US-based Sequential Algorithm Integrating an AI Model for Advanced Liver Fibrosis Screening.

Background Noninvasive tests can be used to screen patients with chronic liver disease for advanced liver fibrosis; however, the use of single tests may not be adequate. Purpose To construct sequential clinical algorithms that include a US deep learning (DL) model and compare their ability to predict advanced liver fibrosis with that of other noninvasive tests. Materials and Methods This retrospective study included adult patients with a history of chronic liver disease or unexplained abnormal liver function test results who underwent B-mode US of the liver between January 2014 and September 2022 at three health care facilities. A US-based DL network (FIB-Net) was trained on US images to predict whether the shear-wave elastography (SWE) value was 8.7 kPa or higher, indicative of advanced fibrosis. In the internal and external test sets, a two-step algorithm (Two-step#1) using the Fibrosis-4 Index (FIB-4) followed by FIB-Net and a three-step algorithm (Three-step#1) using FIB-4 followed by FIB-Net and SWE were used to simulate screening scenarios where liver stiffness measurements were not or were available, respectively. Measures of diagnostic accuracy were calculated using liver biopsy as the reference standard and compared between FIB-4, SWE, FIB-Net, and European Association for the Study of the Liver guidelines (ie, FIB-4 followed by SWE), along with sequential algorithms. Results The training, validation, and test data sets included 3067 (median age, 42 years [IQR, 33-53 years]; 2083 male), 1599 (median age, 41 years [IQR, 33-51 years]; 1124 male), and 1228 (median age, 44 years [IQR, 33-55 years]; 741 male) patients, respectively. FIB-Net obtained a noninferior specificity with a margin of 5% (P < .001) compared with SWE (80% vs 82%). The Two-step#1 algorithm showed higher specificity and positive predictive value (PPV) than FIB-4 (specificity, 79% vs 57%; PPV, 44% vs 32%) while reducing unnecessary referrals by 42%. The Three-step#1 algorithm had higher specificity and PPV compared with European Association for the Study of the Liver guidelines (specificity, 94% vs 88%; PPV, 73% vs 64%) while reducing unnecessary referrals by 35%. Conclusion A sequential algorithm combining FIB-4 and a US DL model showed higher diagnostic accuracy and improved referral management for all-cause advanced liver fibrosis compared with FIB-4 or the DL model alone. © RSNA, 2024 Supplemental material is available for this article. See also the editorial by Ghosh in this issue.

The value of liver stiffness measured by two-dimensional shear wave elastography for predicting symptomatic posthepatectomy liver failure in patients with hepatocellular carcinoma.

PURPOSE: To assess and compare the value of liver stiffness measurement (LSM) by two-dimensional shear wave elastography (2D-SWE) with the diagnosis of clinically significant portal hypertension (CSPH) and pathological examination in predicting symptomatic posthepatectomy liver failure (PHLF) in patients with hepatocellular carcinoma (HCC). METHOD: A total of 130 patients who underwent liver resection for HCC between August 2018 and July 2021 were enrolled. Preoperative assessments for LSM and other clinicopathological tests were performed in all patients. The performance of LSM, CSPH and fibrosis stage in predicting symptomatic PHLF was assessed and compared. Univariate and multivariate analyses were conducted on the risk factors for symptomatic PHLF. RESULTS: Symptomatic PHLF occurred in 40 patients (30.8%). The best LSM cutoff value for predicting symptomatic PHLF was 9.5 kPa. The areas under the receiver operating characteristic curve (AUCs) of LSM ≥ 9.5 kPa, fibrosis stage and CSPH for predicting symptomatic PHLF were 0.732 (95% CI: 0.638-0.826, p < 0.001), 0.655 (95% CI: 0.553-0.758, p = 0.005) and 0.594 (95% CI: 0.484-0.705, p = 0.086), respectively. The AUC of LSM ≥ 9.5 kPa was significantly higher than that of CSPH (p = 0.010), and was comparable to that of fibrosis stage (p = 0.073). Multivariate analysis identified LSM ≥ 9.5 kPa (p = 0.001), major hepatectomy (p = 0.007) and CSPH diagnosis (p = 0.040) as independent predictors of symptomatic PHLF. CONCLUSIONS: LSM by 2D-SWE was promising for predicting symptomatic PHLF in HCC patients. The predictive performance was higher than that of CSPH and comparable to that of pathological fibrosis stage.

Liver Stiffness Measured by Two-Dimensional Shear Wave Elastography for Predicting Symptomatic Post-hepatectomy Liver Failure in Patients with Hepatocellular Carcinoma.

OBJECTIVES: To evaluate the ability of liver stiffness (LS) measured by two-dimensional shear wave elastography (2D SWE) to predict symptomatic post-hepatectomy liver failure (SPHLF) in patients with hepatocellular carcinoma (HCC). METHODS: A total of 119 patients who underwent hepatectomy for HCC between August 2018 and July 2019 were enrolled. Preoperative assessments for LS and other clinicopathological tests were performed in all patients. Univariate and multivariate analyses were conducted for the risk factors of SPHLF. Further subgroup analysis was performed according to multivariate analysis results. RESULTS: SPHLF occurred in 38 patients (31.9%). The best cutoff value of LS for predicting SPHLF was 9.5 kPa. Multivariate analysis identified LS ≥ 9.5 kPa, greater Child-Turcotte-Pugh (CTP) grade, and major hepatectomy as independent predictors of SPHLF. Based on the extent of hepatectomy, CTP grade could stratify the risk of SPHLF in the minor hepatectomy group (12.2% vs. 100.0%, p = 0.001), whereas LS was superior in predicting SPHLF in the major hepatectomy group (18.9% vs. 72.4%, p < 0.001). In patients with CTP grade A, LS could further stratify the risks of SPHLF in both the minor and major hepatectomy groups (3.7% vs. 22.7%, p = 0.043; 17.6% vs. 70.4%, p < 0.001, respectively). CONCLUSIONS: LS measured using 2D SWE could predict SPHLF using the best cutoff value of 9.5 kPa. CTP grade was a stronger indicator of SPHLF in minor hepatectomy, whereas LS was more effective in selecting candidates for major hepatectomy. LS could further stratify the risk of SPHLF in CTP grade A patients, regardless of the extent of hepatectomy.

Histone Deacetylase 1 Regulates the Expression of Progesterone Receptor A During Human Parturition by Occupying the Progesterone Receptor A Promoter.

The functional withdrawal of progesterone is mediated by the enhanced expression ratio of the 2 progesterone receptor (PR) isoforms, PRA and PRB, and causes the pregnant human myometrium to switch from a quiet state to a state of excitation-contraction and subsequent laboring. However, the precise mechanisms responsible for alterations in PRA and PRB expression during human parturition have yet to be resolved. In the present study, we report that PRA expression was increased in myometrium samples during labor (P < .001), concomitant with reduced expression of histone deacetylase 1 (HDAC1; P < .01). These results were further confirmed in the laboratory using cultured primary myometrial cells to investigate the effects of HDAC1 knockdown or overexpression. Finally, we verified that HDAC1 downregulated PRA expression by binding to the promoter region of PRA as confirmed by chromatin immunoprecipitation assays (P < .01) and real-time polymerase chain reaction (P < .001). Therefore, the present study not only demonstrates the epigenetic mechanisms underlying human labor but also provides a potential clinical strategy with which to intervene and prevent labor disorders.