Multimodal CT for Predicting Microvascular Invasion in Solitary cHCC-CCA: Dual-Center External Validation

Wu-Yuan Liu; Yu-Chen Wei; Qiao-Fang Chen; Yuan-Fang Tao; Lu Chen; Jin-Yuan Liao

doi:10.1016/j.acra.2026.01.053

Multimodal CT for Predicting Microvascular Invasion in Solitary cHCC-CCA: Dual-Center External Validation

Acad Radiol. 2026 Feb 20:S1076-6332(26)00082-6. doi: 10.1016/j.acra.2026.01.053. Online ahead of print.

Authors

Wu-Yuan Liu¹, Yu-Chen Wei², Qiao-Fang Chen³, Yuan-Fang Tao⁴, Lu Chen⁴, Jin-Yuan Liao⁵

Affiliations

¹ Department of Radiology, The First Affiliated Hospital of Guangxi Medical University, Nanning, China (W.-Y.L.,Y.-C.W., Q.-F.C., Y.-F.T., L.C., J.-Y.L.); Department of Radiology, People's Hospital of Luchuan, Yulin, Guangxi, China (W.-Y.L.).
² Department of Radiology, The First Affiliated Hospital of Guangxi Medical University, Nanning, China (W.-Y.L.,Y.-C.W., Q.-F.C., Y.-F.T., L.C., J.-Y.L.); Department of Radiology, Guangxi Hospital Division of the First Affiliated Hospital, Sun-Yat-Sen University, China (Y.-C.W.).
³ Department of Radiology, The First Affiliated Hospital of Guangxi Medical University, Nanning, China (W.-Y.L.,Y.-C.W., Q.-F.C., Y.-F.T., L.C., J.-Y.L.); Department of Radiology, Affiliated Hospital of Youjiang Medical University for Nationalities, China (Q.-F.C.).
⁴ Department of Radiology, The First Affiliated Hospital of Guangxi Medical University, Nanning, China (W.-Y.L.,Y.-C.W., Q.-F.C., Y.-F.T., L.C., J.-Y.L.).
⁵ Department of Radiology, The First Affiliated Hospital of Guangxi Medical University, Nanning, China (W.-Y.L.,Y.-C.W., Q.-F.C., Y.-F.T., L.C., J.-Y.L.); Key Laboratory of Early Prevention and Treatment for Regional High Frequency Tumor (Guangxi Medical University), Ministry of Education, Nanning 530021, Guangxi, China (J.-Y.L.). Electronic address: liaojinyuan@gxmu.edu.cn.

PMID: 41723042
DOI: 10.1016/j.acra.2026.01.053

Abstract

Rationale and objectives: Preoperative prediction of microvascular invasion (MVI) in combined hepatocellular-cholangiocarcinoma (cHCC-CCA) remains difficult, and externally validated CT-based tools are scarce. To develop and externally validate a multimodal model for MVI prediction in solitary cHCC-CCA using portal venous-phase quantitative CT features combined with multiphasic CT semantic features, and to compare intratumoral, 10-mm peritumoral, and combined intratumoral + peritumoral segmentation strategies.

Materials and methods: This retrospective dual-center study included 184 patients with pathologically confirmed solitary cHCC-CCA who underwent contrast-enhanced CT within 1 month before resection (Center 1: n = 139; Center 2: n = 45). Center 1 was randomly split into training (n = 97) and internal test (n = 42) cohorts, and Center 2 served as an independent external validation cohort. Clinical variables and CT semantic features were assessed on multiphasic CT, whereas radiomics and deep learning features were extracted exclusively from portal venous-phase images using three segmentation strategies (intratumoral, 10-mm peritumoral, and combined intratumoral + peritumoral). Feature selection, hyperparameter tuning, and calibration were performed in the training cohort. Operating thresholds were selected using training-cohort out-of-fold (OOF) predictions to target a sensitivity around 0.80 and were then fixed for external validation. Model performance was evaluated in the external cohort using area under the receiver operating characteristic curve (AUC; 95% CI), calibration, and decision curve analysis, with SHapley Additive exPlanations (SHAP) used for interpretability.

Results: Interobserver agreement for key semantic features was almost perfect (κ = 0.81-0.84), and overall semantic agreement was high (mean κ = 0.84). Radiomics and deep learning features showed good reproducibility (ICCs > 0.80). In external validation, discrimination was moderate and consistent across segmentation strategies (AUC, 0.761-0.800). The 10-mm peritumoral strategy achieved the numerically highest AUC (0.800; 95% CI: 0.658-0.916) and high sensitivity at a prespecified sensitivity-oriented operating threshold; differences versus other strategies were modest and not statistically significant (all P > 0.05). SHAP analyses consistently highlighted rim arterial-phase hyperenhancement and widened perilesional enhancement as major contributors to MVI-positive predictions.

Conclusion: A multimodal approach combining portal venous-phase quantitative CT features with multiphasic semantic CT features enabled externally validated preoperative MVI risk estimation in solitary cHCC-CCA. Peritumoral modeling showed a consistent but modest numerical advantage without statistically proven superiority. Findings are limited by retrospective design, small external cohort size, and restricted population diversity; prospective multicenter validation is warranted to confirm its role as a decision-support tool for preoperative MVI risk stratification.

Keywords: CHCC-CCA; Deep learning; Microvascular invasion; Peritumoral segmentation; Radiomics.