Phospholipid metabolism-related genotypes of PLA2R1 and CERS4 contribute to nonobese MASLD.

BACKGROUND: Abnormal phospholipid metabolism is linked to metabolic dysfunction-associated steatotic liver disease (MASLD) development and progression. We aimed to clarify whether genetic variants of phospholipid metabolism modify these relationships. METHODS: This case-control study consecutively recruited 600 patients who underwent MRI-based proton density fat fraction examination (240 participants with serum metabonomics analysis, 128 biopsy-proven cases) as 3 groups: healthy control, nonobese MASLD, and obese MASLD, (n = 200 cases each). Ten variants of phospholipid metabolism-related genes [phospholipase A2 Group VII rs1805018, rs76863441, rs1421378, and rs1051931; phospholipase A2 receptor 1 (PLA2R1) rs35771982, rs3828323, and rs3749117; paraoxonase-1 rs662 and rs854560; and ceramide synthase 4 (CERS4) rs17160348)] were genotyped using SNaPshot. RESULTS: The T-allele of CERS4 rs17160348 was associated with a higher risk of both obese and nonobese MASLD (OR: 1.95, 95% CI: 1.20-3.15; OR: 1.76, 95% CI: 1.08-2.86, respectively). PLA2R1 rs35771982-allele is a risk factor for nonobese MASLD (OR: 1.66, 95% CI: 1.11-1.24), moderate-to-severe steatosis (OR: 3.24, 95% CI: 1.96-6.22), and steatohepatitis (OR: 2.61, 95% CI: 1.15-3.87), while the paraoxonase-1 rs854560 T-allele (OR: 0.50, 95% CI: 0.26-0.97) and PLA2R1 rs3749117 C-allele (OR: 1.70, 95% CI: 1.14-2.52) are closely related to obese MASLD. After adjusting for sphingomyelin level, the effect of the PLA2R1 rs35771982CC allele on MASLD was attenuated. Furthermore, similar effects on the association between the CERS4 rs17160348 C allele and MASLD were observed for phosphatidylcholine, phosphatidic acid, sphingomyelin, and phosphatidylinositol. CONCLUSIONS: The mutations in PLA2R1 rs35771982 and CERS4 rs17160348 presented detrimental impact on the risk of occurrence and disease severity in nonobese MASLD through altered phospholipid metabolism.

Artificial intelligence for diagnosis and prognosis prediction of natural killer/T cell lymphoma using magnetic resonance imaging.

Accurate diagnosis and prognosis prediction are conducive to early intervention and improvement of medical care for natural killer/T cell lymphoma (NKTCL). Artificial intelligence (AI)-based systems are developed based on nasopharynx magnetic resonance imaging. The diagnostic systems achieve areas under the curve of 0.905-0.960 in detecting malignant nasopharyngeal lesions and distinguishing NKTCL from nasopharyngeal carcinoma in independent validation datasets. In comparison to human radiologists, the diagnostic systems show higher accuracies than resident radiologists and comparable ones to senior radiologists. The prognostic system shows promising performance in predicting survival outcomes of NKTCL and outperforms several clinical models. For patients with early-stage NKTCL, only the high-risk group benefits from early radiotherapy (hazard ratio = 0.414 vs. late radiotherapy; 95% confidence interval, 0.190-0.900, p = 0.022), while progression-free survival does not differ in the low-risk group. In conclusion, AI-based systems show potential in assisting accurate diagnosis and prognosis prediction and may contribute to therapeutic optimization for NKTCL.

A novel multidisciplinary machine learning approach based on clinical, imaging, colonoscopy, and pathology features for distinguishing intestinal tuberculosis from Crohn's disease.

