The coronavirus disease 2019 (COVID-19) pandemic is a global health care emergency. Although reverse-transcription polymerase chain reaction testing is the reference standard method to identify patients with COVID-19 infection, chest radiography and CT play a vital role in the detection and management of these patients. Prediction models for COVID-19 imaging are rapidly being developed to support medical decision making. However, inadequate availability of a diverse annotated data set has limited the performance and generalizability of existing models. To address this unmet need, the RSNA and Society of Thoracic Radiology collaborated to develop the RSNA International COVID-19 Open Radiology Database (RICORD). This database is the first multi-institutional, multinational, expert-annotated COVID-19 imaging data set. It is made freely available to the machine learning community as a research and educational resource for COVID-19 chest imaging. Pixel-level volumetric segmentation with clinical annotations was performed by thoracic radiology subspecialists for all COVID-19–positive thoracic CT scans. The labeling schema was coordinated with other international consensus panels and COVID-19 data annotation efforts, the European Society of Medical Imaging Informatics, the American College of Radiology, and the American Association of Physicists in Medicine. Study-level COVID-19 classification labels for chest radiographs were annotated by three radiologists, with majority vote adjudication by board-certified radiologists. RICORD consists of 240 thoracic CT scans and 1000 chest radiographs contributed from four international sites. It is anticipated that RICORD will ideally lead to prediction models that can demonstrate sustained performance across populations and health care systems. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Bai and Thomasian in this issue.

PurposeTrastuzumab improves survival in patients with HER2+ early breast cancer. However, cardiotoxicity remains a concern, particularly in the curative setting, and there are limited data on its incidence outside of clinical trials. We retrospectively evaluated the cardiotoxicity rates (left ventricular ejection fraction [LVEF] decline, congestive heart failure [CHF], cardiac death or trastuzumab discontinuation) and assessed the performance of a proposed model to predict cardiotoxicity in routine clinical practice. MethodsPatients receiving curative trastuzumab between 2011-2018 were identi ed. Demographics, treatments, assessments and toxicities were recorded. Fisher's exact test, chi-squared and logistic regression were used. Results931 patients were included in the analysis. Median age was 54 years (range 24-83) and Charlson comorbidity index 0 (0-6), with 195 patients (20.9%) aged 65 or older. 228 (24.5%) were smokers. Anthracyclines were given in 608 (65.3%). Median number of trastuzumab doses was 18 (1-18). The HFA-ICOS cardiovascular risk was low in 401 patients (43.1%), medium in 454 (48.8%), high in 70 (7.5%) and very high in 6 (0.6%).Overall, 155 (16.6%) patients experienced cardiotoxicity: LVEF decline≥10% in 141 (15.1%), falling below 50% in 55 (5.9%), CHF NYHA class II in 42 (4.5%) and class III-IV in 5 (0.5%) and discontinuation due to cardiac reasons in 35 (3.8%). No deaths were observed.Cardiotoxicity rates increased with HFA-ICOS score (14.0% low, 16.7% medium, 30.3% high/very high; p=0.002). ConclusionsCardiotoxicity was relatively common (16.6%), but symptomatic heart failure on trastuzumab was rare in our cohort. The HFA-ICOS score identi es patients at high risk of cardiotoxicity

No abstract

Cognitive fusion MRI-TRUS-guided targeted biopsy yielded substantially lower rates of clinically significant cancer in PI-RADS v2 score 4 and 5 lesions when compared to published results using in-bore MR-guided or automated MRI-TRUS fusion guidance systems. Cancer detection was worst for TZ lesions.