Skip to main content

REVIEW article

Front. Artif. Intell.
Sec. Medicine and Public Health
Volume 7 - 2024 | doi: 10.3389/frai.2024.1398205
This article is part of the Research Topic AI in Digital Oncology: Imaging and Wearable Technology for Cancer Detection and Management View all 3 articles

Diagnostic Performance of AI-based Models versus Physicians Among Patients with Hepatocellular Carcinoma: A Systematic Review and Meta-analysis

Provisionally accepted
Feras Al-Obeidat Feras Al-Obeidat 1*Wael Hafez Wael Hafez 2,3*Muneir Gador Muneir Gador 2Nesma Ahmed Nesma Ahmed 4Marwa Mohamed Marwa Mohamed 4
  • 1 Abu Dhabi Campus, College of Technological Innovation, Zayed University, Dubai, United Arab Emirates
  • 2 NMC Royal Hospital, Abu Dhabi, United Arab Emirates
  • 3 National Research Centre (Egypt), Cairo, Cairo, Egypt
  • 4 MARS-GLOBAL -, Clinical Research and Statistics, United Kingdom

The final, formatted version of the article will be published soon.

    Background: Hepatocellular carcinoma (HCC) is a common primary liver cancer that requires early diagnosis due to its poor prognosis. Recent advances in artificial intelligence (AI) have facilitated hepatocellular carcinoma detection using multiple AI models; however, their performance is still uncertain.Aim: This meta-analysis aimed to compare the diagnostic performance of different AI models with that of clinicians in the detection of hepatocellular carcinoma.We searched the PubMed, Scopus, Cochrane Library, and Web of Science databases for eligible studies. The R package was used to synthesize the results. The outcomes of various studies were aggregated using fixed-effect and random-effects models. Statistical heterogeneity was evaluated using I-squared (I²) and chi-square statistics.: Seven studies were included. The region-based convolutional neural network (RCNN) model of Bin Liu et al. (2023) and the model of Hamm et al. (2019) showed high sensitivity (96% and 95%, respectively). According to Kim et al. (2020), the convolutional neural network (CNN) model has the same specificity as expert radiologists (93%). Model F in Zhen et al. (2020) had the highest specificity (96.2%), while the model in Urhuț et al. (2023) had the lowest value (56.2%). The leave-one-out sensitivity revealed high heterogeneity among studies, which represented true differences among the studies. Conclusion: Models based on Faster R-CNN excel in image classification and data extraction, while both CNN-based models and models combining contrast-enhanced ultrasound (CEUS) with artificial intelligence (AI) had good sensitivity. Although AI models outperform physicians in diagnosing HCC, they should be utilized as supportive tools to help make more accurate and timely decisions.

    Keywords: artificial intelligence, Hepatocellular Carcinoma, HCC, Diagnostic performance, AI models

    Received: 09 Mar 2024; Accepted: 26 Jul 2024.

    Copyright: © 2024 Al-Obeidat, Hafez, Gador, Ahmed and Mohamed. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

    * Correspondence:
    Feras Al-Obeidat, Abu Dhabi Campus, College of Technological Innovation, Zayed University, Dubai, 19282, United Arab Emirates
    Wael Hafez, NMC Royal Hospital, Abu Dhabi, United Arab Emirates

    Disclaimer: All claims expressed in this article are solely those of the authors and do not necessarily represent those of their affiliated organizations, or those of the publisher, the editors and the reviewers. Any product that may be evaluated in this article or claim that may be made by its manufacturer is not guaranteed or endorsed by the publisher.