gov, NCT04146142.

FINDINGS

Between Nov 11, 2019, and Feb 23, 2021, 792 patients were referred for biopsy, of whom 555 (70%) were randomly allocated to treatment groups. 277 (50%) patients received antibiotic prophylaxis and 276 (50%) did not; two (&lt;1%) patients were excluded after randomisation because of unknown allergy to study drug. Sepsis or urinary tract infections requiring hospitalisation occurred in no patients given antibiotic prophylaxis (0%, 95% CI 0 to 1·37) or not given antibiotic prophylaxis (0%, 0 to 1·37; difference 0% [95% CI -1·37 to 1·37]). Urinary tract infections not requiring hospitalisation occurred in one patient given antibiotic prophylaxis (0·36%, 95% CI 0·01 to 2·00) and three patients not given antibiotic prophylaxis (1·09%, 0·37 to 3·15; difference 0·73% [95% CI -1·08 to 2·81]). The number needed to treat with antibiotic prophylaxis to avoid one infection was 137.

INTERPRETATION

The non-inferiority margin of 4% was not exceeded, suggesting rates of infections were not higher in patients not receiving antibiotic prophylaxis before transperineal prostate biopsy than in those receiving it. Therefore, antibiotic prophylaxis might be omitted in this population.

FUNDING

Oslo University Hospital, Oslo, Norway and Vivantes Klinikum Am Urban, Berlin, Germany.

Canadian Association of Radiologists Prostate MRI White Paper

Prostate cancer is the most common malignancy and the third most common cause of death in Canadian men. In light of evolving diagnostic pathways for prostate cancer and the increased use of MRI, which now includes its use in men prior to biopsy, the Canadian Association of Radiologists established a Prostate MRI Working Group to produce a white paper to provide recommendations on establishing and maintaining a Prostate MRI Programme in the context of the Canadian healthcare system. The recommendations, which are based on available scientific evidence and/or expert consensus, are intended to maintain quality in image acquisition, interpretation, reporting and targeted biopsy to ensure optimal patient care. The paper covers technique, reporting, quality assurance and targeted biopsy considerations and includes appendices detailing suggested reporting templates, quality assessment tools and sample image acquisition protocols relevant to the Canadian healthcare context.

Utility of a Rule-Based Algorithm in the Assessment of Standardized Reporting in PI-RADS

RATIONALE AND OBJECTIVES

Adoption of the Prostate Imaging Reporting & Data System (PI-RADS) has been shown to increase detection of clinically significant prostate cancer on prostate mpMRI. We propose that a rule-based algorithm based on Regular Expression (RegEx) matching can be used to automatically categorize prostate mpMRI reports into categories as a means by which to assess for opportunities for quality improvement.

MATERIALS AND METHODS

All prostate mpMRIs performed in the Duke University Health System from January 2, 2015, to January 29, 2021, were analyzed. Exclusion criteria were applied, for a total of 5343 male patients and 6264 prostate mpMRI reports. These reports were then analyzed by our RegEx algorithm to be categorized as PI-RADS 1 through PI-RADS 5, Recurrent Disease, or "No Information Available." A stratified, random sample of 502 mpMRI reports was reviewed by a blinded clinical team to assess performance of the RegEx algorithm.

RESULTS

Compared to manual review, the RegEx algorithm achieved overall accuracy of 92.6%, average precision of 88.8%, average recall of 85.6%, and F1 score of 0.871. The clinical team also reviewed 344 cases that were classified as "No Information Available," and found that in 150 instances, no numerical PI-RADS score for any lesion was included in the impression section of the mpMRI report.

CONCLUSION

Rule-based processing is an accurate method for the large-scale, automated extraction of PI-RADS scores from the text of radiology reports. These natural language processing approaches can be used for future initiatives in quality improvement in prostate mpMRI reporting with PI-RADS.