OBJECTIVES: Differentiating intestinal tuberculosis (ITB) from Crohn's disease (CD) remains a diagnostic dilemma. Misdiagnosis carries potential grave implications. We aim to establish a multidisciplinary-based model using machine learning approach for distinguishing ITB from CD. METHODS: Eighty-two patients including 25 patients with ITB and 57 patients with CD were retrospectively recruited (54 in training cohort and 28 in testing cohort). The region of interest (ROI) for the lesion was delineated on magnetic resonance enterography (MRE) and colonoscopy images. Radiomic features were extracted by least absolute shrinkage and selection operator regression. Pathological feature was extracted automatically by deep-learning method. Clinical features were filtered by logistic regression analysis. Diagnostic performance was evaluated by receiver operating characteristic (ROC) curve and decision curve analysis (DCA). Delong's test was applied to compare the efficiency between the multidisciplinary-based model and the other four single-disciplinary-based models. RESULTS: The radiomics model based on MRE features yielded an AUC of 0.87 (95% confidence interval [CI] 0.68-0.96) on the test data set, which was similar to the clinical model (AUC, 0.90 [95% CI 0.71-0.98]) and higher than the colonoscopy radiomics model (AUC, 0.68 [95% CI 0.48-0.84]) and pathology deep-learning model (AUC, 0.70 [95% CI 0.49-0.85]). Multidisciplinary model, integrating 3 clinical, 21 MRE radiomic, 5 colonoscopy radiomic, and 4 pathology deep-learning features, could significantly improve the diagnostic performance (AUC of 0.94, 95% CI 0.78-1.00) on the bases of single-disciplinary-based models. DCA confirmed the clinical utility. CONCLUSIONS: Multidisciplinary-based model integrating clinical, MRE, colonoscopy, and pathology features was useful in distinguishing ITB from CD.

Development and validation of a deep learning radiomics model with clinical-radiological characteristics for the identification of occult peritoneal metastases in patients with pancreatic ductal adenocarcinoma.

BACKGROUND: Occult peritoneal metastases (OPM) in patients with pancreatic ductal adenocarcinoma (PDAC) are frequently overlooked during imaging. The authors aimed to develop and validate a computed tomography (CT)-based deep learning-based radiomics (DLR) model to identify OPM in PDAC before treatment. METHODS: This retrospective, bicentric study included 302 patients with PDAC (training: n =167, OPM-positive, n =22; internal test: n =72, OPM-positive, n =9: external test, n =63, OPM-positive, n =9) who had undergone baseline CT examinations between January 2012 and October 2022. Handcrafted radiomics (HCR) and DLR features of the tumor and HCR features of peritoneum were extracted from CT images. Mutual information and least absolute shrinkage and selection operator algorithms were used for feature selection. A combined model, which incorporated the selected clinical-radiological, HCR, and DLR features, was developed using a logistic regression classifier using data from the training cohort and validated in the test cohorts. RESULTS: Three clinical-radiological characteristics (carcinoembryonic antigen 19-9 and CT-based T and N stages), nine HCR features of the tumor, 14 DLR features of the tumor, and three HCR features of the peritoneum were retained after feature selection. The combined model yielded satisfactory predictive performance, with an area under the curve (AUC) of 0.853 (95% CI: 0.790-0.903), 0.845 (95% CI: 0.740-0.919), and 0.852 (95% CI: 0.740-0.929) in the training, internal test, and external test cohorts, respectively (all P <0.05). The combined model showed better discrimination than the clinical-radiological model in the training (AUC=0.853 vs. 0.612, P <0.001) and the total test (AUC=0.842 vs. 0.638, P <0.05) cohorts. The decision curves revealed that the combined model had greater clinical applicability than the clinical-radiological model. CONCLUSIONS: The model combining CT-based DLR and clinical-radiological features showed satisfactory performance for predicting OPM in patients with PDAC.

Predicting One-year Recurrence of HCC based on Gadoxetic Acid-enhanced MRI by Machine Learning Models.

OBJECTIVE: Accurate prediction of recurrence risk after resction in patients with Hepatocellular Carcinoma (HCC) may help to individualize therapy strategies. This study aimed to develop machine learning models based on preoperative clinical factors and multiparameter Magnetic Resonance Imaging (MRI) characteristics to predict the 1-year recurrence after HCC resection. METHODS: Eighty-two patients with single HCC who underwent surgery were retrospectively analyzed. All patients underwent preoperative gadoxetic acidenhanced MRI examination. Preoperative clinical factors and MRI characteristics were collected for feature selection. Least Absolute Shrinkage and Selection Operator (LASSO) was applied to select the optimal features for predicting postoperative 1-year recurrence of HCC. Four machine learning algorithms, Multilayer Perception (MLP), random forest, support vector machine, and k-nearest neighbor, were used to construct the predictive models based on the selected features. A Receiver Operating Characteristic (ROC) curve was used to assess the performance of each model. RESULTS: Among the enrolled patients, 32 patients experienced recurrences within one year, while 50 did not. Tumor size, peritumoral hypointensity, decreasing ratio of liver parenchyma T1 value (ΔT1), and α-fetoprotein (AFP) levels were selected by using LASSO to develop the machine learning models. The area under the curve (AUC) of each model exceeded 0.72. Among the models, the MLP model showed the best performance with an AUC, accuracy, sensitivity, and specificity of 0.813, 0.742, 0.570, and 0.853, respectively. CONCLUSION: Machine learning models can accurately predict postoperative 1-year recurrence in patients with HCC, which may help to provide individualized treatment.

