Improving Radiographic Fracture Recognition Performance and Efficiency Using Artificial Intelligence.

Background Missed fractures are a common cause of diagnostic discrepancy between initial radiographic interpretation and the final read by board-certified radiologists. Purpose To assess the effect of assistance by artificial intelligence (AI) on diagnostic performances of physicians for fractures on radiographs. Materials and Methods This retrospective diagnostic study used the multi-reader, multi-case methodology based on an external multicenter data set of 480 examinations with at least 60 examinations per body region (foot and ankle, knee and leg, hip and pelvis, hand and wrist, elbow and arm, shoulder and clavicle, rib cage, and thoracolumbar spine) between July 2020 and January 2021. Fracture prevalence was set at 50%. The ground truth was determined by two musculoskeletal radiologists, with discrepancies solved by a third. Twenty-four readers (radiologists, orthopedists, emergency physicians, physician assistants, rheumatologists, family physicians) were presented the whole validation data set (n = 480), with and without AI assistance, with a 1-month minimum washout period. The primary analysis had to demonstrate superiority of sensitivity per patient and the noninferiority of specificity per patient at -3% margin with AI aid. Stand-alone AI performance was also assessed using receiver operating characteristic curves. Results A total of 480 patients were included (mean age, 59 years ± 16 [standard deviation]; 327 women). The sensitivity per patient was 10.4% higher (95% CI: 6.9, 13.9; P < .001 for superiority) with AI aid (4331 of 5760 readings, 75.2%) than without AI (3732 of 5760 readings, 64.8%). The specificity per patient with AI aid (5504 of 5760 readings, 95.6%) was noninferior to that without AI aid (5217 of 5760 readings, 90.6%), with a difference of +5.0% (95% CI: +2.0, +8.0; P = .001 for noninferiority). AI shortened the average reading time by 6.3 seconds per examination (95% CI: -12.5, -0.1; P = .046). The sensitivity by patient gain was significant in all regions (+8.0% to +16.2%; P < .05) but shoulder and clavicle and spine (+4.2% and +2.6%; P = .12 and .52). Conclusion AI assistance improved the sensitivity and may even improve the specificity of fracture detection by radiologists and nonradiologists, without lengthening reading time. Published under a CC BY 4.0 license. Online supplemental material is available for this article. See also the editorial by Link and Pedoia in this issue.

Frequency of MRI-detected peripheral osteoarthritis in athletes during the Summer Olympics in Rio 2016.

Objective: To describe the frequency and severity of magnetic resonance imaging (MRI) based peripheral osteoarthritis (OA) in athletes during the Rio de Janeiro 2016 Olympic Games. Methods: All MRIs of the peripheral joints in Olympic athletes, performed at the centralized imaging facility, either following acute trauma or for non-traumatic joint pain, were included. All MRIs were retrospectively reviewed for presence and severity of MRI-based OA using an adapted Outerbridge classification for cartilage and adapted classifications for other tissues. Scoring of MRI abnormalities was independently and retrospectively performed without reference to the on-site clinical reports. The frequencies of MRI-detected OA were tabulated and grouped into sports categories, athletes' age (<25; 25-29; and ≥30 years of age), and sex. Results: 11,274 athletes participated in the Games. 320 athletes underwent MRI of the peripheral joints. One hundred sixty (50.0%) were female, 109 (34.1%) were <25 years, 132 (41.3%) between the ages of 25 and 29 years old, and 79 (24.7%) ≥30 years old. 53 (16.6%) had MRI-based OA, with slightly more than half having severe OA. In every age category, severe OA was the most frequent finding and there was a linear trend for increased likelihood of having OA with increasing age (Cochran-Armitage test, p â€‹= â€‹0.009). Frequencies of OA were similar in male and female athletes. The wrist (29.2%) and the knee (23.3%) were the most commonly affected joints. Conclusions: MRI-defined OA was not uncommon among elite athletes in this selected sample.

Do as AI say: susceptibility in deployment of clinical decision-aids.

Artificial intelligence (AI) models for decision support have been developed for clinical settings such as radiology, but little work evaluates the potential impact of such systems. In this study, physicians received chest X-rays and diagnostic advice, some of which was inaccurate, and were asked to evaluate advice quality and make diagnoses. All advice was generated by human experts, but some was labeled as coming from an AI system. As a group, radiologists rated advice as lower quality when it appeared to come from an AI system; physicians with less task-expertise did not. Diagnostic accuracy was significantly worse when participants received inaccurate advice, regardless of the purported source. This work raises important considerations for how advice, AI and non-AI, should be deployed in clinical environments.

Imaging of Gastrointestinal Tract Perforation.

Gastrointestinal tract perforation involving the stomach, duodenum, small intestine, or large bowel occurs as a result of full-thickness gastrointestinal wall injury with release of intraluminal contents into the peritoneal or retroperitoneal cavity. Most cases are associated with high mortality and morbidity, requiring urgent surgical evaluation. Initial patient presentations can be nonspecific with a broad differential, which can delay timely management. This article provides brief overviews of different causes of perforation. Various imaging modalities and protocols are discussed, along with direct and indirect imaging findings of perforation. Specific findings associated with different causes are also described to aid in the diagnosis.

Computed tomography (CT) in the evaluation of bladder and ureteral trauma: indications, technique, and diagnosis.

INTRODUCTION: Trauma to the genitourinary system includes blunt and penetrating injuries to bladder and ureters. These are rare injuries and are overlooked as other abdominal and pelvic injuries often take priority. Delayed diagnosis can lead to significant morbidity and mortality. Computed tomography has taken a central role in the imaging of the ureters and bladder. METHODS: This article reviews the anatomic relationships, mechanisms of injury, and clinical presentation to help physicians determine when bladder and ureteral injuries should be suspected and further imaging should be pursued. Radiologic evaluation of bladder and ureteral injury with CT cystography and CT urography, respectively, will be reviewed. CONCLUSION: CT cystography and CT urography are effective tools in identifying potentially serious injuries to the genitourinary system. Timely recognition of these injuries can be crucial for the overall management and prognosis.