ABSTRACT
In the early diagnostic workup of acute pancreatitis (AP), the role of contrast-enhanced CT is to establish the diagnosis in uncertain cases, assess severity, and detect potential complications like necrosis, fluid collections, bleeding or portal vein thrombosis. The value of texture analysis/radiomics of medical images has rapidly increased during the past decade, and the main focus has been on oncological imaging and tumor classification. Previous studies assessed the value of radiomics for differentiating between malignancies and inflammatory diseases of the pancreas as well as for prediction of AP severity. The aim of our study was to evaluate an automatic machine learning model for AP detection using radiomics analysis. Patients with abdominal pain and contrast-enhanced CT of the abdomen in an emergency setting were retrospectively included in this single-center study. The pancreas was automatically segmented using TotalSegmentator and radiomics features were extracted using PyRadiomics. We performed unsupervised hierarchical clustering and applied the random-forest based Boruta model to select the most important radiomics features. Important features and lipase levels were included in a logistic regression model with AP as the dependent variable. The model was established in a training cohort using fivefold cross-validation and applied to the test cohort (80/20 split). From a total of 1012 patients, 137 patients with AP and 138 patients without AP were included in the final study cohort. Feature selection confirmed 28 important features (mainly shape and first-order features) for the differentiation between AP and controls. The logistic regression model showed excellent diagnostic accuracy of radiomics features for the detection of AP, with an area under the curve (AUC) of 0.932. Using lipase levels only, an AUC of 0.946 was observed. Using both radiomics features and lipase levels, we showed an excellent AUC of 0.933 for the detection of AP. Automated segmentation of the pancreas and consecutive radiomics analysis almost achieved the high diagnostic accuracy of lipase levels, a well-established predictor of AP, and might be considered an additional diagnostic tool in unclear cases. This study provides scientific evidence that automated image analysis of the pancreas achieves comparable diagnostic accuracy to lipase levels and might therefore be used in the future in the rapidly growing era of AI-based image analysis.
ABSTRACT
PURPOSE: Tibial shaft spiral fractures and fractures of the distal third of the tibia (AO:42A/B/C and 43A) frequently occur with non-displaced posterior malleolus fractures (PM). This study investigated the hypothesis that plain X-ray is not sufficient for a reliable diagnosis of associated non-displaced PM fractures in tibial shaft spiral fractures. METHODS: 50 X-rays showing 42A/B/C and 43A fractures were evaluated by two groups of physicians, each group was comprised of a resident and a fellowship-trained traumatologist or radiologist. Each group was tasked to make a diagnosis and/or suggest if further imaging was needed. One group was primed with the incidence of PM fractures and asked to explicitly assess the PM. RESULTS: Overall, 9.13/25 (SD ± 5.77) PM fractures were diagnosed on X-ray. If the posterior malleolus fracture was named or a CT was requested, the fracture was considered "detected". With this in mind, 14.8 ± 5.95 posterior malleolus fractures were detected. Significantly more fractures were diagnosed/detected (14 vs. 4.25/25; p < 0.001/14.8 vs. 10.5/25; p < 0.001) in the group with awareness. However, there were significantly more false positives in the awareness group (2.5 vs. 0.5; p = 0.024). Senior physicians recognized slightly more fractures than residents (residents: 13.0 ± 7.79; senior physicians: 16.5 ± 3.70; p = 0.040). No significant differences were demonstrated between radiologists and trauma surgeons. The inner-rater reliability was high with 91.2% agreement. Inter-rater reliability showed fair agreement (Fleiss-Kappa 0.274, p < 0.001) across all examiners and moderate agreement (Fleiss-Kappa 0.561, p < 0.001) in group 2. CONCLUSION: Only 17% of PM fractures were identified on plain X-ray and awareness of PM only improved diagnosis by 39%. While experiencing improved accuracy, CT imaging should be included in a comprehensive examination of tibial shaft spiral fractures. LEVEL OF EVIDENCE: II. Diagnostic prospective cohort study. TRAIL REGISTRATION NUMBER: DRKS00030075.
