Preoperative Diagnosis of Dual-Phenotype Hepatocellular Carcinoma Using Enhanced MRI Radiomics Models.

BACKGROUND: Dual-phenotype hepatocellular carcinoma (DPHCC) is highly aggressive and difficult to distinguish from hepatocellular carcinoma (HCC). PURPOSE: To develop and validate clinical and radiomics models based on contrast-enhanced MRI for the preoperative diagnosis of DPHCC. STUDY TYPE: Retrospective. POPULATION: A total of 87 patients with DPHCC and 92 patients with non-DPHCC randomly divided into a training cohort (n = 125: 64 non-DPHCC; 61 DPHCC) and a validation cohort (n = 54: 28 non-DPHCC; 26 DPHCC). FIELD STRENGTH/SEQUENCE: A 3.0 T; dynamic contrast-enhanced MRI with time-resolved T1-weighted imaging sequence. ASSESSMENT: In the clinical model, the maximum tumor diameter and hepatitis B virus (HBV) were independent risk factors of DPHCC. In the radiomics model, a total of 1781 radiomics features were extracted from tumor volumes of interest (VOIs) in the arterial phase (AP) and portal venous phase (PP) images. For feature reduction and selection, Pearson correlation coefficient (PCC) and recursive feature elimination (RFE) were used. Clinical, AP, PP, and combined radiomics models were established using machine learning algorithms (support vector machine [SVM], logistic regression [LR], and logistic regression-least absolute shrinkage and selection operator [LR-LASSO]) and their discriminatory efficacy assessed and compared. STATISTICAL TESTS: The independent sample t test, Mann-Whitney U test, Chi-square test, regression analysis, receiver operating characteristic curve (ROC) analysis, Pearson correlation analysis, the Delong test. A P value < 0.05 was considered statistically significant. RESULTS: In the validation cohort, the combined radiomics model (area under the curve [AUC] = 0.908, 95% confidence interval [CI]: 0.831-0.985) showed the highest diagnostic performance. The AUCs of the PP (AUC = 0.879, 95% CI: 0.779-0.979) and combined radiomics models were significantly higher than that of clinical model (AUC = 0.685, 95% CI: 0.526-0.844). There were no significant differences in AUC between AP or PP radiomics model and combined radiomics model (P = 0.286, 0.180 and 0.543). CONCLUSION: MRI radiomics models may be useful for discriminating DPHCC from non-DPHCC before surgery. EVIDENCE LEVEL: 4 TECHNICAL EFFICACY: Stage 2.

Encapsulating peritoneal sclerosis in an AMA-M2 positive patient: A case report.

BACKGROUND: Encapsulating peritoneal sclerosis (EPS) is hard to diagnose because of nonspecific symptoms and signs. It is a general consensus that EPS is classified as primary and secondary. There have been several studies discovering some high-risk factors such as liver cirrhosis, of which AMA-M2 is a biomarker, and intra-abdominal surgery such as laparoscopic surgery. Imaging studies help to diagnose EPS and exploratory laparotomy might be an alternative if imaging fails. Nowadays, laparotomy plays a key role in treating EPS, especially when medical treatments do not work and medical therapy fails to ease patients' symptoms. CASE SUMMARY: A 58-year-old man complained of unexplained vomiting and abdominal distension 2 mo after laparoscopic cholecystectomy. Increased alkaline phosphatase and liver enzymes were discovered. An autoimmune liver disease test showed that AMA-M2 was positive. A gastroscopy revealed bile reflux gastritis. A magnetic resonance imaging scan showed a slight dilatation of the intrahepatic bile duct. A colonoscopy showed that there was a mucosal eminence lesion in the sigmoid colon (24 cm away from the anus), with a size of 3 cm × 3 cm and erosive surface. At last, the small intestine and the stomach were found to be encased in a cocoon-like membrane during the surgery. The membrane was dissected and adhesiolysis was done to release the trapped organs. The patient recovered and was discharged 44 d after the operation, and there was no recurrence during a follow-up period of 3 mo. CONCLUSION: AMA-M2 is a marker of primary biliary sclerosis and may help to make a preoperative diagnosis of EPS.

Chest imaging of H7N9 subtype of human avian influenza.

BACKGROUND: Human infection with avian influenza A H7N9 virus is an acute respiratory infectious disease, which usually causes severe pneumonia with a high mortality. Chest radiographs and Computed Tomography (CT) are principal radiological modalities to assess the lung abnormalities. OBJECTIVES: The goal of this study was to investigate the chest images characteristic of H7N9 subtype of human avian influenza. MATERIALS AND METHODS: The clinical and imaging data of 11 cases diagnosed as H7N9 subtype of human avian influenza were collected from 4 cities in the southern region of the Yangtze River, China. The chest imaging manifestations were analyzed by the assigned expert group. The analyzed cases include 7 males and 4 females aged from 20 to 84 years, with a mean of 55.6 years. The clinical symptoms were mainly fever (100%, 11/11) and cough (72.7%, 8/11). RESULTS: Segmental or lobar ground-glass opacity (GGO) or consolidation was shown in 8 cases (72.7% or 8/11). Air bronchogram was found in 7 cases (63.6% or 7/11). The lesions developed into multiple or diffuse in both lungs rapidly at the progressive stage. The reticulation shadows were shown after some lesions absorbed at the stable stage. CONCLUSIONS: The characteristic imaging demonstrations of H7N9 subtype of human avian influenza are segmental or lobar exudative lesions at lungs at the initial stage, which rapidly progress into bilateral distribution at lungs at the progressive stage.