Quantitative assessment of brown adipose tissue whitening in a high-fat-diet murine model using synthetic magnetic resonance imaging.

Purpose: This study aimed to quantitatively evaluate the whitening process of brown adipose tissue (BAT) in mice using synthetic magnetic resonance imaging (SyMRI) and analyzed the correlation between SyMRI quantitative measurements of BAT and serum lipid profiles. Methods: Fifteen C57BL/6 mice were divided into three groups and fed different diets as follows: normal chow diet for 12 weeks, NCD group; high-fat diet (HFD) for 12 weeks, HFD-12w group; and HFD for 36 weeks, HFD-36w group. Mice were scanned using 3.0 T SyMRI. T1 and T2 values of BAT and interscapular BAT (iBAT) volume were measured. After sacrifice, the body weight of mice, lipid profiles, BAT morphology, and uncoupling protein 1 (UCP1) levels were determined. Statistical analysis was performed using one-way analysis of variance or Kruskal-Wallis test followed by Bonferroni correction for pairwise comparisons. Bonferroni-adjusted significance level was set at P < 0.017 (alpha: 0.05/3 = 0.017). Results: T2 values of BAT in the HFD-12w group were significantly higher than those in the NCD group (P < 0.001), and those in the HFD-36w group were significantly higher than those in the other two groups (both P < 0.001). The iBAT volume in the HFD-36w group was significantly higher than that in the HFD-12w (P = 0.013) and NCD groups (P = 0.005). T2 values of BAT and iBAT volume were significantly correlated with serum lipid profiles and mouse body weight. Conclusions: SyMRI can noninvasively evaluate the whitening process of BAT using T2 values and iBAT volume, thereby facilitating the visualization of the whitening process.

Hepatic Pecoma versus Hepatocellular Carcinoma In The Noncirrhotic Liver on Gd-EOB-DTPA-Enhanced MRI: A Diagnostic Challenge.

AIM: Hepatic perivascular epithelioid cell tumors (PEComa) often mimic hepatocellular carcinoma (HCC) in patients without cirrhosis. This study aimed to develop a nomogram using imaging characteristics on Gd-EOB-DTPA-enhanced MRI and to distinguish PEComa from HCC in a noncirrhotic liver. METHODS: Forty patients with non-cirrhotic Gd-EOB-DTPA-enhanced magnetic resonance imaging(MRI) were included in our study. A multivariate logistic regression model was used to select significant variables to distinguish PEComa from HCC. A nomogram was developed based on the regression model. The performance of the nomogram was assessed with respect to the ROC curve and calibration curve. Decision curve analysis (DCA) was performed to evaluate the clinical usefulness of the nomogram. RESULTS: Two significant predictors were identified: the appearance of an early draining vein and the T1D value of tumors. The ROC curve showed that the area under the curve (AUC) of the model to predict the risk of PEComa was 0.91 (95% CI: 0.80~1) and showed that the model had high specificity (92.3%) and sensitivity (88.9%). The nomogram incorporating these two predictors showed favorable calibration, which was validated using 1000 resampling procedures, and the corrected C-index of this model was 0.90. Furthermore, DCA analysis showed that the model had clinical practicability. CONCLUSION: In conclusion, the nomogram model showed favorable predictive accuracy for distinguishing PEComa from HCC in non-cirrhotic patients and may aid in clinical decision-making.

Deep learning for differentiation of osteolytic osteosarcoma and giant cell tumor around the knee joint on radiographs: a multicenter study.

