Machine Learning Based Prediction Model for Closed-Loop Small Bowel Obstruction Using Computed Tomography and Clinical Findings.

PURPOSE: The aim of the study was to develop a prediction model for closed-loop small bowel obstruction integrating computed tomography (CT) and clinical findings. METHODS: The radiology database and surgical reports from 2 suburban teaching hospitals were retrospectively reviewed for patients undergoing surgery for suspected closed-loop small bowel obstruction (CLSBO). Two observers independently reviewed the CT scans for the presence of imaging features of CLSBO, blinded to the surgically confirmed diagnosis and clinical parameters. Random forest analysis was used to train and validate a prediction model for CLSBO, by combining CT and clinical findings, after randomly splitting the sample into 80% training and 20% test subsets. RESULTS: Surgery confirmed CLSBO in 185 of 223 patients with clinically suspected CLSBO. Age greater than 52 years showed 2.82 (95% confidence interval = 1.13-4.77) times higher risk for CLSBO (P = 0.021). Sensitivity/specificity of CT findings included proximal dilatation (97/5%), distal collapse (96/2%), mesenteric edema (94/5%), pneumatosis (1/100%), free air (1/98%), and portal venous gas (0/100%). The random forest model combining imaging/clinical findings yielded an area under receiver operating curve of 0.73 (95% confidence interval = 0.58-0.94), sensitivity of 0.72 (0.55-0.85), specificity of 0.8 (0.28-0.99), and accuracy of 0.73 (0.57-0.85). Prior surgery, age, lactate, whirl sign, U/C-shaped bowel configuration, and fecalization were the most important variables in predicting CLSBO. CONCLUSIONS: A random forest model found clinical factors including prior surgery, age, lactate, and imaging factors including whirl sign, fecalization, and U/C-shaped bowel configuration are helpful in improving the prediction of CLSBO. Individual CT findings in CLSBO had either high sensitivity or specificity, suggesting that accurate diagnosis requires systematic assessment of all CT signs.

Thromboembolic complications of COVID-19.

The symptomology of patients afflicted with novel 2019 coronavirus disease (SARS-CoV-2 or COVID-19) has varied greatly, ranging from the asymptomatic state to debilitating hypoxemic respiratory failure caused by severe atypical viral pneumonia. Patients may also develop a hyper-inflammatory state that can lead to multi-organ failure. It has become increasingly apparent that, as part of the hyper-inflammatory state, COVID-19 infection increases susceptibility to systemic thromboembolic complications that can contribute to rapid clinical deterioration or demise. This article aims to review imaging features of various systemic thrombotic complications in six patients with moderate to severe disease. This case series includes examples of pulmonary embolism, stroke, right ventricular thrombosis, renal vein thrombosis, and aortic thrombosis with leg ischemia.

Clinical and imaging features indicative of clinically worrisome pneumatosis: key components to identifying proper medical intervention.

PURPOSE: The purpose of this retrospective study was to determine clinical and imaging factors on computed tomography (CT) associated with clinically worrisome pneumatosis intestinalis (PI) that may aid in the decision to provide conservative management or urgent surgical intervention. METHODS: Informed consent was waived in this IRB approved study. Imaging features assessed included the presence, location, and pattern of PI, bowel dilatation, thickening, enhancement, stranding, portal venous (PV) and mesenteric venous gas, mesenteric edema, free air, and ascites. Two radiologists retrospectively evaluated 167 patients with CT reports containing the text "PI" between 1/1/11 and 12/31/13. Clinical data collected included serum lactate, malignancy, bowel disease, operative findings, and death during admission. Clinically, worrisome PI was tabulated by summation of surgical diagnosis of dead bowel and/or death during admission. Chi-square test or Fisher's exact test was used when appropriate to compare subjects with benign or worrisome PI for categorical variables and the Mann-Whitney test used to compare continuous measures. RESULTS: Clinically, worrisome PI was present in 44 cases. Benign PI was diagnosed in 97 cases, and these patients were followed conservatively. There was a statistically significant association between clinically worrisome PI and imaging features: location in small bowel (p < 0.0001), bowel dilatation (p = 0.0003), stranding (p = 0.0002), bowel enhancement (p = 0.0384), PV gas (p < 0.0001), mesenteric venous gas (p = 0.0141), and moderate mesenteric edema (p = 0.0036). Location of PI in the small bowel exhibited a statistically significant association with benign PI (p < 0.0002). Statistical significance was found between worrisome PI and the following clinical features: elevated serum lactate (p = 0.0003), underlying bowel disease (p = 0.0004), and mechanical cause of bowel obstruction (p = 0.0497). CONCLUSION: CT imaging characteristics and clinical features can help predict clinically worrisome PI and guide crucial management decisions.

