Renal Mass Imaging with MRI Clear Cell Likelihood Score: A User's Guide.

Small solid renal masses (SRMs) are frequently detected at imaging. Nearly 20% are benign, making careful evaluation with MRI an important consideration before deciding on management. Clear cell renal cell carcinoma (ccRCC) is the most common renal cell carcinoma subtype with potentially aggressive behavior. Thus, confident identification of ccRCC imaging features is a critical task for the radiologist. Imaging features distinguishing ccRCC from other benign and malignant renal masses are based on major features (T2 signal intensity, corticomedullary phase enhancement, and the presence of microscopic fat) and ancillary features (segmental enhancement inversion, arterial-to-delayed enhancement ratio, and diffusion restriction). The clear cell likelihood score (ccLS) system was recently devised to provide a standardized framework for categorizing SRMs, offering a Likert score of the likelihood of ccRCC ranging from 1 (very unlikely) to 5 (very likely). Alternative diagnoses based on imaging appearance are also suggested by the algorithm. Furthermore, the ccLS system aims to stratify which patients may or may not benefit from biopsy. The authors use case examples to guide the reader through the evaluation of major and ancillary MRI features of the ccLS algorithm for assigning a likelihood score to an SRM. The authors also discuss patient selection, imaging parameters, pitfalls, and areas for future development. The goal is for radiologists to be better equipped to guide management and improve shared decision making between the patient and treating physician. © RSNA, 2023 Quiz questions for this article are available in the supplemental material. See the invited commentary by Pedrosa in this issue.

Self-Assessment Feedback Form Improves Quality of Out-of-Hospital CPR.

Objective: Various continuous quality improvement (CQI) approaches have been used to improve quality of cardiopulmonary resuscitation (CPR) delivered at the scene of out-of-hospital cardiac arrest. We evaluated a post-event, self-assessment, CQI feedback form to determine its impact on delivery of CPR quality metrics. Methods: This before/after retrospective review evaluated data from a CQI program in a midsized urban emergency medical services (EMS) system using CPR quality metrics captured by Zoll Medical Inc. X-series defibrillator ECG files in adult patients (≥18 years old) with non-traumatic out-of-hospital cardiac arrest. Two 9-month periods, one before and one after implementation of the feedback form on December 31, 2013 were evaluated. Metrics included the mean and percentage of goal achievement for chest compression depth (goal: >5 centimeters [cm]; >90%/episode), rate (goal: 100-120 compressions/minute [min]), chest compression fraction (goal: ≥75%), and preshock pause (goal: <10 seconds [sec]). The feedback form was distributed to all EMS providers involved in the resuscitation within 72 hours for self-review. Results: A total of 439 encounters before and 621 encounters after were evaluated including basic life support (BLS) and advanced life support (ALS) providers. The Before Group consisted of 408 patients with an average age of 61 ± 17 years, 61.8% male. The After Group consisted of 556 patients with an average age of 61 ± 17 years, 58.3% male. Overall, combining BLS and ALS encounters, the mean CPR metric values before and after were: chest compression depth (5.0 cm vs. 5.5 cm; p < 0.001), rate (109.6/min vs 114.8/min; p < 0.001), fraction (79.2% vs. 86.4%; p < 0.001), and preshock pause (18.8 sec vs. 11.8 sec; p < 0.001), respectively. Overall, the percent goal achievement before and after were: chest compression depth (48.5% vs. 66.6%; p < 0.001), rate (71.8% vs. 71.7%, p = 0.78), fraction (68.1% vs. 91.0%; p < 0.001), and preshock pause (24.1% vs. 59.5%; p < 0.001), respectively. The BLS encounters and ALS encounters had similar statistically significant improvements seen in all metrics. Conclusion: This post-event, self-assessment CQI feedback form was associated with significant improvement in delivery of out-of-hospital CPR depth, fraction and preshock pause time.

Accurate segmentation of prostate cancer histomorphometric features using a weakly supervised convolutional neural network.

Purpose: Prostate cancer primarily arises from the glandular epithelium. Histomophometric techniques have been used to assess the glandular epithelium in automated detection and classification pipelines; however, they are often rigid in their implementation, and their performance suffers on large datasets where variation in staining, imaging, and preparation is difficult to control. The purpose of this study is to quantify performance of a pixelwise segmentation algorithm that was trained using different combinations of weak and strong stroma, epithelium, and lumen labels in a prostate histology dataset. Approach: We have combined weakly labeled datasets generated using simple morphometric techniques and high-quality labeled datasets from human observers in prostate biopsy cores to train a convolutional neural network for use in whole mount prostate labeling pipelines. With trained networks, we characterize pixelwise segmentation of stromal, epithelium, and lumen (SEL) regions on both biopsy core and whole-mount H&E-stained tissue. Results: We provide evidence that by simply training a deep learning algorithm on weakly labeled data generated from rigid morphometric methods, we can improve the robustness of classification over the morphometric methods used to train the classifier. Conclusions: We show that not only does our approach of combining weak and strong labels for training the CNN improve qualitative SEL labeling within tissue but also the deep learning generated labels are superior for cancer classification in a higher-order algorithm over the morphometrically derived labels it was trained on.