OBJECTIVES: To develop a deep learning (DL) model for differentiating between osteolytic osteosarcoma (OS) and giant cell tumor (GCT) on radiographs. METHODS: Patients with osteolytic OS and GCT proven by postoperative pathology were retrospectively recruited from four centers (center A, training and internal testing; centers B, C, and D, external testing). Sixteen radiologists with different experiences in musculoskeletal imaging diagnosis were divided into three groups and participated with or without the DL model's assistance. DL model was generated using EfficientNet-B6 architecture, and the clinical model was trained using clinical variables. The performance of various models was compared using McNemar's test. RESULTS: Three hundred thirty-three patients were included (mean age, 27 years ± 12 [SD]; 186 men). Compared to the clinical model, the DL model achieved a higher area under the curve (AUC) in both the internal (0.97 vs. 0.77, p = 0.008) and external test set (0.97 vs. 0.64, p < 0.001). In the total test set (including the internal and external test sets), the DL model achieved higher accuracy than the junior expert committee (93.1% vs. 72.4%; p < 0.001) and was comparable to the intermediate and senior expert committee (93.1% vs. 88.8%, p = 0.25; 87.1%, p = 0.35). With DL model assistance, the accuracy of the junior expert committee was improved from 72.4% to 91.4% (p = 0.051). CONCLUSION: The DL model accurately distinguished osteolytic OS and GCT with better performance than the junior radiologists, whose own diagnostic performances were significantly improved with the aid of the model, indicating the potential for the differential diagnosis of the two bone tumors on radiographs. CRITICAL RELEVANCE STATEMENT: The deep learning model can accurately distinguish osteolytic osteosarcoma and giant cell tumor on radiographs, which may help radiologists improve the diagnostic accuracy of two types of tumors. KEY POINTS: • The DL model shows robust performance in distinguishing osteolytic osteosarcoma and giant cell tumor. • The diagnosis performance of the DL model is better than junior radiologists'. • The DL model shows potential for differentiating osteolytic osteosarcoma and giant cell tumor.

Prediction of immunocyte infiltration and prognosis in postoperative hepatitis B virus-related hepatocellular carcinoma patients using magnetic resonance imaging.

Background: The immune microenvironment (IME) is closely associated with prognosis and therapeutic response of hepatitis B virus-related hepatocellular carcinoma (HBV-HCC). Multi-parametric magnetic resonance imaging (MRI) enables non-invasive assessment of IME and predicts prognosis in HBV-HCC. We aimed to construct an MRI prediction model of the immunocyte-infiltration subtypes and explore its prognostic significance. Methods: HBV-HCC patients at the First Affiliated Hospital of Sun Yat-sen University (Guangzhou, China) with radical surgery (between 1 October and 30 December 2021) were prospectively enrolled. Patients with pathologically proven HCC (between 1 December 2013 and 30 October 2019) were retrospectively enrolled. Pearson correlation analysis was used to examine the relationship between the immunocyte-infiltration counts and MRI parameters. An MRI prediction model of immunocyte-infiltration subtypes was constructed in prospective cohort. Kaplan-Meier survival analysis was used to analyse its prognostic significance in the retrospective cohort. Results: Twenty-four patients were prospectively enrolled to construct the MRI prediction model. Eighty-nine patients were retrospectively enrolled to determine its prognostic significance. MRI parameters (relative enhancement, ratio of the apparent diffusion coefficient value of tumoral region to peritumoral region [rADC], T1 value) correlated significantly with the immunocyte-infiltration counts (leukocytes, T help cells, PD1+Tc cells, B lymphocytes). rADC differed significantly between high and low immunocyte-infiltration groups (1.47 ± 0.36 vs 1.09 ± 0.25, P = 0.009). The area under the curve of the MRI model was 0.787 (95% confidence interval 0.587-0.987). Based on the MRI model, the recurrence-free time was longer in the high immunocyte-infiltration group than in the low immunocyte-infiltration group (P = 0.026). Conclusions: MRI is a non-invasive method for assessing the IME and immunocyte-infiltration subtypes, and predicting prognosis in post-operative HBV-HCC patients.

CT-based radiomics signature of visceral adipose tissue and bowel lesions for identifying patients with Crohn's disease resistant to infliximab.

