Clinical utility of MR/ultrasound fusion-guided biopsy in patients with lower suspicion lesions on active surveillance for low-risk prostate cancer.

BACKGROUND: The utility of Multiparametric magnetic resonance imaging (mpMRI) guided prostate biopsy among patients with prostate cancer (CaP) managed with active surveillance (AS) with low-suspicion lesions remains unsettled. METHODS: We performed a retrospective analysis of 415 men with low-risk CaP managed with active surveillance. We selected men with mpMRI visible index lesions scored as 2 or 3 according to Prostate Imaging Reporting and Data System (PI-RADS) version 2. The primary outcome was detection of clinically significant prostate cancer (csCaP) was defined as Gleason grade group ≥ 2. We assessed the diagnostic accuracy of biopsy approaches using area under the receiver operator characteristic (ROC) curve and evaluated factors associated with csCaP in these patients using multivariate logistic regression. RESULTS: CsCaP was identified in 22 of 125 patients (17.6%) with PI-RADS 2 or 3 index lesions during surveillance prostate biopsies. These included 10 (45.5%) diagnosed by systematic biopsy alone, 9 (40.9%) by targeted alone, and 3 (13.6%) by both approaches. On multivariable analysis, the only significant variable predicting the detection of csCaP in men with low-risk imaging mpMRI characteristics was higher PSAD (OR per 0.1 unit=2.26, 95% CI 1.25-4.06, P = 0.007. A PSAD cutoff of 0.1, 0.12 and 0.15 resulted in a negative predictive value (NPV) of 90.9%, 87.1% and 86.2%, respectively. When stratified by PI-RADS score, a PSAD cutoff of 0.1, 0.12 and 0.15 resulted in NPV of 96.2%, 90.6% and 89.7% and 86.2%, 84.2% and 83.3% for detection of csCaP in PI-RADS 2 and 3 lesions, respectively. In patients with PIRDAS 2 lesions, using a PSAD of 0.1 would potentially allow 51% of patients to avoid biopsy with only a 3.8% chance of missing csCaP. CONCLUSION: In men with clinical low-risk prostate cancer on active surveillance with PI-RADS 2 and 3 lesions, there is an almost 18% risk of upgrade to csCaP. Integration of PSAD may be a useful adjunctive tool in identifying patients at highest risk for upgrade despite favorable imaging findings. In men with PIRADS 2 lesions with PSAD ≤0.12 biopsy can be avoided. For men with PIRADS 2 lesions with PSAD ≤0.15 informed decision making regarding the AS intensity should include that these patients have a low risk (>10%) of developing csCaP. In men with PIRADS 3 lesions with PSAD >0.1, shared decision making should include discussion of a >10% miss rate of csCaP.

Doubling of Decipher Biopsy Genomic Score Is Related to Disease Reclassification on Subsequent Surveillance Biopsy but Not Adverse Features on Radical Prostatectomy.

The utility of serial Decipher biopsy scores in a true active surveillance population is still unknown. In a man on active surveillance for low-risk prostate cancer, a doubling of the Decipher biopsy score within genomic low-risk category from first to the second biopsy related to biopsy reclassification to Gleason grade group 4 on the third biopsy. However, the final pathology at radical prostatectomy showed Gleason grade group 2 with an organ-confined disease. This case suggests that the genomic risk category of Decipher biopsy scores during active surveillance may be more informative than either the interval genomic score change or the biopsy Gleason grade group.

The Prognostic Association of Prostate MRI PI-RADS™ v2 Assessment Category and Risk of Biochemical Recurrence after Definitive Local Therapy for Prostate Cancer: A Systematic Review and Meta-Analysis.

