Population-Scale CT-based Body Composition Analysis of a Large Outpatient Population Using Deep Learning to Derive Age-, Sex-, and Race-specific Reference Curves.

Background Although CT-based body composition (BC) metrics may inform disease risk and outcomes, obtaining these metrics has been too resource intensive for large-scale use. Thus, population-wide distributions of BC remain uncertain. Purpose To demonstrate the validity of fully automated, deep learning BC analysis from abdominal CT examinations, to define demographically adjusted BC reference curves, and to illustrate the advantage of use of these curves compared with standard methods, along with their biologic significance in predicting survival. Materials and Methods After external validation and equivalency testing with manual segmentation, a fully automated deep learning BC analysis pipeline was applied to a cross-sectional population cohort that included any outpatient without a cardiovascular disease or cancer who underwent abdominal CT examination at one of three hospitals in 2012. Demographically adjusted population reference curves were generated for each BC area. The z scores derived from these curves were compared with sex-specific thresholds for sarcopenia by using χ2 tests and used to predict 2-year survival in multivariable Cox proportional hazards models that included weight and body mass index (BMI). Results External validation showed excellent correlation (R = 0.99) and equivalency (P < .001) of the fully automated deep learning BC analysis method with manual segmentation. With use of the fully automated BC data from 12 128 outpatients (mean age, 52 years; 6936 [57%] women), age-, race-, and sex-normalized BC reference curves were generated. All BC areas varied significantly with these variables (P < .001 except for subcutaneous fat area vs age [P = .003]). Sex-specific thresholds for sarcopenia demonstrated that age and race bias were not present if z scores derived from the reference curves were used (P < .001). Skeletal muscle area z scores were significantly predictive of 2-year survival (P = .04) in combined models that included BMI. Conclusion Fully automated body composition (BC) metrics vary significantly by age, race, and sex. The z scores derived from reference curves for BC parameters better capture the demographic distribution of BC compared with standard methods and can help predict survival. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Summers in this issue.

Tibial bone stress injury: diagnostic performance and inter-reader agreement of an abbreviated 5-min magnetic resonance protocol.

OBJECTIVE: To compare the diagnostic performance and inter-reader agreement of an abbreviated (5 min) MR protocol compared to a complete (25 min) protocol, for evaluation of suspected tibial bone stress injury. MATERIALS AND METHODS: This IRB-approved retrospective study consisted of 95 consecutive MR examinations in 88 patients with suspected tibial bone stress injury. Three musculoskeletal radiologists independently classified all examinations utilizing both an abbreviated protocol consisting only of axial T2-weighted images with fat suppression, and after a washout period again classified the complete examinations. Accuracy was calculated as proportion of cases classified exactly, within 1 grade, within 2 grades, and also utilizing a simplified "clinically relevant" classification combining grades 2, 3, and 4A into a single group. Significance testing was performed with the chi-test, and a post-hoc power analysis was performed. Inter-reader agreement was calculated with Kendall's coefficient of concordance, with significance testing performed utilizing the z-test after bootstrapping to obtain the standard error. RESULTS AND CONCLUSIONS: There was no significant difference in accuracy of grading tibial bone stress injuries between complete and abbreviated examinations. For complete exams, pooled exact accuracy was 47.8%; accuracy within 1 grade was 82.8%; and accuracy within 2 grades was 96.1%. For the abbreviated protocol, corresponding accuracies were 50.2, 82.0, and 93.9%. With the "clinically relevant" simplified classification, accuracy was 58.6% for complete exams and 64.2% for abbreviated exams. There was no significant difference in inter-reader agreement, with substantial agreement demonstrated for both complete (Kendall coefficient of concordance 0.805) and abbreviated examinations (coefficient of 0.767).

A simplified classification of proximal femoral fractures improves accuracy, confidence, and inter-reader agreement of hip fracture classification by radiology residents.

PURPOSE: To demonstrate the effect of teaching a simplified treatment-based classification of proximal femoral fractures on the accuracy, confidence, and inter-reader agreement of radiology residents. The authors hypothesize that these measures will improve after viewing an educational presentation. MATERIALS AND METHODS: Three radiology residents independently classified 100 operative proximal femoral fractures, both before and after viewing a 45-min educational video describing the simplified classification scheme, with a washout period of at least 12 weeks between sessions. Based on the gold standard established by consensus of two radiologists and an orthopedic trauma surgeon utilizing intraoperative fluoroscopic imaging, operative reports, and pre-procedural imaging, accuracy of classification was calculated for each reader before and after viewing the educational video. Reader confidence was recorded on a 0-10 scale, and inter-reader agreement was calculated with Fleiss's kappa. McNemar's test was used to compare accuracy, a paired t test was used to compare confidence, and the Z-test was used to compare kappa values after bootstrapping to determine the standard error of the mean. RESULTS: The study cohort included 60/100 females, with a mean age of 76.6 years. The pooled classification accuracy was initially 65%, which improved to 80% in the second reading session after viewing the educational video (p < 0.0001). Confidence improved from 6.9 initially to 8.6 (p < 0.0001). Inter-reader agreement improved from a kappa of 0.45 (moderate agreement) to 0.74 (substantial agreement) (p < 0.0001). CONCLUSIONS: A simplified treatment-based classification of proximal femoral fractures is easily taught to radiology residents and resulted in increased accuracy, increased inter-reader agreement, and increased reader confidence.