PURPOSE: To develop a CT-based radiomics model combining with VAT and bowel features to improve the predictive efficacy of IFX therapy on the basis of bowel model. METHODS: This retrospective study included 231 CD patients (training cohort, n = 112; internal validation cohort, n = 48; external validation cohort, n = 71) from two tertiary centers. Machine-learning VAT model and bowel model were developed separately to identify CD patients with primary nonresponse to IFX. A comprehensive model incorporating VAT and bowel radiomics features was further established to verify whether CT features extracted from VAT would improve the predictive efficacy of bowel model. Area under the curve (AUC) and decision curve analysis were used to compare the prediction performance. Clinical utility was assessed by integrated differentiation improvement (IDI). RESULTS: VAT model and bowel model exhibited comparable performance for identifying patients with primary nonresponse in both internal (AUC: VAT model vs bowel model, 0.737 (95% CI, 0.590-0.854) vs. 0.832 (95% CI, 0.750-0.896)) and external validation cohort [AUC: VAT model vs. bowel model, 0.714 (95% CI, 0.595-0.815) vs. 0.799 (95% CI, 0.687-0.885)), exhibiting a relatively good net benefit. The comprehensive model incorporating VAT into bowel model yielded a satisfactory predictive efficacy in both internal (AUC, 0.840 (95% CI, 0.706-0.930)) and external validation cohort (AUC, 0.833 (95% CI, 0.726-0.911)), significantly better than bowel alone (IDI = 4.2% and 3.7% in internal and external validation cohorts, both p < 0.05). CONCLUSION: VAT has an effect on IFX treatment response. It improves the performance for identification of CD patients at high risk of primary nonresponse to IFX therapy with selected features from RM. CRITICAL RELEVANCE STATEMENT: Our radiomics model (RM) for VAT-bowel analysis captured the pathophysiological changes occurring in VAT and whole bowel lesion, which could help to identify CD patients who would not response to infliximab at the beginning of therapy. KEY POINTS: • Radiomics signatures with VAT and bowel alone or in combination predicting infliximab efficacy. • VAT features contribute to the prediction of IFX treatment efficacy. • Comprehensive model improved the performance compared with the bowel model alone.

Robustly federated learning model for identifying high-risk patients with postoperative gastric cancer recurrence.

The prediction of patient disease risk via computed tomography (CT) images and artificial intelligence techniques shows great potential. However, training a robust artificial intelligence model typically requires large-scale data support. In practice, the collection of medical data faces obstacles related to privacy protection. Therefore, the present study aims to establish a robust federated learning model to overcome the data island problem and identify high-risk patients with postoperative gastric cancer recurrence in a multicentre, cross-institution setting, thereby enabling robust treatment with significant value. In the present study, we collect data from four independent medical institutions for experimentation. The robust federated learning model algorithm yields area under the receiver operating characteristic curve (AUC) values of 0.710, 0.798, 0.809, and 0.869 across four data centres. Additionally, the effectiveness of the algorithm is evaluated, and both adaptive and common features are identified through analysis.

Quantitative assessment of inflammation and evaluation of spatial heterogeneity for non-alcoholic fatty liver disease in mice based on iron-adjustive T1.

Background: A sensitive and non-invasive method is necessary to diagnose non-alcoholic fatty liver disease (NAFLD). We explored the iron-adjustive T1 (aT1) ability to quantify the degree of liver inflammation and evaluate the spatial heterogeneity. Methods: Male C57BL/6J mice were randomly categorized as the NAFLD model (n=40), NAFLD-related liver cirrhosis model (n=20), and normal mice (n=10). T1 and T2* maps were acquired using a 3.0T scanner of magnetic resonance imaging (MRI) and aT1 maps through post-processing corrected iron's effect on T1 using T2*. Pathological changes in the left and right liver lobes were assessed using the Non-alcoholic Steatohepatitis-Clinical Research Network scoring system, though hepatic ballooning lesion were rare in models. Spearman's and partial correlation analyses were used to evaluate correlations, and the receiver operating characteristic curve was used to analyze the diagnostic performance. Results: aT1 was highly correlated with NAFLD activity score (NAS) (r=0.747, P<0.001) but not with the fibrosis stage when adjusted by NAS (r=-0.135, P=0.147). The area under the curve (AUC) of the aT1 value distinguishing groups with 0< NAS <4 and NAS ≥4 was 0.802. On analyzing the histogram features of aT1, the entropy, interquartile range, range, and variance were significantly different between the groups with 0< NAS <4 and NAS ≥4 (P<0.05). The entropy was the risk factor of NAS ≥4. Conclusions: aT1 could help evaluate the inflammatory activity in NAFLD mice unaffected by mild fibrosis, and the higher the degree of inflammation, the higher the heterogeneity of the aT1 map.

Dual-energy CT improves differentiation of non-hypervascular pancreatic neuroendocrine neoplasms from CA 19-9-negative pancreatic ductal adenocarcinomas.