PURPOSE: Although the Prostate Imaging-Reporting and Data System™ version 2 (PI-RADS™ v2) is a reliable diagnostic tool for significant prostate cancer, less is known about the prognostic significance of the structured reporting scheme for estimating oncologic outcomes after treatment. We aimed to synthesize the available evidence regarding the association of PI-RADS v2 score and risk of biochemical recurrence (BCR) among patients undergoing primary definitive treatment for prostate cancer. MATERIALS AND METHODS: We systematically queried the PubMed® and Web of Science™ databases to identify studies addressing the association between the PI-RADS v2 and treatment outcomes. We included studies through November 2020 that assessed the independent prognostic significance of PI-RADS v2. After assessing risk of bias and quality, we conducted a formal meta-analysis to estimate the pooled effects of prostate magnetic resonance imaging (MRI) classification on the risk of BCR. RESULTS: We identified 9 and 7 eligible studies including 2,274 and 1,215 patients for the systematic review and meta-analysis, respectively. Eight were conducted in the context of radical prostatectomy and 1 post-radiation. Among patients treated with radical prostatectomy, higher PI-RADS v2 scores were significantly associated with risk of BCR (pooled HR 3.06, 95% CI 2.16-4.33; p <0.01). There was no significant heterogeneity among studies. For all studies, PI-RADS v2 score remained significantly associated with BCR (pooled HR 3.19, 95% CI 2.28-4.45; p <0.01). CONCLUSIONS: Prostate MRI findings assessed with the PI-RADS v2 classification were independently associated with risk of BCR after definitive local therapy, primarily based on data from radical prostatectomy. These findings support the prognostic significance of MRI, in addition to its role in prostate cancer diagnosis.

Prostate Magnetic Resonance Imaging for Local Recurrence Reporting (PI-RR): International Consensus -based Guidelines on Multiparametric Magnetic Resonance Imaging for Prostate Cancer Recurrence after Radiation Therapy and Radical Prostatectomy.

BACKGROUND: Imaging techniques are used to identify local recurrence of prostate cancer (PCa) for salvage therapy and to exclude metastases that should be addressed with systemic therapy. For magnetic resonance imaging (MRI), a reduction in the variability of acquisition, interpretation, and reporting is required to detect local PCa recurrence in men with biochemical relapse after local treatment with curative intent. OBJECTIVE: To propose a standardised method for image acquisition and assessment of PCa local recurrence using MRI after radiation therapy (RP) and radical prostatectomy (RT). EVIDENCE ACQUISITION: Prostate Imaging for Recurrence Reporting (PI-RR) was formulated using the existing literature. An international panel of experts conducted a nonsystematic review of the literature. The PI-RR system was created via consensus through a combination of face-to-face and online discussions. EVIDENCE SYNTHESIS: Similar to with PI-RADS, based on the best available evidence and expert opinion, the minimum acceptable MRI parameters for detection of recurrence after radiation therapy and radical prostatectomy are set. Also, a simplified and standardised terminology and content of the reports that use five assessment categories to summarise the suspicion of local recurrence (PI-RR) are designed. PI-RR scores of 1 and 2 are assigned to lesions with a very low and low likelihood of recurrence, respectively. PI-RR 3 is assigned if the presence of recurrence is uncertain. PI-RR 4 and 5 are assigned for a high and very high likelihood of recurrence, respectively. PI-RR is intended to be used in routine clinical practice and to facilitate data collection and outcome monitoring for research. CONCLUSIONS: This paper provides a structured reporting system (PI-RR) for MRI evaluation of local recurrence of PCa after RT and RP. PATIENT SUMMARY: A new method called PI-RR was developed to promote standardisation and reduce variations in the acquisition, interpretation, and reporting of magnetic resonance imaging for evaluating local recurrence of prostate cancer and guiding therapy.

Use of Intravenous Gadolinium-Based Contrast Media in Patients With Kidney Disease: Consensus Statements from the American College of Radiology and the National Kidney Foundation.

Inaugural consensus statements were developed and endorsed by the American College of Radiology (ACR) and National Kidney Foundation to improve and standardize the care of patients with kidney disease who have indication(s) to receive ACR-designated group II or group III intravenous gadolinium-based contrast media (GBCM). The risk of nephrogenic systemic fibrosis (NSF) from group II GBCM in patients with advanced kidney disease is thought to be very low (zero events following 4931 administrations to patients with estimated glomerular filtration rate [eGFR] <30 mL/min per 1.73 m2; upper bounds of the 95% confidence intervals: 0.07% overall, 0.2% for stage 5D chronic kidney disease [CKD], 0.5% for stage 5 CKD and no dialysis). No unconfounded cases of NSF have been reported for the only available group III GBCM (gadoxetate disodium). Depending on the clinical indication, the potential harms of delaying or withholding group II or group III GBCM for an MRI in a patient with acute kidney injury or eGFR less than 30 mL/min per 1.73 m2 should be balanced against and may outweigh the risk of NSF. Dialysis initiation or alteration is likely unnecessary based on group II or group III GBCM administration.

