AI Multimodal Model for Liver Cancer Diagnosis and Prognosis

NCT07658586 | Active Not Recruiting

• 1 other identifier: KY20260007
• Study Type: observational
• Target: 600
• Locations: 1 country
• Sites: 1

Brief Summary

This study aims to develop a comprehensive artificial intelligence model system integrating preoperative multimodal data (CT/MRI imaging, clinical laboratory data, and radiology report text) to achieve two core objectives. First, to develop a multimodal fusion diagnostic model for non-invasive and accurate preoperative differentiation of liver cancer subtypes, including distinguishing benign from malignant lesions and differentiating hepatocellular carcinoma from intrahepatic cholangiocarcinoma. Second, to develop a prognostic prediction model for patients with confirmed liver cancer undergoing radical surgery to assess postoperative progression-free survival and overall survival. This is a multicenter retrospective cohort study with an anticipated sample size of ≥600 patients. Model performance will be evaluated using AUC, accuracy, sensitivity, specificity, C-index, and calibration curves. Subgroup analysis will be conducted based on whether patients received neoadjuvant therapy.

Conditions

Liver Cancer; Hepatocellular Carcinoma; Intrahepatic Cholangiocarcinoma (Icc)

Outcome Measures

Primary Outcomes (2)

• Diagnostic Accuracy of the Multimodal AI Model for Liver Lesion Classification

  The diagnostic performance of the multimodal AI model in differentiating benign from malignant liver lesions and distinguishing hepatocellular carcinoma from intrahepatic cholangiocarcinoma, evaluated using pathology results as the gold standard. Performance metrics include area under the receiver operating characteristic curve (AUC), accuracy, sensitivity, and specificity.

  At the time of initial diagnosis

• Prognostic Performance of the Multimodal AI Model for Postoperative Survival Prediction

  The prognostic performance of the multimodal AI model in predicting postoperative progression-free survival (PFS) and overall survival (OS) in patients with pathologically confirmed liver cancer who underwent radical hepatectomy. Performance metric includes the concordance index (C-index). Calibration curves are also assessed.

  minimum follow-up of 24 months

Study Arms (2)

Diagnostic

Diagnostic Model Cohort: Patients with suspected liver space-occupying lesions who underwent preoperative contrast-enhanced CT or MRI and have definite pathological diagnosis (surgical or biopsy) as gold standard.

Prognostic

Prognostic Prediction Model Cohort: Patients selected from the diagnostic cohort who were pathologically diagnosed with liver cancer, received radical hepatectomy, and have complete postoperative follow-up data (minimum 24 months) to determine progression-free survival and overall survival endpoints.

Eligibility Criteria

• Age: 18 Years - 80 Years
• Sex: all
• Healthy Volunteers: No
• Age Groups: Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

(1) Key clinical, imaging, or pathological data severely missing or incomplete; (2) Preoperative CT or MRI images of poor quality or missing sequences, unable to perform reliable image analysis; (3) Prior local treatment for the target liver lesion, unless clearly recorded as neoadjuvant therapy before surgery; (4) Concurrent other malignant tumors; (5) Lost to follow-up or follow-up data cannot meet endpoint determination requirements.

You may qualify if:

• Diagnostic Model Cohort:
• Age ≥18 years
• Underwent preoperative contrast-enhanced CT or MRI for clinically suspected liver space-occupying lesion
• Have complete preoperative clinical laboratory data
• Have complete original CT/MRI imaging data and radiology reports
• Have definite pathological diagnosis from surgery or biopsy as gold standard
• Prognostic Prediction Model Cohort (selected from diagnostic cohort):
• Pathologically confirmed liver cancer
• Underwent radical hepatectomy
• Have complete preoperative multimodal data (CT/MRI imaging, clinical laboratory data, radiology reports)
• Have complete postoperative follow-up data to determine progression-free survival and overall survival endpoints and time (minimum follow-up of 24 months)

You may not qualify if:

• · Key clinical, imaging, or pathological data severely missing or incomplete
• Preoperative CT or MRI images of poor quality or missing sequences, unable to perform reliable image analysis
• Prior local treatment for the target liver lesion, unless clearly recorded as neoadjuvant therapy before surgery
• Concurrent other malignant tumors
• Lost to follow-up or follow-up data cannot meet endpoint determination requirements

Sponsors & Collaborators

• Guangxi Medical University: lead

Study Sites (1)

Guangxi Medical University First Affiliated Hospital

Nanning, Guangxi, China

Location

Related Publications (11)

• Di Martino F, Delmastro F. Explainable AI for clinical and remote health applications: a survey on tabular and time series data. Artif Intell Rev. 2023;56(6):5261-5315. doi: 10.1007/s10462-022-10304-3. Epub 2022 Oct 26.

  PMID: 36320613 BACKGROUND

• Xu P, Zhu X, Clifton DA. Multimodal Learning With Transformers: A Survey. IEEE Trans Pattern Anal Mach Intell. 2023 Oct;45(10):12113-12132. doi: 10.1109/TPAMI.2023.3275156. Epub 2023 Sep 5.

