Daichi Hayashi

OBJECTIVE: To examine use of magnetic resonance imaging (MRI) of knees with no radiographic evidence of osteoarthritis to determine the prevalence of structural lesions associated with osteoarthritis and their relation to age, sex, and obesity. DESIGN: Population based observational study. SETTING: Community cohort in Framingham, MA, United States (Framingham osteoarthritis study). PARTICIPANTS: 710 people aged >50 who had no radiographic evidence of knee osteoarthritis (Kellgren-Lawrence grade 0) and who underwent MRI of the knee. MAIN OUTCOME MEASURES: Prevalence of MRI findings that are suggestive of knee osteoarthritis (osteophytes, cartilage damage, bone marrow lesions, subchondral cysts, meniscal lesions, synovitis, attrition, and ligamentous lesions) in all participants and after stratification by age, sex, body mass index (BMI), and the presence or absence of knee pain. Pain was assessed by three different questions and also by WOMAC questionnaire. RESULTS: Of the 710 participants, 393 (55%) were women, 660 (93%) were white, and 206 (29%) had knee pain in the past month. The mean age was 62.3 years and mean BMI was 27.9. Prevalence of "any abnormality" was 89% (631/710) overall. Osteophytes were the most common abnormality among all participants (74%, 524/710), followed by cartilage damage (69%, 492/710) and bone marrow lesions (52%, 371/710). The higher the age, the higher the prevalence of all types of abnormalities detectable by MRI. There were no significant differences in the prevalence of any of the features between BMI groups. The prevalence of at least one type of pathology ("any abnormality") was high in both painful (90-97%, depending on pain definition) and painless (86-88%) knees. CONCLUSIONS: MRI shows lesions in the tibiofemoral joint in most middle aged and elderly people in whom knee radiographs do not show any features of osteoarthritis, regardless of pain.

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.

Imaging of cartilage has traditionally been achieved indirectly with conventional radiography. Loss of joint space width, or 'joint space narrowing', is considered a surrogate marker for cartilage thinning. However, radiography is severely limited by its inability to visualize cartilage, the difficulty of ascertaining the optimum and reproducible positioning of the joint in serial assessments, and the difficulty of grading joint space narrowing visually. With the availability of advanced magnetic resonance imaging (MRI) scanners, new pulse sequences, and imaging techniques, direct visualization of cartilage has become possible. MRI enables visualization not only of cartilage but also of other important features of osteoarthritis simultaneously. 'Pre-radiographic' cartilage changes depicted by MRI can be measured reliably by a semiquantitative or quantitative approach. MRI enables accurate measurement of longitudinal changes in quantitative cartilage morphology in knee osteoarthritis. Moreover, compositional MRI allows imaging of 'pre-morphologic' changes (that is, visualization of subtle intrasubstance matrix changes before any obvious morphologic alterations occur). Detection of joint space narrowing on radiography seems outdated now that it is possible to directly visualize morphologic and pre-morphologic changes of cartilage by using conventional as well as complex MRI techniques.