Deep learning-assisted differentiation of pathologically proven atypical and typical hepatocellular carcinoma (HCC) versus non-HCC on contrast-enhanced MRI of the liver.

OBJECTIVES: To train a deep learning model to differentiate between pathologically proven hepatocellular carcinoma (HCC) and non-HCC lesions including lesions with atypical imaging features on MRI. METHODS: This IRB-approved retrospective study included 118 patients with 150 lesions (93 (62%) HCC and 57 (38%) non-HCC) pathologically confirmed through biopsies (n = 72), resections (n = 29), liver transplants (n = 46), and autopsies (n = 3). Forty-seven percent of HCC lesions showed atypical imaging features (not meeting Liver Imaging Reporting and Data System [LI-RADS] criteria for definitive HCC/LR5). A 3D convolutional neural network (CNN) was trained on 140 lesions and tested for its ability to classify the 10 remaining lesions (5 HCC/5 non-HCC). Performance of the model was averaged over 150 runs with random sub-sampling to provide class-balanced test sets. A lesion grading system was developed to demonstrate the similarity between atypical HCC and non-HCC lesions prone to misclassification by the CNN. RESULTS: The CNN demonstrated an overall accuracy of 87.3%. Sensitivities/specificities for HCC and non-HCC lesions were 92.7%/82.0% and 82.0%/92.7%, respectively. The area under the receiver operating curve was 0.912. CNN's performance was correlated with the lesion grading system, becoming less accurate the more atypical imaging features the lesions showed. CONCLUSION: This study provides proof-of-concept for CNN-based classification of both typical- and atypical-appearing HCC lesions on multi-phasic MRI, utilizing pathologically confirmed lesions as "ground truth." KEY POINTS: • A CNN trained on atypical appearing pathologically proven HCC lesions not meeting LI-RADS criteria for definitive HCC (LR5) can correctly differentiate HCC lesions from other liver malignancies, potentially expanding the role of image-based diagnosis in primary liver cancer with atypical features. • The trained CNN demonstrated an overall accuracy of 87.3% and a computational time of < 3 ms which paves the way for clinical application as a decision support instrument.

PI-RADS Committee Position on MRI Without Contrast Medium in Biopsy-Naive Men With Suspected Prostate Cancer: Narrative Review.

The steadily increasing demand for diagnostic prostate MRI has led to concerns regarding the lack of access to and the availability of qualified MRI scanners and sufficiently experienced radiologists, radiographers, and technologists to meet the demand. Solutions must enhance operational benefits without compromising diagnostic performance, quality, and delivery of service. Solutions should also mitigate risks such as decreased reader confidence and referrer engagement. One approach may be the implementation of MRI without the use gadolinium-based contrast medium (bipara-metric MRI), but only if certain prerequisites such as high-quality imaging, expert interpretation quality, and availability of patient recall or on-table monitoring are mandated. Alternatively, or in combination, a clinical risk-based approach could be used for protocol selection, specifically, which biopsy-naive men need MRI with contrast medium (multiparametric MRI). There is a need for prospective studies in which biopsy decisions are made according to MRI without contrast enhancement. Such studies must define clinical and operational benefits and identify which patient groups can be scanned successfully without contrast enhancement. These higher-quality data are needed before the Prostate Imaging Reporting and Data System (PI-RADS) Committee can make evidence-based recommendations about MRI without contrast enhancement as an initial diagnostic approach for prostate cancer workup.

Use of Intravenous Iodinated Contrast Media in Patients With Kidney Disease: Consensus Statements from the American College of Radiology and the National Kidney Foundation.