Quality of Multicenter Studies Using MRI Radiomics for Diagnosing Clinically Significant Prostate Cancer: A Systematic Review

Background: Reproducibility and generalization are major challenges for clinically significant prostate cancer modeling using MRI radiomics. Multicenter data seem indispensable to deal with these challenges, but the quality of such studies is currently unknown. The aim of this study was to systematically review the quality of multicenter studies on MRI radiomics for diagnosing clinically significant PCa. Methods: This systematic review followed the 2020 Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) checklist. Multicenter studies investigating the value of MRI radiomics for the diagnosis of clinically significant prostate cancer were included. Quality was assessed using the checklist for artificial intelligence in medical imaging (CLAIM) and the radiomics quality score (RQS). CLAIM consisted of 42 equally important items referencing different elements of good practice AI in medical imaging. RQS consisted of 36 points awarded over 16 items related to good practice radiomics. Final CLAIM and RQS scores were percentage-based, allowing for a total quality score consisting of the average of CLAIM and RQS. Results: Four studies were included. The average total CLAIM score was 74.6% and the average RQS was 52.8%. The corresponding average total quality score (CLAIM + RQS) was 63.7%. Conclusions: A very small number of multicenter radiomics PCa classification studies have been performed with the existing studies being of bad or average quality. Good multicenter studies might increase by encouraging preferably prospective data sharing and paying extra care to documentation in regards to reproducibility and clinical utility.

MRI as a screening tool for prostate cancer: current evidence and future challenges

Purpose

Prostate cancer (PCa) screening, which relies on prostate-specific antigen (PSA) testing, is a contentious topic that received negative attention due to the low sensitivity and specificity of PSA to detect clinically significant PCa. In this context, due to the higher sensitivity and specificity of magnetic resonance imaging (MRI), several trials investigate the feasibility of “MRI-only” screening approaches, and question if PSA testing may be replaced within prostate cancer screening programs.

Methods

This narrative review discusses the current literature and the outlook on the potential of MRI-based PCa screening.

Results

Several prospective randomized population-based trials are ongoing. Preliminary study results appear to favor the “MRI-only” approach. However, MRI-based PCa screening programs face a variety of obstacles that have yet to be fully addressed. These include the increased cost of MRI, lack of broad availability, differences in MRI acquisition and interpretation protocols, and lack of long-term impact on cancer-specific mortality. Partly, these issues are being addressed by shorter and simpler MRI approaches (5–20 min bi-parametric MRI), novel quality indicators (PI-QUAL) and the implementation of radiomics (deep learning, machine learning).

Conclusion

Although promising preliminary results were reported, MRI-based PCa screening still lack long-term data on crucial endpoints such as the impact of MRI screening on mortality. Furthermore, the issues of availability, cost-effectiveness, and differences in MRI acquisition and interpretation still need to be addressed.

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.

Using IVIM Parameters to Differentiate Prostate Cancer and Contralateral Normal Tissue through Fusion of MRI Images with Whole-Mount Pathology Specimen Images by Control Point Registration Method

The intravoxel incoherent motion (IVIM) model may enhance the clinical value of multiparametric magnetic resonance imaging (mpMRI) in the detection of prostate cancer (PCa). However, while past IVIM modeling studies have shown promise, they have also reported inconsistent results and limitations, underscoring the need to further enhance the accuracy of IVIM modeling for PCa detection. Therefore, this study utilized the control point registration toolbox function in MATLAB to fuse T2-weighted imaging (T2WI) and diffusion-weighted imaging (DWI) MRI images with whole-mount pathology specimen images in order to eliminate potential bias in IVIM calculations. Sixteen PCa patients underwent prostate MRI scans before undergoing radical prostatectomies. The image fusion method was then applied in calculating the patients’ IVIM parameters. Furthermore, MRI scans were also performed on 22 healthy young volunteers in order to evaluate the changes in IVIM parameters with aging. Among the full study cohort, the f parameter was significantly increased with age, while the D* parameter was significantly decreased. Among the PCa patients, the D and ADC parameters could differentiate PCa tissue from contralateral normal tissue, while the f and D* parameters could not. The presented image fusion method also provided improved precision when comparing regions of interest side by side. However, further studies with more standardized methods are needed to further clarify the benefits of the presented approach and the different IVIM parameters in PCa characterization.

Results from a PI-RADS-based MRI-directed diagnostic pathway for biopsy-naive patients in a non-university hospital

Purpose

To assess the safety and performance of a MRI-directed diagnostic pathway for patients with first-time suspicion of prostate cancer in a non-university hospital.

Methods

Between May 2017 and December 2018 all biopsy-naive patients examined in our hospital followed a MRI-directed diagnostic work-up algorithm based on PI-RADS score. In short, PI-RADS 1–2 was generally not biopsied and PI-RADS 3–5 was reviewed by a multidisciplinary team. Patients with PI-RADS 4-5 were all referred to biopsy, either transrectal ultrasound-guided biopsy or MRI in-bore biopsy for small tumors and for sites difficult to access. PI-RADS scores were compared to the histopathology from biopsies and surgical specimens for patients who had prostatectomy. Non-biopsied patients were referred to a safety net monitoring regimen.

