Yahaya Bappah Suleiman, Osman Noor Diyana, Karim Noor Khairiah A, Appalanaido Gokula Kumar, Isa Iza Sazanita
Department of Biomedical Imaging, Advanced Medical and Dental Institute, Universiti Sains Malaysia, Kepala Batas, Pulau Penang, 13200, Malaysia; Department of Radiography and Radiation Sciences, Faculty of Allied Health Sciences, Federal University of Health Sciences Azare, Nigeria.
Department of Biomedical Imaging, Advanced Medical and Dental Institute, Universiti Sains Malaysia, Kepala Batas, Pulau Penang, 13200, Malaysia; Advanced Management of Liver Malignancies Research Program, Advanced Medical and Dental Institute, Universiti Sains Malaysia, Penang, Malaysia.
Comput Biol Med. 2025 Aug;194:110491. doi: 10.1016/j.compbiomed.2025.110491. Epub 2025 Jun 3.
Computed tomography (CT) has been widely used as an effective tool for liver imaging due to its high spatial resolution, and ability to differentiate tissue densities, which contributing to comprehensive image analysis. Recent advancements in artificial intelligence (AI) promoted the role of Machine Learning (ML) in managing liver cancers by predicting or classifying tumours using mathematical algorithms. Deep learning (DL), a subset of ML, expanded these capabilities through convolutional neural networks (CNN) that analyse large data automatically. This review examines methods, achievements, limitations, and performance outcomes of ML-based radiomics and DL models for liver malignancies from CT imaging.
A systematic search for full-text articles in English on CT radiomics and DL in liver cancer analysis was conducted in PubMed, Scopus, Science Citation Index, and Cochrane Library databases between 2020 and 2024 using the keywords; machine learning, radiomics, deep learning, computed tomography, liver cancer and associated MESH terms. PRISMA guidelines were used to identify and screen studies for inclusion.
A total of 49 studies were included consisting of 17 Radiomics, 24 DL, and 8 combined DL/Radiomics studies. Radiomics has been predominantly utilised for predictive analysis, while DL has been extensively applied to automatic liver and tumour segmentation with a surge of a recent increase in studies integrating both techniques.
Despite the growing popularity of DL methods, classical radiomics models are still relevant and often preferred over DL methods when performance is similar, due to lower computational and data needs. Performance of models keep improving, but challenges like data scarcity and lack of standardised protocols persists.
计算机断层扫描（CT）因其高空间分辨率以及区分组织密度的能力，已被广泛用作肝脏成像的有效工具，这有助于进行全面的图像分析。人工智能（AI）的最新进展推动了机器学习（ML）在肝癌管理中的作用，通过使用数学算法预测或分类肿瘤。深度学习（DL）作为ML的一个子集，通过自动分析大数据的卷积神经网络（CNN）扩展了这些能力。本综述探讨了基于ML的放射组学和DL模型在CT成像的肝脏恶性肿瘤方面的方法、成果、局限性和性能结果。
在2020年至2024年期间，使用关键词“机器学习”“放射组学”“深度学习,”“计算机断层扫描”“肝癌”及相关医学主题词，在PubMed、Scopus、科学引文索引和考克兰图书馆数据库中对关于CT放射组学和DL在肝癌分析中的英文全文文章进行系统检索。采用PRISMA指南来识别和筛选纳入研究。
共纳入49项研究，其中包括17项放射组学研究、24项DL研究和8项DL/放射组学联合研究。放射组学主要用于预测分析，而DL已广泛应用于肝脏和肿瘤的自动分割，最近将这两种技术结合的研究数量激增。
尽管DL方法越来越受欢迎，但经典的放射组学模型仍然具有相关性，并且在性能相似时，由于计算和数据需求较低，通常比DL方法更受青睐。模型的性能不断提高，但数据稀缺和缺乏标准化协议等挑战仍然存在。