Intravenous iodinated contrast media are commonly used with CT to evaluate disease and to determine treatment response. The risk of acute kidney injury (AKI) developing in patients with reduced kidney function following exposure to intravenous iodinated contrast media has been overstated. This is due primarily to historic lack of control groups sufficient to separate contrast-induced AKI (CI-AKI; ie, AKI caused by contrast media administration) from contrast-associated AKI (CA-AKI; ie, AKI coincident to contrast media administration). Although the true risk of CI-AKI remains uncertain for patients with severe kidney disease, prophylaxis with intravenous normal saline is indicated for patients who have AKI or an estimated glomerular filtration rate less than 30 mL/min/1.73 m2 who are not undergoing maintenance dialysis. In individual high-risk circumstances, prophylaxis may be considered in patients with an estimated glomerular filtration rate of 30-44 mL/min/1.73 m2 at the discretion of the ordering clinician.

Assessing the Impact of Referral on Multidisciplinary Tumor Board Outcomes in Patients With Hepatocellular Carcinoma.

BACKGROUND AND AIMS: Hepatocellular carcinoma (HCC) is a complex and unique cancer. At many tertiary care institutions, optimal treatment is planned at a multidisciplinary liver tumor board (MDLTB). This study examined the impact of referral on MDLTB outcomes for patients with HCC. METHODS: Chart review was performed of incident HCC cases presented over 3 years at an American College of Surgeons accredited MDLTB. Internal cases were defined as patients whose care originated within the tertiary care institution of the MDLTB; external cases were defined as patients who received initial care from outside institutions and referred to the tertiary care MDLTB for consultation. Internal and external cases were compared for differences in HCC diagnosis, treatment, and survival. RESULTS: There were 120 internal cases and 163 external cases. Compared with internal cases, external cases took significantly more time to be diagnosed with HCC (4.5 versus 37.5 days, P < .001) and to be discussed at MDLTB (19 versus 53 days, P < .001). Internal cases were more often diagnosed by imaging studies (77.5%), and external cases were more often diagnosed by biopsy (43%) or by consensus of experts at MDLTB (26%). CONCLUSION: Patients with HCC, whose care originated within the tertiary care institution of the MDLTB, were less likely to require biopsy and had shorter time from initial suspicion to diagnosis of HCC. The data suggest that referral of external HCC cases to a tertiary center MDLTB at initial suspicion may limit unnecessary diagnostic procedures, possibly resulting in decreased health care costs and reduced uncertainty for patients.

PI-RADS Steering Committee: The PI-RADS Multiparametric MRI and MRI-directed Biopsy Pathway.

High-quality evidence shows that MRI in biopsy-naive men can reduce the number of men who need prostate biopsy and can reduce the number of diagnoses of clinically insignificant cancers that are unlikely to cause harm. In men with prior negative biopsy results who remain under persistent suspicion, MRI improves the detection and localization of life-threatening prostate cancer with greater clinical utility than the current standard of care, systematic transrectal US-guided biopsy. Systematic analyses show that MRI-directed biopsy increases the effectiveness of the prostate cancer diagnosis pathway. The incorporation of MRI-directed pathways into clinical care guidelines in prostate cancer detection has begun. The widespread adoption of the Prostate Imaging Reporting and Data System (PI-RADS) for multiparametric MRI data acquisition, interpretation, and reporting has promoted these changes in practice. The PI-RADS MRI-directed biopsy pathway enables the delivery of key diagnostic benefits to men suspected of having cancer based on clinical suspicion. Herein, the PI-RADS Steering Committee discusses how the MRI pathway should be incorporated into routine clinical practice and the challenges in delivering the positive health impacts needed by men suspected of having clinically significant prostate cancer.

Deep learning for liver tumor diagnosis part II: convolutional neural network interpretation using radiologic imaging features.