Results

Two hundred and ninety-eight men were enrolled. 97 (33%) had PI-RADS 1–2, 44 (15%) had PI-RADS 3, and 157 (53%) had PI-RADS 4–5. 116 (39%) of the patients avoided biopsy. None of these were diagnosed with significant cancer within 2–3.5 years of safety net monitoring. Almost all high ISUP grade groups (≥ 3) were in the PI-RADS 4–5 category (98%). Prostatectomy specimens and systematic biopsies from MRI-negative areas indicated that very few clinically significant cancers were missed by the MRI-directed diagnostic pathway.

Conclusion

Our findings add to evidence that a MRI-directed diagnostic pathway can be safely established in a non-university hospital. The pathway reduced the number of biopsies and reliably detected the site of the most aggressive cancers.

Graphic abstract

Supplementary Information

The online version contains supplementary material available at 10.1007/s00261-021-03249-8.

Imaging temporomandibular disorders: Reliability of a novel MRI-based scoring system

The aim of this study was to assess the inter- and intrarater reliability of a recently proposed scoring system for temporomandibular disorders (TMD), based upon radiological findings from magnetic resonance imaging (MRI). Patients with clinically suspected uni- or bilateral TMD, and subsequently conducted MRI examination of both temporomandibular joints, were included in this study. MRI data were independently evaluated by two experienced radiologists according to the DLJ scoring system proposed by Wurm et al., which includes assessment of the following categories: articular disk (prefix 'D'), direction of disk luxation (prefix 'L'), and osseous joint alterations (prefix 'J'). 60 patients (49 female and 11 male) were eligible for analysis. No significant differences were found between both observers regarding 'D' and 'L' scores (p = 0.13 and p = 0.59, respectively). Significant differences were found for the assessment of subtle osseous changes ('J0' category: p = 0.041; 'J1' category: p = 0.018). Almost perfect intra- and interrater agreements were found for 'D' and 'L' categories (intrarater and interrater agreements for 'D': κ = 0.92 and κ = 0.84, respectively; intrarater and interrater agreements for 'L': κ = 0.93 and κ = 0.89, respectively). However, the assessment of 'J' categories revealed only moderate interrater agreement (κ = 0.49). The DLJ scoring system based upon MRI findings is feasible for routine clinical TMD assessment, and may help to simplify interdisciplinary communication between radiologists and clinicians.

1.5 vs 3 Tesla Magnetic Resonance Imaging: A Review of Favorite Clinical Applications for Both Field Strengths-Part 1

ABSTRACT

Whole-body magnetic resonance imaging (MRI) systems with a field strength of 3 T have been offered by all leading manufacturers for approximately 2 decades and are increasingly used in clinical diagnostics despite higher costs. Technologically, MRI systems operating at 3 T have reached a high standard in recent years, as well as the 1.5-T devices that have been in use for a longer time. For modern MRI systems with 3 T, more complexity is required, especially for the magnet and the radiofrequency (RF) system (with multichannel transmission). Many clinical applications benefit greatly from the higher field strength due to the higher signal yield (eg, imaging of the brain or extremities), but there are also applications where the disadvantages of 3 T might outweigh the advantages (eg, lung imaging or examinations in the presence of implants). This review describes some technical features of modern 1.5-T and 3-T whole-body MRI systems, and reports on the experience of using both types of devices in different clinical settings, with all sections written by specialist radiologists in the respective fields.This first part of the review includes an overview of the general physicotechnical aspects of both field strengths and elaborates the special conditions of diffusion imaging. Many relevant aspects in the application areas of musculoskeletal imaging, abdominal imaging, and prostate diagnostics are discussed.

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.

Emerging role of multiparametric magnetic resonance imaging in identifying clinically relevant localized prostate cancer

PURPOSE OF REVIEW

To explore the recent advances and utility of multiparametric magnetic resonance imaging (mpMRI) in the diagnosis and risk-stratification of prostate cancer.