Value of gadolinium-enhanced MRI in detection of acute appendicitis in children and adolescents.

OBJECTIVE: The aim of this study was to determine both the value of gadolinium-enhanced MRI in children with suspected acute appendicitis and the best sequences for detecting acute appendicitis, to thereby decrease imaging time. MATERIALS AND METHODS: This was a retrospective review of pediatric patients with suspected appendicitis who had undergone MRI at our institution between 2010 and 2011 after an indeterminate ultrasound examination. MRI examinations included T1-weighted unenhanced and contrast-enhanced, T2-weighted, and balanced steady-state free precession (SSFP) sequences in axial and coronal planes. Sequences were reviewed together and individually by five radiologists who were blinded to the final diagnosis. Radiologists were asked to score their confidence of appendicitis diagnosis using a 5-point scale. The diagnostic performance of each MR sequence was obtained by comparing the mean area under the curve (AUC) using receiver operating characteristic (ROC) analysis. RESULTS: A total of 49 patients with clinically suspected appendicitis were included, of whom 16 received a diagnosis of appendicitis. The mean AUCs for reviewing all sequences together, contrast-enhanced sequences alone, T2-weighted sequences alone, and balanced SSFP alone were 0.984, 0.979, 0.944, and 0.910, respectively. No significant difference was observed between reviewing all sequences together versus contrast-enhanced sequences alone (p = 0.90) and T2-weighted sequences alone (p = 0.23). A significant difference was observed between contrast-enhanced sequences and balanced SSFP (p < 0.03). CONCLUSION: Gadolinium-enhanced images and T2-weighted images are most helpful in the assessment of acute appendicitis in the pediatric population. These findings have led to protocol modifications that have reduced imaging time.

Routine intraoperative hepatic sonography does not affect staging or postsurgical hepatic recurrence in pancreatic adenocarcinoma.

OBJECTIVES: The purpose of this study was to evaluate the utility of intraoperative sonography of the liver in the staging of pancreatic adenocarcinoma and its impact on the rate of postoperative tumor recurrence in the liver. METHODS: We performed a retrospective analysis of the rate in which intraoperative sonography of the liver changed surgical management in 470 surgical candidates with pancreatic adenocarcinoma. In postsurgical patients, we performed a χ(2) analysis to examine whether the patients who underwent hepatic intraoperative sonography had a lower rate of recurrent disease in the liver within the first 6 months of surgery compared to patients who did not undergo the procedure. RESULTS: Hepatic intraoperative sonography affected management in less than 1% of cases, detecting 1 unsuspected liver metastasis in 470 surgical patients with pancreatic adenocarcinoma. Of 3 patients with equivocal liver lesions identified on preoperative computed tomography or magnetic resonance imaging, hepatic intraoperative sonography excluded metastasis and cleared all the patients for surgical resection. There was no significant difference in postoperative liver recurrence between the group of patients who received intraoperative sonography before resection and patients who did not have the procedure done (P > .99). CONCLUSIONS: Routine intraoperative sonography of the liver does not affect staging of pancreatic adenocarcinoma. It may be useful for evaluating equivocal lesions.

Comparison of CT and MRI in patients with tibial plateau fracture: can CT findings predict ligament tear or meniscal injury?

OBJECTIVE: (1) To determine the accuracy of computed tomography (CT) in the evaluation of ligament tear and avulsion in patients with tibial plateau fracture. (2) To evaluate whether the presence or severity of fracture gap and articular depression can predict meniscal injury. DESIGN AND PATIENTS: A fellowship-trained musculoskeletal radiologist retrospectively reviewed knee CT and MRI examinations of 41 consecutive patients presenting to a level 1 trauma center with tibial plateau fractures. Fracture gap, articular depression, ligament tear and footprint avulsions were assessed on CT examinations. The MRI studies were examined for osseous and soft tissue injuries, including meniscal tear, meniscal displacement, ligament tear, and ligament avulsion. RESULTS: CT demonstrated torn ligaments with 80% sensitivity and 98% specificity. Only 2% of ligaments deemed intact on careful CT evaluation had partial or complete tears on MRI. Although the degree of fracture gap and articular depression was significantly greater in patients with meniscal injury compared with those without meniscal injury, ROC analysis demonstrated no clear threshold for gap or depression that yielded a combination of high sensitivity and specificity. CONCLUSIONS: In the acute setting, CT offers high sensitivity and specificity for depicting osseous avulsions, as well as high negative predictive value for excluding ligament injury. However, MRI remains necessary for the preoperative detection of meniscal injury.