Deep learning nomogram for preoperative distinction between Xanthogranulomatous cholecystitis and gallbladder carcinoma: A novel approach for surgical decision.

The distinction between Xanthogranulomatous Cholecystitis (XGC) and Gallbladder Carcinoma (GBC) is challenging due to their similar imaging features. This study aimed to differentiate between XGC and GBC using a deep learning nomogram model built from contrast enhanced computed tomography (CT) scans. 297 patients were included with confirmed XGC (94) and GBC (203) as the training and internal validation cohort from 2017 to 2021. The deep learning model Resnet-18 with Fourier transformation named FCovResnet18, shows most impressive potential in distinguishing XGC from GBC using 3-phase merged images. The accuracy, precision and area under the curve (AUC) of the model were then calculated. An additional cohort of 74 patients consisting of 22 XGC and 52 GBC patients was enrolled from two subsidiary hospitals as the external validation cohort. The accuracy, precision and AUC achieve 0.98, 0.99, 1.00 in the internal validation cohort and 0.89, 0.92, 0.92 in external validation cohort. A nomogram model combining clinical characteristics and deep learning prediction score showed improved predicting value. Altogether, FCovResnet18 nomogram has demonstrated its ability to effectively differentiate XGC from GBC preoperatively, which significantly aid surgeons in making informed and accurate surgical decisions for XGC and GBC patients.

MVI-TR: A Transformer-Based Deep Learning Model with Contrast-Enhanced CT for Preoperative Prediction of Microvascular Invasion in Hepatocellular Carcinoma.

In this study, we considered preoperative prediction of microvascular invasion (MVI) status with deep learning (DL) models for patients with early-stage hepatocellular carcinoma (HCC) (tumor size ≤ 5 cm). Two types of DL models based only on venous phase (VP) of contrast-enhanced computed tomography (CECT) were constructed and validated. From our hospital (First Affiliated Hospital of Zhejiang University, Zhejiang, P.R. China), 559 patients, who had histopathological confirmed MVI status, participated in this study. All preoperative CECT were collected, and the patients were randomly divided into training and validation cohorts at a ratio of 4:1. We proposed a novel transformer-based end-to-end DL model, named MVI-TR, which is a supervised learning method. MVI-TR can capture features automatically from radiomics and perform MVI preoperative assessments. In addition, a popular self-supervised learning method, the contrastive learning model, and the widely used residual networks (ResNets family) were constructed for fair comparisons. With an accuracy of 99.1%, a precision of 99.3%, an area under the curve (AUC) of 0.98, a recalling rate of 98.8%, and an F1-score of 99.1% in the training cohort, MVI-TR achieved superior outcomes. Additionally, the validation cohort's MVI status prediction had the best accuracy (97.2%), precision (97.3%), AUC (0.935), recalling rate (93.1%), and F1-score (95.2%). MVI-TR outperformed other models for predicting MVI status, and showed great preoperative predictive value for early-stage HCC patients.

Comparison of anthropometric indices for predicting the risk of metabolic syndrome and its components in Chinese adults: a prospective, longitudinal study.

OBJECTIVES: Our study aimed to distinguish the ability of anthropometric indices to assess the risk of metabolic syndrome (MetS). DESIGN: Prospective cohort study. SETTING: Shenyang, China. PARTICIPANTS: A total of 379 residents aged between 40 and 65 were enrolled. 253 of them were free of MetS and had been followed up for 4.5 years. METHODS: At baseline, all the participants underwent a thorough medical examination. A variety of anthropometric parameters were measured and calculated, including waist circumference (WC), body mass index (BMI), a body shape index (ABSI), abdominal volume index (AVI), body adiposity index, body roundness index, conicity index, waist-to-hip ratio and visceral adiposity index (VAI). After 4.5 year follow-up, we re-examined whether participants were suffering from MetS. A receiver operating characteristic (ROC) curve was applied to examine the potential of the above indices to identify the status and risk of MetS. OUTCOMES: Occurrence of MetS. RESULTS: At baseline, 33.2% participants suffered from MetS. All of the anthropometric indices showed clinical significance, and VAI was superior to the other indices as it was found to have the largest area under the ROC curve. After a 4.5 year follow-up, 37.8% of men and 23.9% of women developed MetS. ROC curve analysis suggested that baseline BMI was the strongest predictor of MetS for men (0.77 (0.68-0.85)), and AVI was the strongest for women (0.72 (0.64-0.79)). However, no significant difference was observed between WC and both indices. In contrast, the baseline ABSI did not predict MetS in both genders. CONCLUSIONS: The present study indicated that these different indices derived from anthropometric parameters have different discriminatory abilities for MetS. Although WC did not have the largest area under the ROC curve for diagnosing and predicting MetS, it may remain a better index of MetS status and risk because of its simplicity and wide use.

The correlation between serum free thyroxine and regression of dyslipidemia in adult males: A 4.5-year prospective study.

Elevated free thyroxine (FT4) levels may play a protective role in development of dyslipidemia. However, few prospective studies have been performed to definite the effects of thyroid hormones on the improvement of dyslipidemia and its components. Thus, this study aims to clarify the association between thyroid hormones within normal range and reversal of dyslipidemia in the absence of intervention.A prospective analysis including 134 adult males was performed between 2010 and 2014. Anthropometric parameters, thyroid function, and lipid profile were measured at baseline and during follow-up. Logistic regression and receiver operating characteristic (ROC) analysis were conducted to identify the variables in forecasting the reversal of dyslipidemia and its components.During 4.5-year follow-up, 36.6% (49/134) patients resolved their dyslipidemia status without drug intervention. Compared with the continuous dyslipidemia group, subjects in reversal group had elevated FT4 and high-density lipoprotein cholesterol (HDL-C) levels, as well as decreased total cholesterol (TC), triglycerides (TG), and low-density lipoprotein cholesterol (LDL-C) levels at baseline. Furthermore, baseline FT4 is negatively associated with the change percentages of TG (r = -0.286, P = .001), while positively associated with HDL-C (r = 0.227, P = .008). However, no correlation of lipid profile change percentages with FT3 and TSH were observed. Furthermore, the improving effects of baseline FT4 on dyslipidemia, high TG, and low HDL-C status were still observed after multivariable adjustment. In ROC analysis, areas under curve (AUCs) for FT4 in predicting the reversal of dyslipidemia, high TG, and low HDL-C were 0.666, 0.643, and 0.702, respectively (P = .001 for dyslipidemia, .018 for high TG, and .001 for low HDL-C).Higher FT4 value within normal range may ameliorate the dyslipidemia, especially high TG and low HDL-C status, in males without drug intervention. This suggests that a more flexible lipid-lowering therapy may be appropriate for patients with high-normal FT4.