RECENT FINDINGS

Low-risk, clinically insignificant prostate cancer has a decreased risk of morbidity or mortality. Meanwhile, patients with intermediate and high-risk prostate cancer may significantly benefit from interventions like radiation or surgery. To appropriately risk stratify these patients, MRI has emerged as the imaging modality in the last decade to assist in defining prostate cancer significance, location, and biologic aggressiveness. Traditional 12-core transrectal ultrasound-guided biopsy is associated with over-detection, and ultimately over-treatment of clinically insignificant disease, and the under-detection of clinically significant disease. Biopsy accuracy is improved with MRI-guided targeted biopsy and with the use of standardized risk stratification imaging score systems. Cancer detection accuracy is further improved with combined biopsy techniques that include both systematic and MRI-targeted biopsy that aid in detection of MRI-invisible lesions.

SUMMARY

mpMRI is an area of expanding innovation that continues to refine the diagnostic accuracy of prostate biopsies. As mpMRI-targeted biopsy in prostate cancer becomes more commonplace, advances like artificial intelligence and less invasive dynamic metabolic imaging will continue to improve the utility of MRI.

Value of bowel preparation techniques for prostate MRI: a preliminary study

Background

Bowel preparation before multiparametric MRI (mpMRI) of the prostate is performed widely, despite contradictory or no evidence for efficacy.

Purpose

To investigate the value of hyoscine N-butylbromide (HBB), microenema (ME) and ‘dietary restrictions’ (DR) for artifact reduction and image quality (IQ) in mpMRI of the prostate.

Study type

Retrospective.

Population

Between 10/2018 and 02/2020 treatment-naïve men (median age, 64.9; range 39.8–87.3) who underwent mpMRI of the prostate were included. The total patient sample comprised of n = 180 patients, who received either HBB, ME, were instructed to adhere to DR, or received a combination of those measures prior to the MR scan.

Field strength/sequence

T2-weighted imaging (T2w), diffusion-weighted imaging (DWI), and dynamic contrast-enhanced MRI (DCE-MRI) scanned on two 3T systems.

Assessment

A radiologist specialized in urogenital imaging (R1) and a senior radiology resident (R2) visually assessed IQ parameters on transversal T2w, DWI and ADC maps on a 5-point Likert-like scale.

Statistical tests

Group comparison between IQ parameters was performed on reader level using Kruskal–Wallis and Mann–Whitney U tests. Binary univariate logistic regression analysis was used to assess independent predictors of IQ. Interrater agreement was assessed using Intraclass Correlation Coefficient (ICC).

Results

‘DWI geometric distortion’ was significantly more pronounced in the HBB+/ME−/DR− (R1, 3.6 and R2, 4.0) as compared to the HBB−/ME+/DR− (R1, 4.2 and R2, 4.6) and HBB+/ME+/DR− (R1, 4.3 and R2, 4.7) cohort, respectively. Parameters ‘DWI IQ’ and ‘Whole MRI IQ’ were rated similarly by both readers. ME was a significant independent predictor of ‘good IQ’ for the whole MRI for R1 [b = 1.09, OR 2.98 (95% CI 1.29, 6.87)] and R2 [b = 1.01, OR 2.73 (95% CI 1.24, 6.04)], respectively.

Data conclusion

ME seems to significantly improve image quality of DWI and the whole mpMRI image set of the prostate. HBB and DR did not have any benefit.

Assessment of prostate imaging reporting and data system version 2.1 false-positive category 4 and 5 lesions in clinically significant prostate cancer

PURPOSE

To determine the incidence and false-positive rates of clinically significant prostate cancer (CSPC) in prostate imaging reporting and data system (PI-RADS) category 4 and 5 lesions using PI-RADS v2.1.

METHODS

One hundred and eighty-two lesions in 169 subjects with a PI-RADS score of 4 or 5 were included in our study. Lesions with clinically insignificant prostate cancer (CIPC) or benign pathologic findings were reviewed and categorized by a radiologist. The initial comparison of demographic and clinical data was performed by t-test and χ² test, and then the logistic regression model was used to determine factors associated with CIPC or benign pathological findings.

RESULTS

Of the 182 PI-RADS category 4 and 5 lesions, 84.6% (154/182) were prostate cancer (PCa), 73.1% (133/182) were CSPC, and 26.9% (49/182) were CIPC or benign pathologic findings. The false-positive cases included 44.9% (22/49) with inflammation, 42.9% (21/49) with CIPC, 8.2% (4/49) with BPH nodules and 4.1% (2/49) with normal anatomy cases. In multivariate analysis, factors associated with CIPC or benign features included those in both the peripheral zone (PZ) and central gland (CG) (odds ratio [OR] 0.062; p = 0.003) and a low prostate-specific antigen density (PSAD) (OR 0.34; p = 0.012).

