Artificial intelligence CAD tools in trauma imaging: a scoping review from the American Society of Emergency Radiology (ASER) AI/ML Expert Panel.

BACKGROUND: AI/ML CAD tools can potentially improve outcomes in the high-stakes, high-volume model of trauma radiology. No prior scoping review has been undertaken to comprehensively assess tools in this subspecialty. PURPOSE: To map the evolution and current state of trauma radiology CAD tools along key dimensions of technology readiness. METHODS: Following a search of databases, abstract screening, and full-text document review, CAD tool maturity was charted using elements of data curation, performance validation, outcomes research, explainability, user acceptance, and funding patterns. Descriptive statistics were used to illustrate key trends. RESULTS: A total of 4052 records were screened, and 233 full-text articles were selected for content analysis. Twenty-one papers described FDA-approved commercial tools, and 212 reported algorithm prototypes. Works ranged from foundational research to multi-reader multi-case trials with heterogeneous external data. Scalable convolutional neural network-based implementations increased steeply after 2016 and were used in all commercial products; however, options for explainability were narrow. Of FDA-approved tools, 9/10 performed detection tasks. Dataset sizes ranged from < 100 to > 500,000 patients, and commercialization coincided with public dataset availability. Cross-sectional torso datasets were uniformly small. Data curation methods with ground truth labeling by independent readers were uncommon. No papers assessed user acceptance, and no method included human-computer interaction. The USA and China had the highest research output and frequency of research funding. CONCLUSIONS: Trauma imaging CAD tools are likely to improve patient care but are currently in an early stage of maturity, with few FDA-approved products for a limited number of uses. The scarcity of high-quality annotated data remains a major barrier.

Assessment of adverse reaction rates during gadoteridol-enhanced MR imaging in 28,078 patients.

PURPOSE: To determine adverse reaction rates in a tertiary care clinical setting after adoption of gadoteridol as the institutional routine magnetic resonance (MR) imaging contrast agent. MATERIALS AND METHODS: With institutional review board approval, informed consent waiver, and HIPAA compliance, a prospective observational study of 28 078 patients who underwent intravenous gadoteridol-enhanced MR imaging from July 2007 to December 2009 was performed. Reactions were recorded by technologists who noted types of reactions, method of injection, and treatment. Reactions were classified as mild, moderate, or severe per American College of Radiology definitions. Comparisons of reaction rates with dose and method of injection were analyzed with the Fisher exact and χ(2) tests. RESULTS: Overall reaction rate was 0.666% (187 patients), including 177 mild, six moderate, and four severe reactions. Treatment was given in 27 patients (14.4%). The most frequent reaction was nausea (and/or vomiting) in 149 patients (79.7% of patients with any adverse reaction, 0.530% of overall population). Method of injection did not affect reaction rate or severity. There was no difference in type or severity of reactions in comparison of patients receiving half the dose versus patients receiving the standard dose (P = .33-.75). CONCLUSION: The observed adverse reaction rate to gadoteridol was lower than previously reported. Specifically, the rate of nausea (0.530%) was less than half the rate (1.4%) in clinical trials of 1251 patients, leading to FDA approval in 1992. Rates of adverse reactions for this macrocyclic contrast agent are comparable to those published for linear gadolinium-based contrast agents.