OBJECTIVES: To develop a proof-of-concept "interpretable" deep learning prototype that justifies aspects of its predictions from a pre-trained hepatic lesion classifier. METHODS: A convolutional neural network (CNN) was engineered and trained to classify six hepatic tumor entities using 494 lesions on multi-phasic MRI, described in Part 1. A subset of each lesion class was labeled with up to four key imaging features per lesion. A post hoc algorithm inferred the presence of these features in a test set of 60 lesions by analyzing activation patterns of the pre-trained CNN model. Feature maps were generated that highlight regions in the original image that correspond to particular features. Additionally, relevance scores were assigned to each identified feature, denoting the relative contribution of a feature to the predicted lesion classification. RESULTS: The interpretable deep learning system achieved 76.5% positive predictive value and 82.9% sensitivity in identifying the correct radiological features present in each test lesion. The model misclassified 12% of lesions. Incorrect features were found more often in misclassified lesions than correctly identified lesions (60.4% vs. 85.6%). Feature maps were consistent with original image voxels contributing to each imaging feature. Feature relevance scores tended to reflect the most prominent imaging criteria for each class. CONCLUSIONS: This interpretable deep learning system demonstrates proof of principle for illuminating portions of a pre-trained deep neural network's decision-making, by analyzing inner layers and automatically describing features contributing to predictions. KEY POINTS: • An interpretable deep learning system prototype can explain aspects of its decision-making by identifying relevant imaging features and showing where these features are found on an image, facilitating clinical translation. • By providing feedback on the importance of various radiological features in performing differential diagnosis, interpretable deep learning systems have the potential to interface with standardized reporting systems such as LI-RADS, validating ancillary features and improving clinical practicality. • An interpretable deep learning system could potentially add quantitative data to radiologic reports and serve radiologists with evidence-based decision support.

Deep learning for liver tumor diagnosis part I: development of a convolutional neural network classifier for multi-phasic MRI.

OBJECTIVES: To develop and validate a proof-of-concept convolutional neural network (CNN)-based deep learning system (DLS) that classifies common hepatic lesions on multi-phasic MRI. METHODS: A custom CNN was engineered by iteratively optimizing the network architecture and training cases, finally consisting of three convolutional layers with associated rectified linear units, two maximum pooling layers, and two fully connected layers. Four hundred ninety-four hepatic lesions with typical imaging features from six categories were utilized, divided into training (n = 434) and test (n = 60) sets. Established augmentation techniques were used to generate 43,400 training samples. An Adam optimizer was used for training. Monte Carlo cross-validation was performed. After model engineering was finalized, classification accuracy for the final CNN was compared with two board-certified radiologists on an identical unseen test set. RESULTS: The DLS demonstrated a 92% accuracy, a 92% sensitivity (Sn), and a 98% specificity (Sp). Test set performance in a single run of random unseen cases showed an average 90% Sn and 98% Sp. The average Sn/Sp on these same cases for radiologists was 82.5%/96.5%. Results showed a 90% Sn for classifying hepatocellular carcinoma (HCC) compared to 60%/70% for radiologists. For HCC classification, the true positive and false positive rates were 93.5% and 1.6%, respectively, with a receiver operating characteristic area under the curve of 0.992. Computation time per lesion was 5.6 ms. CONCLUSION: This preliminary deep learning study demonstrated feasibility for classifying lesions with typical imaging features from six common hepatic lesion types, motivating future studies with larger multi-institutional datasets and more complex imaging appearances. KEY POINTS: • Deep learning demonstrates high performance in the classification of liver lesions on volumetric multi-phasic MRI, showing potential as an eventual decision-support tool for radiologists. • Demonstrating a classification runtime of a few milliseconds per lesion, a deep learning system could be incorporated into the clinical workflow in a time-efficient manner.

Prostate Imaging Reporting and Data System Version 2.1: 2019 Update of Prostate Imaging Reporting and Data System Version 2.

The Prostate Imaging Reporting and Data System version 2 (PI-RADS v2) was developed with a consensus-based process using a combination of published data, and expert observations and opinions. In the short time since its release, numerous studies have validated the value of PI-RADS v2 but, as expected, have also identified a number of ambiguities and limitations, some of which have been documented in the literature with potential solutions offered. To address these issues, the PI-RADS Steering Committee, again using a consensus-based process, has recommended several modifications to PI-RADS v2, maintaining the framework of assigning scores to individual sequences and using these scores to derive an overall assessment category. This updated version, described in this article, is termed PI-RADS v2.1. It is anticipated that the adoption of these PI-RADS v2.1 modifications will improve inter-reader variability and simplify PI-RADS assessment of prostate magnetic resonance imaging even further. Research on the value and limitations on all components of PI-RADS v2.1 is strongly encouraged.