CONCLUSION

The integration of clinical information (PSAD and lesion location) into mpMRI to identify lesions helps with obtaining a clinically significant diagnosis and decision-making.

Evaluation of Weighted Diffusion Subtraction for Detection of Clinically Significant Prostate Cancer

BACKGROUND

Diffusion-weighted imaging (DWI) is an important method for clinically significant prostate cancer (csPCa) diagnosis; however, the Prostate Imaging-Reporting and Data System (PI-RADS) requires the subjective assessment of "markedly hypointense or not" on apparent diffusion coefficient (ADC) map. We hypothesize that weighted diffusion subtraction (WDS) images, created by weighted subtraction of high and low b-value DWIs, might better show areas of ADC values below a set threshold, thus decreasing the subjectivity of the assessment.

PURPOSE

To evaluate the diagnostic ability of WDS for csPCa by comparing scores based on WDS images (DWI/WDS) with those based on PI-RADS DWI (DWI/ADC).

STUDY TYPE

Retrospective.

SUBJECTS

Eighty-six PCa patients.

FIELD STRENGTH/SEQUENCES

3.0 T; DWI.

ASSESSMENT

Four readers assessed the probability of csPCa in lesions (overall, in the peripheral zone [PZ] and transitional zone [TZ]) using 5-point DWI/ADC and DWI/WDS scores. Prostatectomy specimens were the reference standard. ADC values and contrast between csPCa and normal prostate tissue on ADC maps and WDS images were calculated with reference to the pathological map.

STATISTICAL TESTS

Diagnostic ability was evaluated by Jackknife alternative free-response receiver-operating characteristic curve. Figure of merit (FOM), sensitivity, and positive predictive value (PPV) between the DWI/ADC and DWI/WDS scores were compared using paired t-test. Inter-reader agreement was analyzed using κ statistics, and the significance probability was calculated using the Z statistic. Wilcoxon signed-rank test was used to compare contrast between csPCa and normal prostate tissue on ADC maps and WDS images. A P value <0.05 was considered statistically significant.

RESULTS

FOM and sensitivity of the DWI/WDS scores were significantly better than those of the DWI/ADC scores overall, in the PZ and TZ (FOM: overall, 0.715 vs. 0.783; PZ, 0.756 vs. 0.815; TZ, 0.653 vs. 0.738. Sensitivity: overall, 0.512 vs. 0.607; PZ, 0.485 vs. 0.573; TZ, 0.636 vs. 0.761). For PPV, a statistically significant difference was observed overall (0.727 vs. 0.777). The κ value of DWI/WDS score was significantly higher than that of DWI/ADC score overall and in the PZ (overall, 0.614 vs. 0.792; PZ, 0.609 vs. 0.797). Contrast was significantly higher overall in the PZ and TZ in WDS images (median, 1.26, 1.19, and 1.61) than in ADC maps (0.46, 0.47, and 0.41).

DATA CONCLUSION

WDS images performed better than ADC maps in the diagnosis of csPCa and in inter-reader agreement of the diagnosis.

LEVEL OF EVIDENCE

4 Technical Efficacy Stage: 2.

The Value of Prostate-specific Antigen Density for Prostate Imaging-Reporting and Data System 3 Lesions on Multiparametric Magnetic Resonance Imaging: A Strategy to Avoid Unnecessary Prostate Biopsies

BACKGROUND

Multiparametric magnetic resonance imaging (mpMRI) has excellent sensitivity in detecting significant prostate cancer (sPC). Nevertheless, uncertainty exists regarding the management of Prostate Imaging-Reporting and Data System (PI-RADS) 3 lesions.

OBJECTIVE

To investigate whether PI-RADS 3 lesions in combination with clinical parameters, especially prostate-specific antigen density (PSAD), can be used to exclude sPC.

DESIGN, SETTING, AND PARTICIPANTS

A total of 455 consecutive biopsy-naïve men underwent MRI-guided transperineal prostate fusion biopsy at our department between 2017 and 2018. We identified 101 patients who had exclusively one or more PI-RADS 3 lesions on mpMRI. sPC was defined as intermediate- and high-risk PC (according to the D'Amico risk classification).

OUTCOME MEASURES AND STATISTICAL ANALYSIS

Univariate logistic regression analysis was performed to test different clinical factors as predictors of sPC in men with PI-RADS 3 lesions. The probability of sPC prediction was calculated for different PSAD thresholds.