PURPOSE: To evaluate the utility of dual-energy CT (DECT) in differentiating non-hypervascular pancreatic neuroendocrine neoplasms (PNENs) from pancreatic ductal adenocarcinomas (PDACs) with negative carbohydrate antigen 19-9 (CA 19-9). METHODS: This retrospective study included 26 and 39 patients with pathologically confirmed non-hypervascular PNENs and CA 19-9-negative PDACs, respectively, who underwent contrast-enhanced DECT before treatment between June 2019 and December 2021. The clinical, conventional CT qualitative, conventional CT quantitative, and DECT quantitative parameters of the two groups were compared using univariate analysis and selected by least absolute shrinkage and selection operator regression (LASSO) analysis. Multivariate logistic regression analyses were performed to build qualitative, conventional CT quantitative, DECT quantitative, and comprehensive models. The areas under the receiver operating characteristic curve (AUCs) of the models were compared using DeLong's test. RESULTS: The AUCs of the DECT quantitative (based on normalized iodine concentrations [nICs] in the arterial and portal venous phases: 0.918; 95% confidence interval [CI] 0.852-0.985) and comprehensive (based on tumour location and nICs in the arterial and portal venous phases: 0.966; 95% CI 0.889-0.995) models were higher than those of the qualitative (based on tumour location: 0.782; 95% CI 0.665-0.899) and conventional CT quantitative (based on normalized conventional CT attenuation in the arterial phase: 0.665; 95% CI 0.533-0.797; all P < 0.05) models. The DECT quantitative and comprehensive models had comparable performances (P = 0.076). CONCLUSIONS: Higher nICs in the arterial and portal venous phases were associated with higher blood supply improving the identification of non-hypervascular PNENs.

Computed tomography imaging phenotypes of hepatoblastoma identified from radiomics signatures are associated with the efficacy of neoadjuvant chemotherapy.

BACKGROUND: Though neoadjuvant chemotherapy has been widely used in the treatment of hepatoblastoma, there still lacks an effective way to predict its effect. OBJECTIVE: To characterize hepatoblastoma based on radiomics image features and identify radiomics-based lesion phenotypes by unsupervised machine learning, intended to build a classifier to predict the response to neoadjuvant chemotherapy. MATERIALS AND METHODS: In this retrospective study, we segmented the arterial phase images of 137 cases of pediatric hepatoblastoma and extracted the radiomics features using PyRadiomics. Then unsupervised k-means clustering was applied to cluster the tumors, whose result was verified by t-distributed stochastic neighbor embedding (t-SNE). The least absolute shrinkage and selection operator (LASSO) regression was used for feature selection, and the clusters were visually analyzed by radiologists. The correlations between the clusters, clinical and pathological parameters, and qualitative radiological features were analyzed. RESULTS: Hepatoblastoma was clustered into three phenotypes (homogenous type, heterogenous type, and nodulated type) based on radiomics features. The clustering results had a high correlation with response to neoadjuvant chemotherapy (P=0.02). The epithelial ratio and cystic components in radiological features were also associated with the clusters (P=0.029 and 0.008, respectively). CONCLUSIONS: This radiomics-based cluster system may have the potential to facilitate the precise treatment of hepatoblastoma. In addition, this study further demonstrated the feasibility of using unsupervised machine learning in a disease without a proper imaging classification system.

An Optimized Strategy Based on Conventional Ultrasound for Diagnosing Metabolic Dysfunction-Associated Steatotic Liver Disease.

The inherent drawbacks of the conventional B-mode ultrasound for metabolic dysfunction-associated steatotic liver disease (MASLD) are poorly understood. We aimed to investigate the impact factors and optimize the screening performance of ultrasound in MASLD. In a prospective pilot cohort recruited from July 2020 to January 2022, subjects who had undergone magnetic resonance imaging-based proton density fat fraction (MRI-PDFF), ultrasound, and laboratory test-based assessments were included in the deprivation cohort. A validation cohort including 426 patients with liver histologic assessments from five medical centers in South China was also recruited. A total of 1489 Chinese subjects were enrolled in the deprivation cohort, and ultrasound misdiagnosed 62.2% of the non-MASLD patients and failed to detect 6.1% of the MASLD patients. The number of metabolic dysfunction components and the alanine aminotransferase (ALT) level were associated with a missed diagnosis by ultrasound (OR = 0.67, 95% CI 0.55-0.82 p < 0.001; OR = 0.50, 95% CI 0.31-0.79, p = 0.003, respectively). Compared with ultrasound alone, the new strategy based on ultrasound, in combination with measurements of the number of metabolic dysfunction components and ALT and uric acid levels, significantly improved the AUROC both in the research cohort and the validation cohort (0.66 vs. 0.84, 0.83 vs. 0.92, respectively). The number of metabolic dysfunction components and ALT and uric acid levels improved the screening efficacy of ultrasound for MASLD.

Restoring skeletal muscle mass as an independent determinant of liver fat deposition improvement in MAFLD.

