Implications of ultrasound-based deep learning model for preoperatively differentiating combined hepatocellular-cholangiocarcinoma from hepatocellular carcinoma and intrahepatic cholangiocarcinoma
- 24 November 2023
- journal article
- research article
- Published by Springer Nature in Abdominal Radiology
- Vol. 49 (1) , 93-102
Abstract
Objectives The current study developed an ultrasound-based deep learning model to make preoperative differentiation among hepatocellular carcinoma (HCC), intrahepatic cholangiocarcinoma (ICC), and combined hepatocellular–cholangiocarcinoma (cHCC-ICC). Methods The B-mode ultrasound images of 465 patients with primary liver cancer were enrolled in model construction, comprising 264 HCCs, 105 ICCs, and 96 cHCC-ICCs, of which 50 cases were randomly selected to form an independent test cohort, and the rest of study population was assigned to a training and validation cohorts at the ratio of 4:1. Four deep learning models (Resnet18, MobileNet, DenseNet121, and Inception V3) were constructed, and the fivefold cross-validation was adopted to train and validate the performance of these models. The following indexes were calculated to determine the differential diagnosis performance of the models, including sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV), F-1 score, and area under the receiver operating characteristic curve (AUC) based on images in the independent test cohort. Results Based on the fivefold cross-validation, the Resnet18 outperformed other models in terms of accuracy and robustness, with the overall training and validation accuracy as 99.73% (± 0.07%) and 99.35% (± 0.53%), respectively. Furthers validation based on the independent test cohort suggested that Resnet 18 yielded the best diagnostic performance in identifying HCC, ICC, and cHCC-ICC, with the sensitivity, specificity, accuracy, PPV, NPV, F1-score, and AUC of 84.59%, 92.65%, 86.00%, 85.82%, 92.99%, 92.37%, 85.07%, and 0.9237 (95% CI 0.8633, 0.9840). Conclusion Ultrasound-based deep learning algorithm appeared a promising diagnostic method for identifying cHCC-ICC, HCC, and ICC, which might play a role in clinical decision making and evaluation of prognosis. Graphical abstractKeywords
Funding Information
- Clinical Study of Shanghai Municipal Health Commission (No.20194Y0473)
This publication has 39 references indexed in Scilit:
- Systemic Therapy for Combined Hepatocellular-Cholangiocarcinoma: A Single-Institution ExperienceJournal of the National Comprehensive Cancer Network, 2018
- Hepatocellular Carcinoma and Intrahepatic Cholangiocarcinoma: Imaging for Diagnosis, Tumor Response to Treatment and Liver Response to RadiationSeminars in Radiation Oncology, 2018
- The effectiveness of transarterial chemoembolization in recurrent hepatocellular-cholangiocarcinoma after resectionPLOS ONE, 2018
- Contrast enhanced ultrasound in mixed hepatocellular cholangiocarcinoma: Case series and review of the literatureDigestive and Liver Disease, 2018
- MRI features of combined hepatocellular- cholangiocarcinoma versus mass forming intrahepatic cholangiocarcinomaCancer Imaging, 2018
- Living Donor Liver Transplantation for Combined Hepatocellular Carcinoma and Cholangiocarcinoma: Experience of a Single CenterAnnals of Transplantation, 2017
- Combined hepatocellular carcinoma and cholangiocarcinoma (biphenotypic) tumors: clinical characteristics, imaging features of contrast-enhanced ultrasound and computed tomographyBMC Cancer, 2016
- Guidelines for the diagnosis and management of intrahepatic cholangiocarcinomaJournal of Hepatology, 2014
- Long-term Prognosis of Combined Hepatocellular and Cholangiocarcinoma After Curative Resection Comparison With Hepatocellular Carcinoma and CholangiocarcinomaJournal of Clinical Gastroenterology, 2011
- COMBINED LIVER CELL AND BILE DUCT CARCINOMA1949