RESULTS AND LIMITATIONS

Among patients with PI-RADS 3 lesions, PSAD was a significant predictor of sPC (p = 0.005). For a PI-RADS score of 3 the probability of excluding sPC was 85% (86/101), which increased to 98% (42/43) when combined with PSAD <0.1 ng/ml/ml.

CONCLUSIONS

Inclusion of PSAD < 0.1 ng/ml/ml in the strategy for biopsy-naïve patients with equivocal mpMRI findings would allow a reduction in prostate biopsies in 43% (43/101) of cases at the cost of missing a very small number (2%, 1/43) of intermediate-risk PCs.

PATIENT SUMMARY

At high-volume tertiary care centers with significant experience in prostate multiparametric magnetic resonance imaging, immediate biopsies could be safely omitted for men with lesions with a Prostate Imaging-Reporting and Data System score of 3 and prostate-specific antigen density of PSAD < 0.1 ng/ml/ml. Any decision to omit an immediate biopsy should be associated with close monitoring.

Predictive clinical features for negative histopathology of MRI/Ultrasound-fusion-guided prostate biopsy in patients with high likelihood of cancer at prostate MRI: Analysis from a urologic outpatient clinic1

OBJECTIVE

The aim of this study was to evaluate clinical features associated with benign histopathology of Prostate Imaging Reporting and Data System (PI-RADS) category 4 and 5 lesions.

MATERIALS AND METHODS

Between March 2015 and November 2020, 1161 patients underwent mpMRI/Ultrasound-fusion-guided prostate biopsy (FBx) and concurrent 12-core systematic prostate biopsy (SBx) at the Department of Urology of the Ludwig-Maximilians-University of Munich, Germany. 848/ 1161 (73%) patients presented with either PI-RADS 4 or 5 index lesion and were retrospectively evaluated. Multivariate analysis was performed to evaluate clinical parameters associated with a negative outcome of PI-RADS 4 or 5 category lesions after FBx. Area under the receiver operating characteristics (ROC) curve (AUC) was conducted using ROC-analysis.

RESULTS

676/848 (79.7%) patients with either PI-RADS 4 or 5 index lesion were diagnosed with prostate cancer (PCa) by FBx and 172/848 (20.3%) patients had a negative biopsy (including the concurrent systematic prostate biopsy), respectively. Prostate volume (P-Vol) (OR 0.99, 95% CI = 0.98-1.00, p = 0.038), pre-biopsy-status (OR 0.48, 95% CI = 0.29-0.79, p = 0.004) and localization of the lesion in the transitional zone (OR 0.28, 95% CI = 0.13-0.60, p = 0.001) were independent risk factors for a negative outcome of FBx. Age (OR 1.09, 95% CI = 1.05-1.13, p < 0.001) and PSA density (PSAD) (OR 75.92, 95% CI = 1.03-5584.61, p = 0.048) increased the risk for PCa diagnosis after FBx. The multivariate logistic regression model combining all clinical characteristics achieved an AUC of 0.802 (95% CI = 0.765-0.835; p < 0.001) with a sensitivity and specificity of 66% and 85%.

CONCLUSION

Lesions with high or highly likelihood of PCa on multiparametric magnetic resonance imaging (mpMRI) but subsequent negative prostate biopsy occur in a small amount of patients. Localization of the lesion in the transitional zone, prostate volume and prebiopsy were shown to be predictors for benign histopathology of category 4 or 5 lesions on mpMRI. Integration of these features into daily clinical routine could be used for risk-stratification of these patients after negative biopsy of PI-RADS 4 or 5 index lesions.

Practice Patterns and Challenges of Performing and Interpreting Prostate MRI: A Survey by the Society of Abdominal Radiology Prostate Disease-Focused Panel