Association Between Prostate Magnetic Resonance Imaging and Observation for Low-risk Prostate Cancer.

OBJECTIVE: To evaluate the association between prostate magnetic resonance imaging (MRI) and the use of observation for men with low-risk prostate cancer (PCa). MATERIALS AND METHODS: We used the Surveillance, Epidemiology, and End Results-Medicare database to identify men diagnosed with low-risk PCa during 2010-2013. We assessed the use of prostate MRI and management using claims in period surrounding PCa diagnosis. The relation of clinical and demographic factors to receipt of MRI was evaluated with multivariable logistic regression analysis. Following propensity score matching, we fit conditional logistic regression models to examine the association between prostate MRI and initial management, ie, observation or definitive treatment. RESULTS: Of 8144 patients with low-risk PCa, 495 (6.1%) received MRI. Use of MRI increased from 3.4% in 2010 to 10.5% in 2013. A total of 3060 (37.6%) patients received observation. MRI was performed in 265 (8.7%) of patients receiving observation, and 230 (4.5%) who were treated (P < .0001). In multivariable analysis, measures of socioeconomic status were significantly associated with the use of prostate MRI. Following propensity score matching, receipt of prostate MRI surrounding the diagnosis of PCa was associated with a significantly higher likelihood of observation (odds ratio = 1.90, 95% confidence interval: 1.56-2.32). This effect persisted in sensitivity analyses attempting to exclude treatment-planning MRIs. CONCLUSION: Receipt of prostate MRI surrounding PCa diagnosis was associated with a nearly 2-fold greater odds of receiving observation vs definitive treatment.

MRI-Ultrasound Fusion Targeted Biopsy of Prostate Imaging Reporting and Data System Version 2 Category 5 Lesions Found False-Positive at Multiparametric Prostate MRI.

OBJECTIVE: The purpose of this study was to determine imaging and clinical features associated with Prostate Imaging Reporting and Data System (PI-RADS) category 5 lesions identified prospectively at multiparametric MRI (mpMRI) that were found benign at MRI-ultrasound fusion targeted biopsy. MATERIALS AND METHODS: Between January 2015 and July 2016, 325 men underwent prostate mpMRI followed by MRI-ultrasound fusion targeted biopsy of 420 lesions prospectively identified and assessed with PI-RADS version 2. The frequency of clinically significant prostate cancer (defined as Gleason score ≥ 7) among PI-RADS 5 lesions was determined. Lesions with benign pathologic results were retrospectively reassessed by three abdominal radiologists and categorized as concordant or discordant between mpMRI and biopsy results. Multivariate logistic regression was used to identify factors associated with benign disease. Bonferroni correction was used. RESULTS: Of the 98 PI-RADS 5 lesions identified in 89 patients, 18% (18/98) were benign, 10% (10/98) were Gleason 6 disease, and 71% (70/98) were clinically significant prostate cancer. Factors associated with benign disease at multivariate analysis were lower prostate-specific antigen density (odds ratio [OR], 0.88; p < 0.001) and apex (OR, 3.54; p = 0.001) or base (OR, 7.11; p = 0.012) location. On secondary review of the 18 lesions with benign pathologic results, 39% (7/18) were scored as benign prostatic hyperplasia nodules, 28% (5/18) as inflammatory changes, 5% (1/18) as normal anatomic structures, and 28% (5/18) as discordant with imaging findings. CONCLUSION: PI-RADS 5 lesions identified during routine clinical interpretation are associated with a high risk of clinically significant prostate cancer. A benign pathologic result was significantly correlated with lower prostate-specific antigen density and apex or base location and most commonly attributed to a benign prostatic hyperplasia nodule. Integration of these clinical features may improve the interpretation of high-risk lesions identified with mpMRI.