Radio-pathomic mapping model generated using annotations from five pathologists reliably distinguishes high-grade prostate cancer.

Purpose: Our study predictively maps epithelium density in magnetic resonance imaging (MRI) space while varying the ground truth labels provided by five pathologists to quantify the downstream effects of interobserver variability. Approach: Clinical imaging and postsurgical tissue from 48 recruited prospective patients were used in our study. Tissue was sliced to match the MRI orientation and whole-mount slides were stained and digitized. Data from 28 patients ( n = 33 slides) were sent to five pathologists to be annotated. Slides from the remaining 20 patients ( n = 123 slides) were annotated by one of the five pathologists. Interpathologist variability was measured using Krippendorff's alpha. Pathologist-specific radiopathomic mapping models were trained using a partial least-squares regression using MRI values to predict epithelium density, a known marker for disease severity. An analysis of variance characterized intermodel means difference in epithelium density. A consensus model was created and evaluated using a receiver operator characteristic classifying high grade versus low grade and benign, and was statistically compared to apparent diffusion coefficient (ADC). Results: Interobserver variability ranged from low to acceptable agreement (0.31 to 0.69). There was a statistically significant difference in mean predicted epithelium density values ( p < 0.001 ) between the five models. The consensus model outperformed ADC (areas under the curve = 0.80 and 0.71, respectively, p < 0.05 ). Conclusion: We demonstrate that radiopathomic maps of epithelium density are sensitive to the pathologist annotating the dataset; however, it is unclear if these differences are clinically significant. The consensus model produced the best maps, matched the performance of the best individual model, and outperformed ADC.

Assessment of Consistency Between Peer-Reviewed Publications and Clinical Trial Registries.

Importance: Clinical trial registries are intended to increase clinical research transparency by nonselectively identifying and documenting clinical trial designs and outcomes. Inconsistencies in reported data undermine the utility of such registries and have previously been noted in general medical literature. Objective: To assess whether inconsistencies in reported data exist between ophthalmic literature and clinical trial registries. Design, Setting, and Participants: In this retrospective, cross-sectional study, interventional clinical trials published from January 1, 2014, to December 31, 2014, in the American Journal of Ophthalmology, JAMA Ophthalmology, and Ophthalmology were reviewed. Observational, retrospective, uncontrolled, and post hoc reports were excluded, yielding a sample size of 106 articles. Data collection was performed from January through September 2016. Data review and adjudication continued through January 2017. Main Outcomes and Measures: If possible, articles were matched to registry entries listed in the ClinicalTrials.gov database or in 1 of 16 international registries indexed by the World Health Organization International Clinical Trials Registry Platform version 3.2 search engine. Each article-registry pair was assessed for inconsistencies in design, results, and funding (each of which was further divided into subcategories) by 2 reviewers and adjudicated by a third. Results: Of 106 trials that met the study criteria, matching registry entries were found for 68 (64.2%), whereas no matching registry entries were found for 38 (35.8%). Inconsistencies were identified in study design, study results, and funding sources, including specific interventions in 8 (11.8%), primary outcome measure (POM) designs in 32 (47.1%), and POM results in 48 (70.6%). In addition, numerous data pieces were unreported, including analysis methods in 52 (76.5%) and POM results in 38 (55.9%). Conclusions and Relevance: Clinical trial registries were underused in this sample of ophthalmology clinical trials. For studies with registry data, inconsistency rates between published and registered data were similar to those previously reported for general medical literature. In most cases, inconsistencies involved missing data, but explicit discrepancies in methods and/or data were also found. Transparency and credibility of published trials may be improved by closer attention to their registration and reporting.

Gleason Probability Maps: A Radiomics Tool for Mapping Prostate Cancer Likelihood in MRI Space.

Prostate cancer is the most common noncutaneous cancer in men in the United States. The current paradigm for screening and diagnosis is imperfect, with relatively low specificity, high cost, and high morbidity. This study aims to generate new image contrasts by learning a distribution of unique image signatures associated with prostate cancer. In total, 48 patients were prospectively recruited for this institutional review board-approved study. Patients underwent multiparametric magnetic resonance imaging 2 weeks before surgery. Postsurgical tissues were annotated by a pathologist and aligned to the in vivo imaging. Radiomic profiles were generated by linearly combining 4 image contrasts (T2, apparent diffusion coefficient [ADC] 0-1000, ADC 50-2000, and dynamic contrast-enhanced) segmented using global thresholds. The distribution of radiomic profiles in high-grade cancer, low-grade cancer, and normal tissues was recorded, and the generated probability values were applied to a naive test set. The resulting Gleason probability maps were stable regardless of training cohort, functioned independent of prostate zone, and outperformed conventional clinical imaging (area under the curve [AUC] = 0.79). Extensive overlap was seen in the most common image signatures associated with high- and low-grade cancer, indicating that low- and high-grade tumors present similarly on conventional imaging.