OBJECTIVE. The purpose of this study was to report on the practice patterns and challenges of performing and interpreting prostate MRI. SUBJECTS AND METHODS. An electronic survey regarding prostate MRI practice patterns and challenges was sent to members of the Society of Abdominal Radiology. RESULTS. The response rate was 15% (212/1446). Most (65%) of the respondents were academic abdominal radiologists with 1-5 (52%), 6-10 (20%), 11-20 (15%), and more than 20 (5%) years of experience in reporting prostate MRI. The numbers of prostate MRI examinations reported per week were 0-5 (43%), 6-10 (38%), 11-20 (12%), 21-30 (5%), and more than 30 (2%). Imaging was performed at 3 T (58%), 1.5 T (20%), or either (21%), and most examinations (83%) were performed without an endorectal coil. Highest b values ranged from 800 to 5000 s/mm²; 1400 s/mm² (26%) and 1500 s/mm² (30%) were the most common. Most respondents (79%) acquired dynamic contrast-enhanced images with temporal resolution of less than 10 seconds. Most (71%) of the prostate MRI studies were used for fusion biopsy. PI-RADS version 2 was used by 92% of the respondents and template reporting by 80%. Challenges to performing and interpreting prostate MRI were scored on a 1-5 Likert scale (1, easy; 2, somewhat easy; 3, neutral; 4, somewhat difficult; 5, very difficult). The median scores were 2 or 3 for patient preparatory factors. Image acquisition and reporting factors were scored 1-2, except for performing spectroscopy or using an endorectal coil, both of which scored 4. Acquiring patient history scored 2 and quality factors scored 3. CONCLUSION. Most radiologists perform prostate MRI at 3 T without an endorectal coil and interpret the images using PI-RADS version 2. Challenges include obtaining quality images, acquiring feedback, and variability in the interpretation of PI-RADS scores.

Multiparametric MRI Lesion Classified as Prostate Imaging-Reporting and Data System 5 but Histopathologically Described as Benign: A Case Report and Review of Literature

INTRODUCTION

Prostate cancer (PCa) is the most common malignancy in men. The multiparametric MRI (mpMRI) significantly improved the diagnostic approach of PCa. Although PCa is highly likely to be present in prostate imaging-reporting and data system (PI-RADS) 5 lesions, there are up to 18% of PI-RADS 5 lesions with benign histopathology after targeted biopsy.

CASE DESCRIPTION

We present the case of a 66-year-old man who was referred to our hospital for MRI/ultrasound fusion-based targeted biopsy due to an elevated PSA and a PI-RADS 5 lesion described in the mpMRI. After 2 consecutive biopsies, the mpMRI target showed no malignancy. The lesion was described as PI-RADS 2 two years later.

CONCLUSION

This case demonstrates the risk of false-positive classified PI-RADS 5 lesions in the mpMRI and the challenge in some cases to distinguish between BPH nodules and cancer. Until today, a limited amount of studies exists concerning this issue. However, further studies are required to evaluate further characteristics associated with a higher possibility of histopathologically benign findings in PI-RADS 5 lesions.

Diagnostic Accuracy and Prognostic Value of Serial Prostate Multiparametric Magnetic Resonance Imaging in Men on Active Surveillance for Prostate Cancer

BACKGROUND

Multiparametric magnetic resonance imaging (MRI) is increasingly utilized to improve the detection of clinically significant prostate cancer. Evidence for serial MRI in men on active surveillance (AS) is lacking.

OBJECTIVE

To evaluate the role of MRI in detecting Gleason grade group (GG) ≥2 disease in confirmatory and subsequent surveillance biopsies for men on AS.

DESIGN, SETTING, AND PARTICIPANTS

This was a single-center study of men with low-risk prostate cancer enrolled in an AS cohort between 2006 and 2018. All men were diagnosed by systematic biopsy and underwent MRI prior to confirmatory ("MRI1") and subsequent surveillance ("MRI2") biopsies. MRI lesions were scored with Prostate Imaging Reporting and Data System (PI-RADS) version 2.

OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS

The primary outcome was biopsy upgrade to GG ≥ 2 prostate cancer, and the secondary outcome was definitive treatment. Test characteristics for PI-RADS score were calculated. Multivariable logistic and Cox proportional hazard regression models were used to determine the associations between PI-RADS score change and outcomes, on a per-examination basis.

RESULTS AND LIMITATIONS

Of 125 men with a median follow-up of 78 mo, 38% experienced an increase in PI-RADS scores. The sensitivity and positive predictive value of PI-RADS ≥3 for GG ≥ 2 disease improved from MRI1 to MRI2 (from 85% to 91% and from 26% to 49%, respectively). An increase in PI-RADS scores from MRI1 to MRI2 was associated with GG ≥ 2 (odds ratio [OR] 4.8, 95% confidence interval [CI] 1.7-13.2) compared with PI-RADS 1-3 on both MRI scans. Men with PI-RADS 4-5 lesions on both MRI scans had a higher likelihood of GG ≥ 2 than patients with PI-RADS 1-3 lesions on both (OR 3.3, 95% CI 1.3-8.6). Importantly, any increase in PI-RADS scores was independently associated with definitive treatment (hazard ratio 3.9, 95% CI 1.3-11.9). This study was limited by its retrospective, single-center design.

