To quantitatively compare the monoexponential, biexponential, and stretched‐exponential diffusion‐weighted imaging (DWI) models in differentiating benign from malignant solid hepatic lesions. The institutional review board approved this retrospective study and waived the informed consent requirement. A total of 188 patients with 288 hepatic lesions included 202 malignant lesions and 86 benign lesions were assessed (confirmed by pathology or clinical follow‐up for 6 months). All patients underwent hepatic 3.0‐T MRI, including multi‐b DWI that used 12 b values. The ADC, D_p, D_t, perfusion fraction (f_p), α, and DDC values for normal liver, benign liver lesions, and malignant liver lesions were calculated. Independent sample t tests were used for comparisons. The diagnostic performance of the parameters was evaluated using ROC analysis. The AUC value for each model was also calculated. The value of D_p was significantly lower in benign lesions than in normal hepatic parenchyma while others were significantly higher (P < .001). Whereas Values of D_t and α in malignant hepatic lesions were significantly higher than in normal hepatic parenchyma (P < .001), and the D_p value was significantly lower (P < .001). Values of ADC, f_p, DDC, and α for malignant hepatic lesions were significantly lower than those for benign hepatic lesions (P < .001). ROC analysis showed that the diagnostic value of the biexponential model of normal hepatic parenchyma vs benign hepatic lesions and normal hepatic parenchyma vs malignant hepatic lesions was high (0.946 and 0.876, respectively). In the differential diagnosis of benign and malignant hepatic lesions, DDC had the highest AUC value (0.819). The biexponential and stretched‐exponential DWI may provide additional information and improve the differential diagnosis of benign and malignant hepatic lesions compared with the monoexponential DWI.

Internal hernia (IH)-related surgical acute abdomen is not well understood because of the rarity of cases and underdiagnosis. This study was performed to further understand the clinicopathological features and multi-detector computed tomography (MDCT) findings of IH in cases confirmed by surgery. In all, 51 patients with a definite diagnosis of IH confirmed during surgical exploration from Feb. 2012 to Feb. 2018 in our hospital were included in this research. Medical records, including MDCT images and intra-operative findings, were collected retrospectively. In all, 39 and 12 cases were categorized as adhesive IH (76.5%) and non-adhesive IH (23.5%), respectively. Among the patients with adhesive IH, 73% had a history of abdominal or pelvic surgery. Additionally, the mesentery was the most common component of adhesive bands (64.1%). Congenital peritoneal abnormalities and gastrointestinal reconstruction were the main causes of non-adhesive IH.As a specific sign, the fat notch sign was much more common in adhesive IH than in non-adhesive IH (P = 0.023). Bowel wall thickening (P = 0.041), abnormal bowel wall enhancement (P = 0.006) and twisted bowels with the vessel swirl sign (P = 0.004) were indicators of bowel necrosis. Among all of the cases of IH, 34 (66.7%) were complicated by bowel necrosis, and 1 patient died. In conclusion, non-adhesive IH has different clinicopathological features and MDCT findings from those of adhesive IH. MDCT is a useful tool with high sensitivity for confirming IH and may help to guide the early treatment of IH.

Previous studies mostly use single-type features to establish a prediction model. We aim to develop a comprehensive prediction model that effectively identify patients with poor prognosis for single hepatocellular carcinoma (HCC) based on artificial intelligence (AI). Patients and methods: 236 single HCC patients were studied to establish a comprehensive prediction model. We collected the basic information of patients and used AI to extract the features of magnetic resonance (MR) images. The clinical model based on linear regression (LR) algorithm (AUC: 0.658, 95%CI: 0.5021-0.8137), the radiomics model and deep transfer learning (DTL) model based on light gradient-boosting machine (Light GBM) algorithm (AUC: 0.761, 95%CI: 0.6326-0.8886 and AUC: 0.784, 95%CI: 0.6587-0.9087, respectively) were the optimal prediction models. A comparison revealed that the integrated nomogram had the largest area under the receiver operating characteristic curve (AUC) (all P < 0.05). In the training cohort, the integrated nomogram was predictive of recurrence-free survival (RFS) as well as overall survival (OS) (C-index: 0.735 and 0.712, P < 0.001). In the test cohort, the integrated nomogram also can predict RFS and OS (C-index: 0.718 and 0.740, P < 0.001) in patients. The integrated nomogram composed of signatures in the prediction models can not only predict the postoperative recurrence of single HCC patients but also stratify the risk of OS after the operation.

A critical dilemma in post-transplant surveillance is determining when minor functional changes (subtle serum creatinine fluctuations or slow renal function decline) or ambiguous ultrasound findings (including mildly elevated resistive index or cortical echogenicity) warrant invasive biopsy and treatment modification. We aimed to develop a non-invasive integrated tool combining advanced diffusion MRI with functional biomarkers to stratify patients within this diagnostic gray zone. In this prospective study, 120 renal transplant recipients underwent multi-b-value diffusion-weighted imaging at 3.0 T within 48 h prior to an allograft biopsy. Quantitative parameters of six diffusion MRI models were extracted from renal cortex and medulla. Clinical indicators, including serum HCO₃-, were recorded. To establish a clear endpoint, patients were categorized into a Treatment-Changed group (presence of actionable active pathology, requiring modified therapies) and a Treatment-Unchanged group (normal or solely chronic/non-reversible lesions). Multivariable logistic regression identified independent predictors. Diagnostic performance was assessed using area under the curve (AUC) using repeated stratified 5-fold cross validation with 10 repeats and bootstrap resampling. Kaplan–Meier analysis assessed the association between model-based risk and subsequent graft functional decline, defined as a 30% or greater decrease in estimated glomerular filtration rate (eGFR) from baseline. The cortical distributed diffusion coefficient (DDC) and serum HCO₃-, emerged as independent predictors of treatment-changed group. The integrated model achieved an AUC of 0.941, significantly outperforming the standard clinical reference model (eGFR, proteinuria, and ultrasound; AUC 0.563). Net reclassification improvement (0.479) demonstrated the model correctly reclassified 45.6% of patients. Furthermore, model-derived high-risk status significantly predicted long-term graft functional decline (log-rank p = 0.005). This integrated multiparametric protocol provides promising preliminary decision support for renal allograft surveillance. By noninvasively identifying the potential presence of actionable active pathology, this preliminary model may help optimize biopsy referrals and stratify patients who potentially require treatment modification. However, given the single-centre design, external validation is required before clinical implementation.