Three-dimensional MR Elastography Depicts Liver Inflammation, Fibrosis, and Portal Hypertension in Chronic Hepatitis B or C.

Background The value of measuring mechanical properties to categorize various pathophysiologic states of the liver is as yet undetermined in chronic hepatitis B (CHB) or C (CHC). Purpose To evaluate multiparametric three-dimensional (3D) MR elastography as a means of detecting early necroinflammation, distinguishing necroinflammation from fibrosis, and gauging the severity of portal hypertension (PH) in CHB or CHC. Materials and Methods From January 2015 to September 2019, participants with CHB or CHC were prospectively enrolled from a single institution and were divided into two groups: those with liver biopsy and no evidence of PH (group 1) and those with PH and a hepatic venous pressure gradient (HVPG) measurement (group 2). For group 3, healthy volunteers were separately recruited from a nearby community. Multiple viscoelastic parameters (shear stiffness [SS], storage modulus, loss modulus, and damping ratio [DR]) were determined at 3D MR elastography at 60 Hz, and multivariable logistic or linear regression analysis was used to assess associations of mechanical parameters with histologic scores and HVPG. Results A total of 155 participants (median age, 41 years [interquartile range, 32-48 years]; 85 women) were in group 1 (training set: n = 78, validation set: n = 77), 85 participants (median age, 57 years [interquartile range, 43-61 years]; 51 women) in group 2, and 60 healthy volunteers (median age, 49 years [interquartile range, 27-64 years]; 38 men) in group 3. The liver DR was higher in participants with necroinflammation (DR, 0.13 ± 0.03) versus those without (at liver fibrosis stage F0) (DR, 0.10 ± 0.02; P < .001). Liver DR and SS together performed well in the diagnosis of necroinflammation (area under the receiver operating characteristic curve [AUC], 0.88 [95% CI: 0.79, 0.96]) and the scoring of moderate to severe activity (AUC, 0.88 [95% CI: 0.81, 0.95]) in the validation data set. Liver DR (regression coefficient [ß] = -30.3 [95% CI: -58.0, -2.5]; P = .03) and splenic SS (ß = 2.3 [95% CI: 1.7, 2.9]; P < .001) were independently associated with HVPG. Conclusion Three-dimensional MR elastography may detect early necroinflammation, distinguish necroinflammation from liver fibrosis, and correlate with hepatic venous pressure gradient in chronic hepatitis B and C. © RSNA, 2021 Online supplemental material is available for this article. See also the editorial by Reeder in this issue.

Prediction of clinically relevant Pancreatico-enteric Anastomotic Fistulas after Pancreatoduodenectomy using deep learning of Preoperative Computed Tomography.

Rationale: Clinically relevant postoperative pancreatic fistula (CR-POPF) is among the most formidable complications after pancreatoduodenectomy (PD), heightening morbidity/mortality rates. Fistula Risk Score (FRS) is a well-developed predictor, but it is an intraoperative predictor and quantifies >50% patients as intermediate risk. Therefore, an accurate and easy-to-use preoperative index is desired. Herein, we test the hypothesis that quantitative analysis of contrast-enhanced computed tomography (CE-CT) with deep learning could predict CR-POPFs. Methods: A group of 513 patients underwent pancreatico-enteric anastomosis after PD at three institutions between 2006 and 2019 was retrospectively collected, and formed a training (70%) and a validation dataset (30%) randomly. A convolutional neural network was trained and generated a deep-learning score (DLS) to identify the patients with higher risk of CR-POPF preoperatively using CE-CT images, which was further externally tested in a prospective cohort collected from August 2018 to June 2019 at the fourth institution. The biological underpinnings of DLS were assessed using histomorphological data by multivariate linear regression analysis. Results: CR-POPFs developed in 95 patients (16.3%) in total. Compared to FRS, the DLS offered significantly greater predictability in training (AUC:0.85 [95% CI, 0.80-0.90] vs. 0.78 [95% CI, 0.72-0.84]; P = 0.03), validation (0.81 [95% CI, 0.72-0.89] vs. 0.76 [95% CI, 0.66-0.84], P = 0.05) and test (0.89 [95% CI, 0.79-0.96] vs. 0.73 [95% CI, 0.61-0.83], P < 0.001) cohorts. Especially in the challenging patients of intermediate risk (FRS: 3-6), the DLS showed significantly higher accuracy (training: 79.9% vs. 61.5% [P = 0.005]; validation: 70.3% vs. 56.3% [P = 0.04]; test: 92.1% vs. 65.8% [P = 0.013]). Additionally, DLS was independently associated with pancreatic fibrosis (coefficients: -0.167), main pancreatic duct (coefficients: -0.445) and remnant volume (coefficients: 0.138) in multivariate linear regression analysis (r2 = 0.512, P < 0.001). The user satisfaction score in the test cohort was 4 out of 5. Conclusions: Preoperative CT based deep-learning model provides a promising novel method for predicting CR-POPF occurrences after PD, especially at intermediate FRS risk level. This has a potential to be integrated into radiologic reporting system or incorporated into surgical planning software to accommodate the preferences of surgeons to optimize preoperative strategies, intraoperative decision-making, and even postoperative care.