Search

Abstract Objectives To develop and externally validate a fully automated diagnostic convolutional neural network (CNN) model for cirrhosis based on liver MRI and serum biomarkers. Methods This multicenter retrospective study included consecutive patients receiving pathological evaluation of liver fibrosis stage and contrast-enhanced liver MRI between March 2010 and January 2024. On the training dataset, an MRI-based CNN model was constructed for cirrhosis against pathology, and then a combined model was developed integrating the CNN model and serum biomarkers. On the testing datasets, the area under the receiver operating characteristic curve (AUC) was computed to compare the diagnostic performance of the combined model with that of aminotransferase-to-platelet ratio index (APRI), fibrosis-4 index (FIB-4), and radiologists. The influence of potential confounders on the diagnostic performance was evaluated by subgroup analyses. Results A total of 1315 patients (median age, 54 years; 1065 men; training, n = 840) were included, 855 (65%) with pathological cirrhosis. The CNN model was constructed on pre-contrast T1- and T2-weighted imaging, and the combined model was developed integrating the CNN model, age, and eight serum biomarkers. On the external testing dataset, the combined model achieved an AUC of 0.86, which outperformed FIB-4, APRI and two radiologists (AUC: 0.67 to 0.73, all p

Abstract Objectives To investigate the utility of deep learning (DL) automated segmentation-based MRI radiomic features and clinical-radiological characteristics in predicting early recurrence after curative resection of single hepatocellular carcinoma (HCC). Methods This single-center, retrospective study included consecutive patients with surgically proven HCC who underwent contrast-enhanced MRI before curative hepatectomy from December 2009 to December 2021. Using 3D U-net-based DL algorithms, automated segmentation of the liver and HCC was performed on six MRI sequences. Radiomic features were extracted from the tumor, tumor border extensions (5 mm, 10 mm, and 20 mm), and the liver. A hybrid model incorporating the optimal radiomic signature and preoperative clinical-radiological characteristics was constructed via Cox regression analyses for early recurrence. Model discrimination was characterized with C-index and time-dependent area under the receiver operating curve (tdAUC) and compared with the widely-adopted BCLC and CNLC staging systems. Results Four hundred and thirty-four patients (median age, 52.0 years; 376 men) were included. Among all radiomic signatures, HCC with 5 mm tumor border ex tension and liver showed the optimal predictive performance (training set C-index, 0.696). By incorporating this radiomic signature, rim arterial phase hyperenhancement (APHE), and incomplete tumor “capsule,” a hybrid model demonstrated a validation set C-index of 0.706 and superior 2-year tdAUC (0.743) than both the BCLC (0.550; p < 0.001) and CNLC (0.635; p = 0.032) systems. This model stratified patients into two prognostically distinct risk strata (both datasets p < 0.001). Conclusion A preoperative imaging model incorporating the DL automated segmentation-based radiomic signature with rim APHE and incomplete tumor “capsule” accurately predicted early postsurgical recurrence of a single HCC. Critical relevance statement The DL automated segmentation-based MRI radiomic model with rim APHE and incomplete tumor “capsule” hold the potential to facilitate individualized risk estimation of postsurgical early recurrence in a single HCC. Key Points A hybrid model integrating MRI radiomic signature was constructed for early recurrence prediction of HCC. The hybrid model demonstrated superior 2-year AUC than the BCLC and CNLC systems. The model categorized the low-risk HCC group carried longer RFS. Graphical Abstract

Abstract Background Hepatocellular carcinoma (HCC) expressing cytokeratin (CK) 7 or CK19 has a cholangiocyte phenotype that stimulates HCC proliferation, metastasis, and sorafenib therapy resistance This study aims to noninvasively predict cholangiocyte phenotype-positive HCC and assess its prognosis after hepatectomy. Methods Between January 2010 and May 2022, preoperative contrast-enhanced MRI was performed on consecutive patients who underwent hepatectomy and had pathologically confirmed solitary HCC. Two abdominal radiologists separately assessed the MRI features. A predictive model for cholangiocyte phenotype HCC was created using logistic regression analysis and five-fold cross-validation. A receiver operating characteristic curve was used to calculate the model performance. Kaplan–Meier and log-rank methods were used to evaluate survival outcomes. Results In total, 334 patients were included in this retrospective study. Four contrast-enhanced MRI features, including “rim arterial phase hyperenhancement” (OR = 5.9, 95% confidence interval [CI]: 2.9–12.0, 10 points), “nodule in nodule architecture” (OR = 3.5, 95% CI: 2.1–5.9, 7 points), “non-smooth tumor margin” (OR = 1.6, 95% CI: 0.8–2.9, 3 points), and “non-peripheral washout” (OR = 0.6, 95% CI: 0.3–1.0, − 3 points), were assigned to the cholangiocyte phenotype HCC prediction model. The area under the curves for the training and independent validation set were 0.76 and 0.73, respectively. Patients with model-predicted cholangiocyte phenotype HCC demonstrated lower rates of recurrence-free survival (RFS) and overall survival (OS) after hepatectomy, with an estimated median RFS and OS of 926 vs. 1565 days (p