AIMS: Cross-sectional studies have demonstrated the association of skeletal muscle mass with metabolic-associated fatty liver disease (MAFLD), while longitudinal data are scarce. We aimed to explore the impact of changes in relative skeletal muscle mass on the MAFLD treatment response. METHODS: MAFLD patients undergoing magnetic resonance imaging-based proton density fat fraction for liver fat content (LFC) assessments and bioelectrical impedance analysis before and after treatment (orlistat, meal replacement, lifestyle modifications) were enrolled. Appendicular muscle mass (ASM) was adjusted by weight (ASM/W). RESULTS: Overall, 256 participants were recruited and divided into two groups: with an ASM/W increase (n=166) and without an ASM/W increase (n=90). There was a great reduction in LFC in the group with an ASM/W increase (16.9% versus 8.2%, P < 0.001). However, the change in LFC in the group without an ASM/W increase showed no significant difference (12.5% versus 15.0%, P > 0.05). △ASM/W Follow-up-Baseline [odds ratio (OR)=1.48, 95% confidence interval (CI) 1.05-2.07, P = 0.024] and △total fat mass (OR=1.45, 95% CI 1.12-1.87, P = 0.004) were independent predictors for steatosis improvement (relative reduction of LFC ≥ 30%). The subgroup analysis showed that, despite without weight loss, decrease in HOMA-IR (OR=6.21, 95% CI 1.28-30.13, P=0.023), △total fat mass Baseline -Follow-up (OR=3.48, 95% CI 1.95-6.21, P <0.001 and △ASM/W Follow-up-Baseline (OR=2.13, 95% CI 1.12-4.05, P=0.022) independently predicted steatosis improvement. CONCLUSIONS: ASM/W increase and loss of total fat mass benefit the resolution of liver steatosis, independent of weight loss for MAFLD.

Preoperative assessment of peripheral vascular invasion of pancreatic ductal adenocarcinoma based on high-resolution MRI.

OBJECTIVES: Preoperative imaging of vascular invasion is important for surgical resection of pancreatic ductal adenocarcinoma (PDAC). However, whether MRI and CT share the same evaluation criteria remains unclear. This study aimed to compare the diagnostic accuracy of high-resolution MRI (HR-MRI), conventional MRI (non-HR-MRI) and CT for PDAC vascular invasion. METHODS: Pathologically proven PDAC with preoperative HR-MRI (79 cases, 58 with CT) and non-HR-MRI (77 cases, 59 with CT) were retrospectively collected. Vascular invasion was confirmed surgically or pathologically. The degree of tumour-vascular contact, vessel narrowing and contour irregularity were reviewed respectively. Diagnostic criteria 1 (C1) was the presence of all three characteristics, and criteria 2 (C2) was the presence of any one of them. The diagnostic efficacies of different examination methods and criteria were evaluated and compared. RESULTS: HR-MRI showed satisfactory performance in assessing vascular invasion (AUC: 0.87-0.92), especially better sensitivity (0.79-0.86 vs. 0.40-0.79) than that with non-HR-MRI and CT. HR-MRI was superior to non-HR-MRI. C2 was superior to C1 on CT evaluation (0.85 vs. 0.79, P = 0.03). C1 was superior to C2 in the venous assessment using HR-MRI (0.90 vs. 0.87, P = 0.04) and in the arterial assessment using non-HR-MRI (0.69 vs. 0.68, P = 0.04). The combination of C1-assessed HR-MRI and C2-assessed CT was significantly better than that of CT alone (0.96 vs. 0.86, P = 0.04). CONCLUSIONS: HR-MRI more accurately assessed PDAC vascular invasion than conventional MRI and may contribute to operative decision-making. C1 was more applicable to MRI scans, and C2 to CT scans. The combination of C1-assessed HR-MRI and C2-assessed CT outperformed CT alone and showed the best efficacy in preoperative examination of PDAC.

Comparison of clinical efficacy between LAPS and ALPPS in the treatment of hepatitis B virus-related hepatocellular carcinoma.