CONCLUSIONS

The prognostic value of MRI improves with serial examination and provides additional risk stratification. Validation in other cohorts is needed.

PATIENT SUMMARY

We looked at the role of serial prostate magnetic resonance imaging in men with low-risk prostate cancer on active surveillance at the University of California, San Francisco. We found that both consistently visible and increasingly suspicious lesions were associated with biopsy upgrade and definitive treatment.

Diagnostic pathway of the biopsy-naïve patient suspected for prostate cancer: Real-life scenario when multiparametric Magnetic Resonance Imaging is not centralized

INTRODUCTION

We aimed to compare the pathway including multi-parametric Magnetic Resonance Imaging (mpMRI) versus the one without mpMRI in detection of prostate cancer (PCa) when mpMRI is not centralized.

MATERIALS

January 2019-March 2020: prospective data collection of trans-perineal prostate biopsies. Group A: biopsy-naïve patients who underwent mpMRI (at any institution) versus Group B: patients who did not. Within Group A, patients were stratified into those with negative mpMRI (mpMRI-, PIRADS v2.1=1-3, with PSA density <0.15 if PIRADS 3) who underwent standard biopsy (SB), versus those with positive mpMRI (mpMRI+, when PIRADS 3-5, with PSA density>0.15 if PIRADS 3) who underwent cognitive fusion biopsy.

RESULTS

Two hundred and eighty one biopsies were analyzed. 153 patients underwent mpMRI (Group A). 98 mpMRI+ underwent fusion biopsy; 55 mpMRI- underwent SB. 128 Group B patients underwent SB. Overall PCa detection rate was 52.3% vs. 48.4% (Group A vs. B, P=0.5). Non-clinically-significant PCa was detected in 7.8 vs. 13.3% (Group A vs. B, P=0.1). Among the 98 mpMRI+ Group A patients only 2 had non clinically-significant disease. In 55 mpMRI- patients who underwent SB, 10 (18.2%) had clinically-significant PCa. Prostate volume predicted detection of PCa. In Group B, age and PSA predicted PCa. Sensitivity of mpMRI was 75.0% for all PCa, 85.3% for clinically-significant PCa.

CONCLUSION

Higher detection of PCa and lower detection of non-clinically-significant PCa favored mpMRI pathway. A consistent number of clinically-significant PCa was diagnosed after a mpMRI-. Thus, in real-life scenario, mpMRI- does not obviate indication to biopsy when mpMRI is not centralized.

LEVEL OF EVIDENCE

3.

Semi-automated PIRADS scoring via mpMRI analysis

Purpose: Prostate cancer (PCa) is the most common solid organ cancer and second leading cause of death in men. Multiparametric magnetic resonance imaging (mpMRI) enables detection of the most aggressive, clinically significant PCa (csPCa) tumors that require further treatment. A suspicious region of interest (ROI) detected on mpMRI is now assigned a Prostate Imaging-Reporting and Data System (PIRADS) score to standardize interpretation of mpMRI for PCa detection. However, there is significant inter-reader variability among radiologists in PIRADS score assignment and a minimal input semi-automated artificial intelligence (AI) system is proposed to harmonize PIRADS scores with mpMRI data. Approach: The proposed deep learning model (the seed point model) uses a simulated single-click seed point as input to annotate the lesion on mpMRI. This approach is in contrast to typical medical AI-based approaches that require annotation of the complete lesion. The mpMRI data from 617 patients used in this study were prospectively collected at a major tertiary U.S. medical center. The model was trained and validated to classify whether an mpMRI image had a lesion with a PIRADS score greater than or equal to PIRADS 4. Results: The model yielded an average receiver-operator characteristic (ROC) area under the curve (ROC-AUC) of 0.704 over a 10-fold cross-validation, which is significantly higher than the previously published benchmark. Conclusions: The proposed model could aid in PIRADS scoring of mpMRI, providing second reads to promote quality as well as offering expertise in environments that lack a radiologist with training in prostate mpMRI interpretation. The model could help identify tumors with a higher PIRADS for better clinical management and treatment of PCa patients at an early stage.