Rationale and objectives: To establish a diagnostic model based on contrast-enhanced magnetic resonance imaging (MRI) and clinical characteristics for diagnosing extrahepatic cholangiocarcinoma (eCCA). Materials and methods: From April 2014 to September 2021, consecutive patients with extrahepatic bile duct lesions who underwent contrast-enhanced MRI within 1 month before pathological examination were retrospectively enrolled. Two radiologists blinded to clinicopathological information independently evaluated MR images. Univariable and multivariable logistic regression analyses were performed to identify significant clinicoradiological features associated with eCCA, which were subsequently incorporated into a diagnostic model. Model performance was assessed using the area under the receiver operating characteristic curve (AUC), calibration curve, and decision curve. Results: A total of 182 patients (mean age, 60.8 ± 10.0 years, 117 men) were included, 144 (79 %) of whom had pathologically confirmed eCCA. Diffusion restriction (odds ratio [OR], 8.32; 95 % confidence interval [CI]: 2.88, 25.82; P

Key points EOB-MRI features help capture the characteristics of tumor biology and heterogeneity. EOB-MRI-based HCC differentiation score allowed accurate assessment of poor tumor differentiation preoperatively. This scoring system might be useful for prompting tailored treatment selection.

PurposeAs a coreceptor in Wnt and HGF signaling, glypican-3 (GPC-3) promotes the progression of tumor and is associated with a poor prognosis in hepatocellular carcinoma (HCC). GPC-3 has evolved as a target molecule in various immunotherapies, including chimeric antigen receptor T cell. However, its evaluation still relies on invasive histopathologic examination. Therefore, we aimed to develop an easy-to-use and noninvasive risk score integrating preoperative gadoxetic acid–enhanced magnetic resonance imaging (EOB-MRI) and clinical indicators to predict positive GPC-3 expression in HCC.Methods and materialsConsecutive patients with surgically-confirmed solitary HCC who underwent preoperative EOB-MRI between January 2016 and November 2021 were retrospectively included. EOB-MRI features were independently evaluated by two masked abdominal radiologists and the expression of GPC-3 was determined by two liver pathologists. On the training dataset, a predictive scoring system for GPC-3 was developed against pathology via logistical regression analysis. Model performances were characterized by computing areas under the receiver operating characteristic curve (AUCs).ResultsA total of 278 patients (training set, n=156; internal validation set, n=39; external validation set, n=83) with solitary HCC (208 [75%] with positive GPC-3 expression) were included. Serum alpha-fetoprotein >10 ng/ml (AFP, odds ratio [OR]=2.3, four points) and five EOB-MR imaging features, including tumor size >3.0cm (OR=0.5, -3 points), nonperipheral “washout” (OR=3.0, five points), infiltrative appearance (OR=9.3, 10 points), marked diffusion restriction (OR=3.3, five points), and iron sparing in solid mass (OR=0.2, -7 points) were significantly associated with positive GPC-3 expression. The optimal threshold of scoring system for predicting GPC-3 positive expression was 5.5 points, with AUC 0.726 and 0.681 on the internal and external validation sets, respectively.ConclusionBased on serum AFP and five EOB-MRI features, we developed an easy-to-use and noninvasive risk score which could accurately predict positive GPC-3 HCC, which may help identify potential responders for GPC-3-targeted immunotherapy.

ObjectiveEarly detection and diagnosis of hepatocellular carcinoma (HCC) is essential for prognosis; however, the imaging hallmarks for tumor detection and diagnosis has remained the same for years despite the use of many new immerging imaging methods. This study aimed to evaluate the detection performance of hepatic nodules in high risk patients using either hepatobiliary specific contrast (HBSC) agent or extracellular contrast agent (ECA), and further to compare the diagnostic performances for hepatocellular carcinoma (HCC) using different diagnostic criteria with the histopathological results as reference standard.MethodsThis prospective study included 247 nodules in 222 patients (mean age, 53.32 ± 10.84 years; range, 22–79 years). The detection performance and imaging features of each nodule were evaluated in all MR sequences by three experienced abdominal radiologists. The detection performance of each nodule on all MR sequences were compared and further the diagnostic performance of various diagnostic criteria were evaluated.ResultsFor those patients who underwent ECA-MRI, the conventional imaging hallmark of “AP + PVP and/or DP” was recommended, as 60.19% diagnostic sensitivity, 80.95% specificity and 100% lesion detection rate. Additionally, for those patients who underwent HBSC-MRI, the diagnostic criteria of “DWI + HBP” was recommended. This diagnostic criteria demonstrated, both in all tumor size and for nodules ≤2 cm, higher sensitivity (93.07 and 90.16%, all p 0.05, respectively) than that of the European Association for the Study of the Liver (EASL) criteria.ConclusionsDifferent abbreviated MR protocols were recommended for patients using either ECA or HBSC. These provided imaging settings demonstrated high lesion detection rate and diagnostic performance for HCC.

Purpose: To assess the performance of T1 mapping and residual liver volume (RLV) on Gd-EOBDTPA-enhanced MRI in pretreatment estimation of liver function in patients with liver tumors. Indocyanine green retention rate at 15 min (ICG R-15) was used as a reference standard.Methods: Ethical approval from the institutional review board and informed consent were obtained for this prospective study. We enrolled 155 patients with liver tumors who underwent pretreatment Gd-EOB-DTPA-enhanced MRI. T1 relaxation time before (T1-pre), 20 min after (T1-post) Gd-EOB-DTPA injection and RLV were measured. The absolute reduction (ΔT1) and reduction rate (ΔT1%) of T1 relaxation time, volume-assisted ΔT1 (ΔT1*RLV) and volume-assisted ΔT1% (ΔT1%*RLV) were calculated accordingly. The correlation of MR parameters with ICG R-15 was determined using Spearman's rank correlation analysis. Patients were classified into the normal liver function (NLF) group if their ICG R-15 levels were