Gadolinium-based contrast agents (GBCAs) have an excellent safety profile. However, over the last 2 decades, two specific concerns have surfaced. GBCAs are associated with nephrogenic systemic ...fibrosis (NSF) and tissue retention of gadolinium. NSF is a rare fibrosing disorder with a poor prognosis, which is characterized by skin and subcutaneous thickening as well as systemic manifestations. The disease has been reported exclusively in patients with advanced renal disease, and it is associated with higher doses and specific types of GBCAs. The number of new cases of NSF has fallen over the past decade, presumably because of adherence by health care providers to regulatory guidelines, which continue to evolve. While gadolinium retention has been known to occur in the liver and bones, the relatively recent findings of deposition and retention in the brain have reignited the debate concerning the safety profile of GBCAs. Despite these concerns, there have been no proven health effects related to gadolinium deposition and retention other than NSF. The authors review the different categories of GBCAs available for commercial use, discuss NSF and gadolinium retention in the brain, and provide updates on the latest U.S. and European regulatory guidelines regarding use of these agents. Given the frequency with which GBCAs are used in clinical practice, it is imperative for all radiologists to learn the current guidelines to provide the safest and highest quality of patient care.
RSNA, 2019.
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.
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.
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.
The Prostate Imaging Reporting and Data System (PI-RADS) Committee, using a consensus-based process, has recommended several modifications to PI-RADS version 2 (v2), maintaining the framework of assigning scores to individual sequences and using these scores to derive an overall assessment category. The updated version is termed PI-RADS v2.1.
Abstract The Prostate Imaging – Reporting and Data System Version 2 (PI-RADS™ v2) is the product of an international collaboration of the American College of Radiology (ACR), European Society of ...Uroradiology (ESUR), and AdMetech Foundation. It is designed to promote global standardization and diminish variation in the acquisition, interpretation, and reporting of prostate multiparametric magnetic resonance imaging (mpMRI) examination, and it is based on the best available evidence and expert consensus opinion. It establishes minimum acceptable technical parameters for prostate mpMRI, simplifies and standardizes terminology and content of reports, and provides assessment categories that summarize levels of suspicion or risk of clinically significant prostate cancer that can be used to assist selection of patients for biopsies and management. It is intended to be used in routine clinical practice and also to facilitate data collection and outcome monitoring for research.
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 m
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 m
at the discretion of the ordering clinician. This article is a simultaneous joint publication in
and
. The articles are identical except for stylistic changes in keeping with each journal's style. Either version may be used in citing this article.
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.
The objective of our study was to evaluate the diagnostic accuracy of abbreviated biparametric MRI (bpMRI) versus standard multiparametric MRI (mpMRI) for prostate cancer (PCa) using guided biopsy or ...prostatectomy histopathology results as the reference standard.
A comprehensive literature search of PubMed, Web of Science, and Cochrane Library databases was performed by two researchers independently and the relevant references were assessed. Original research studies comparing bpMRI with mpMRI in diagnosing PCa were included. The methodologic quality of eligible studies was assessed using the Quality Assessment of Diagnostic Accuracy Studies 2 tool. Data necessary to complete 2 × 2 contingency tables were obtained to calculate the diagnostic performance of bpMRI and mpMRI using Stata (version 14).
Ten studies were included, and a total of 1705 patients and 3419 lesions were analyzed. Sensitivity, specificity, positive likelihood ratio (LR), negative LR, and diagnostic odds ratio (DOR) of mpMRI in diagnosing PCa were 0.79 (95% CI, 0.69-0.87), 0.89 (95% CI, 0.70-0.96), 6.9 (95% CI, 2.5-18.8), 0.24 (95% CI, 0.16-0.35), and 29 (95% CI, 10-83). Sensitivity, specificity, positive LR, negative LR, and DOR of bpMRI in diagnosing PCa were 0.79 (95% CI, 0.69-0.87), 0.88 (95% CI, 0.73-0.95), 6.4 (95% CI, 2.9-14.5), 0.24 (95% CI, 0.16-0.35), and 27 (95% CI, 11-67). Meta-analysis showed no statistically significant difference between bpMRI and mpMRI for the diagnosis of PCa, and the areas under the summary ROC (SROC) curves were 0.89 and 0.88, respectively (p = 0.9944). Results of the sensitivity analysis were consistent, and the area under the SROC curve for bpMRI and mpMRI was 0.89 for both (p = 0.9349).
The available evidence indicates that bpMRI and mpMRI have similar diagnostic efficacy in diagnosing PCa.