  PMID: 37167049 BACKGROUND

• Schmauch B, Elsoukkary SS, Moro A, Raj R, Wehrle CJ, Sasaki K, Calderaro J, Sin-Chan P, Aucejo F, Roberts DE. Combining a deep learning model with clinical data better predicts hepatocellular carcinoma behavior following surgery. J Pathol Inform. 2023 Dec 29;15:100360. doi: 10.1016/j.jpi.2023.100360. eCollection 2024 Dec.

  PMID: 38292073 BACKGROUND

• Ji GW, Zhu FP, Xu Q, Wang K, Wu MY, Tang WW, Li XC, Wang XH. Radiomic Features at Contrast-enhanced CT Predict Recurrence in Early Stage Hepatocellular Carcinoma: A Multi-Institutional Study. Radiology. 2020 Mar;294(3):568-579. doi: 10.1148/radiol.2020191470. Epub 2020 Jan 14.

  PMID: 31934830 BACKGROUND

• Peng J, Kang S, Ning Z, Deng H, Shen J, Xu Y, Zhang J, Zhao W, Li X, Gong W, Huang J, Liu L. Residual convolutional neural network for predicting response of transarterial chemoembolization in hepatocellular carcinoma from CT imaging. Eur Radiol. 2020 Jan;30(1):413-424. doi: 10.1007/s00330-019-06318-1. Epub 2019 Jul 22.

  PMID: 31332558 BACKGROUND

• Castaldo A, De Lucia DR, Pontillo G, Gatti M, Cocozza S, Ugga L, Cuocolo R. State of the Art in Artificial Intelligence and Radiomics in Hepatocellular Carcinoma. Diagnostics (Basel). 2021 Jun 30;11(7):1194. doi: 10.3390/diagnostics11071194.

  PMID: 34209197 BACKGROUND

• Wang C, Wei F, Sun X, Qiu W, Yu Y, Sun D, Zhi Y, Li J, Fan Z, Lv G, Wang G. Exploring potential predictive biomarkers through historical perspectives on the evolution of systemic therapies into the emergence of neoadjuvant therapy for the treatment of hepatocellular carcinoma. Front Oncol. 2024 Jun 27;14:1429919. doi: 10.3389/fonc.2024.1429919. eCollection 2024.

  PMID: 38993637 BACKGROUND

• He Z, She X, Liu Z, Gao X, Lu LU, Huang J, Lu C, Lin Y, Liang R, Ye J. Advances in post-operative prognostic models for hepatocellular carcinoma. J Zhejiang Univ Sci B. 2023 Mar 15;24(3):191-206. doi: 10.1631/jzus.B2200067.

  PMID: 36915996 BACKGROUND

• Herden U, Schoening W, Pratschke J, Manekeller S, Paul A, Linke R, Lorf T, Lehner F, Braun F, Stippel DL, Sucher R, Schmidt H, Strassburg CP, Guba M, van Rosmalen M, Rogiers X, Samuel U, Schon GM, Nashan B. Accuracy of Pretransplant Imaging Diagnostic for Hepatocellular Carcinoma: A Retrospective German Multicenter Study. Can J Gastroenterol Hepatol. 2019 Mar 5;2019:8747438. doi: 10.1155/2019/8747438. eCollection 2019.

  PMID: 30949459 BACKGROUND

• Saito R, Amemiya H, Hosomura N, Kawaida H, Maruyama S, Shimizu H, Furuya S, Akaike H, Kawaguchi Y, Sudo M, Inoue S, Kono H, Ichikawa D. Prognostic Significance of Treatment Strategies for the Recurrent Hepatocellular Carcinomas After Radical Resection. In Vivo. 2020 May-Jun;34(3):1265-1270. doi: 10.21873/invivo.11900.

  PMID: 32354917 BACKGROUND

• Bray F, Laversanne M, Sung H, Ferlay J, Siegel RL, Soerjomataram I, Jemal A. Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries. CA Cancer J Clin. 2024 May-Jun;74(3):229-263. doi: 10.3322/caac.21834. Epub 2024 Apr 4.

  PMID: 38572751 BACKGROUND

MeSH Terms

Conditions

Liver Neoplasms; Carcinoma, Hepatocellular; Cholangiocarcinoma; Cirrhosis, Familial, with Pulmonary Hypertension

Condition Hierarchy (Ancestors)

Digestive System Neoplasms; Neoplasms by Site; Neoplasms; Digestive System Diseases; Liver Diseases; Adenocarcinoma; Carcinoma; Neoplasms, Glandular and Epithelial; Neoplasms by Histologic Type

Study Design

• Study Type: observational
• Observational Model: COHORT
• Time Perspective: PROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: PRINCIPAL INVESTIGATOR
• PI Title: Doctor of Medicine

Study Record Dates

• First Submitted: June 14, 2026
• First Posted: June 22, 2026
• Study Start: December 1, 2025
• Primary Completion (Estimated): December 1, 2028
• Study Completion (Estimated): December 1, 2028
• Last Updated: July 1, 2026

Record last verified: 2026-06

Locations

CN (1)