Background: Insufficient post-operative future liver remnant (FLR) limits the feasibility of hepatectomy for patients. Staged hepatectomy is an effective surgical approach that can improve the resection rate of hepatocellular carcinoma (HCC). This study aimed to compare the safety and efficacy of laparoscopic microwave ablation and portal vein ligation for staged hepatectomy (LAPS) and classical associating liver partition and portal vein ligation for staged hepatectomy (ALPPS) in the treatment of hepatitis B virus (HBV)-related HCC. Methods: Clinical data of patients with HBV-related HCC who underwent LAPS or ALPPS in our institute between January 2017 and May 2022 were retrospectively analysed. Results: A total of 18 patients with HBV-related HCC were retrospectively analysed and divided into the LAPS group (n = 9) and ALPPS group (n = 9). Eight patients in the LAPS group and eight patients in the ALPPS group proceeded to a similar resection rate (88.9% vs 88.9%, P = 1.000). The patients undergoing LAPS had a lower total comprehensive complication index than those undergoing ALPPS but there was not a significant different between the two groups (8.66 vs 35.87, P = 0.054). The hypertrophy rate of FLR induced by ALPPS tended to be more rapid than that induced by LAPS (24.29 vs 13.17 mL/d, P = 0.095). The 2-year recurrence-free survival (RFS) was 0% for ALPPS and 35.7% for LAPS (P = 0.009), whereas the 2-year overall survival for ALPPS and LAPS was 33.3% and 100.0% (P = 0.052), respectively. Conclusions: LAPS tended to induce lower morbidity and FLR hypertrophy more slowly than ALPPS, with a comparable resection rate and better long-term RFS in HBV-related HCC patients.

Comparisons of Insulin Resistance- and Steatosis-Based Scores in Monitoring Metabolic Associated Fatty Liver Disease Treatment Response.

BACKGROUND: Quantitative measurements of liver fat contents (LFCs) by magnetic resonance imaging derived-proton density fat fraction (MRI-PDFF) are accurate but limited by availability, convenience, and expense in the surveillance of metabolic associated fatty liver (MAFLD). Insulin resistance (IR) and steatosis-associated serum indices are useful in screening for MAFLD, but their value in monitoring MAFLD with or without chronic hepatitis B virus (CHB) infection remains unclear and we aimed to evaluate these scores in predicting changes in LFC. METHODS: We conducted a prospective study between January 2015 and December 2021 with 620 consecutive participants with MAFLD (212 participants with CHB) who received a 24-week lifestyle intervention. The homeostasis model assessment of IR (HOMA-IR), HOMA2 index, glucose-insulin ratio, quantitative insulin sensitivity check index, fasting insulin resistance index, fatty liver index (FLI), hepatic steatosis index (HSI), liver fat score (LFS), visceral adiposity index, and triglycerides * glucose were calculated. RESULTS: When using endpoints such as LFS improvements of ≥5% or 10% or escalations of ≥5%, LFS had the highest area under the curve (AUC) values at all endpoints for MAFLD alone (0.756, 95% CI: 0.707-0.805; 0.761, 95% CI: 0.705-0.818; 0.807, 95% CI: 0.713-0.901, all p < 0.05, respectively). With CHB, the FLI (AUC = 0.750) and HIS (AUC = 0.770) exhibited the highest AUCs between the former two outcomes, respectively, but no score could predict LFC escalation of ≥5%. CONCLUSION: Among IR and steatosis scores, changes in LFC through lifestyle interventions can be captured with LFS possessing moderate precision but not in those with CHB.

Clinical Interpretability of Deep Learning for Predicting Microvascular Invasion in Hepatocellular Carcinoma by Using Attention Mechanism.

Preoperative prediction of microvascular invasion (MVI) is essential for management decision in hepatocellular carcinoma (HCC). Deep learning-based prediction models of MVI are numerous but lack clinical interpretation due to their "black-box" nature. Consequently, we aimed to use an attention-guided feature fusion network, including intra- and inter-attention modules, to solve this problem. This retrospective study recruited 210 HCC patients who underwent gadoxetate-enhanced MRI examination before surgery. The MRIs on pre-contrast, arterial, portal, and hepatobiliary phases (hepatobiliary phase: HBP) were used to develop single-phase and multi-phase models. Attention weights provided by attention modules were used to obtain visual explanations of predictive decisions. The four-phase fusion model achieved the highest area under the curve (AUC) of 0.92 (95% CI: 0.84-1.00), and the other models proposed AUCs of 0.75-0.91. Attention heatmaps of collaborative-attention layers revealed that tumor margins in all phases and peritumoral areas in the arterial phase and HBP were salient regions for MVI prediction. Heatmaps of weights in fully connected layers showed that the HBP contributed the most to MVI prediction. Our study firstly implemented self-attention and collaborative-attention to reveal the relationship between deep features and MVI, improving the clinical interpretation of prediction models. The clinical interpretability offers radiologists and clinicians more confidence to apply deep learning models in clinical practice, helping HCC patients formulate personalized therapies.