Department of Biomedical Engineering and Medical Physics, School of Medicine, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
Department of Biomedical Engineering and Medical Physics, School of Medicine, Shahid Beheshti University of Medical Sciences, Tehran, Iran.
Comput Methods Programs Biomed. 2024 Feb;244:107932. doi: 10.1016/j.cmpb.2023.107932. Epub 2023 Nov 22.
BACKGROUND AND OBJECTIVES: Non-alcoholic fatty liver disease (NAFLD) is a common liver disease with a rapidly growing incidence worldwide. For prognostication and therapeutic decisions, it is important to distinguish the pathological stages of NAFLD: steatosis, steatohepatitis, and liver fibrosis, which are definitively diagnosed on invasive biopsy. Non-invasive ultrasound (US) imaging, including US elastography technique, and clinical parameters can be used to diagnose and grade NAFLD and its complications. Artificial intelligence (AI) is increasingly being harnessed for developing NAFLD diagnostic models based on clinical, biomarker, or imaging data. In this work, we systemically reviewed the literature for AI-enabled NAFLD diagnostic models based on US (including elastography) and clinical (including serological) data. METHODS: We performed a comprehensive search on Google Scholar, Scopus, and PubMed search engines for articles published between January 2005 and June 2023 related to AI models for NAFLD diagnosis based on US and/or clinical parameters using the following search terms: "non-alcoholic fatty liver disease", "non-alcoholic steatohepatitis", "deep learning", "machine learning", "artificial intelligence", "ultrasound imaging", "sonography", "clinical information". RESULTS: We reviewed 64 published models that used either US (including elastography) or clinical data input to detect the presence of NAFLD, non-alcoholic steatohepatitis, and/or fibrosis, and in some cases, the severity of steatosis, inflammation, and/or fibrosis as well. The performances of the published models were summarized, and stratified by data input and algorithms used, which could be broadly divided into machine and deep learning approaches. CONCLUSION: AI models based on US imaging and clinical data can reliably detect NAFLD and its complications, thereby reducing diagnostic costs and the need for invasive liver biopsy. The models offer advantages of efficiency, accuracy, and accessibility, and serve as virtual assistants for specialists to accelerate disease diagnosis and reduce treatment costs for patients and healthcare systems.
背景与目的：非酒精性脂肪性肝病（NAFLD）是一种常见的肝脏疾病，其全球发病率正在迅速增长。为了进行预后和治疗决策，区分 NAFLD 的病理阶段（脂肪变性、脂肪性肝炎和肝纤维化）非常重要，这些阶段只能通过有创活检来明确诊断。包括超声弹性成像技术在内的非侵入性超声（US）成像以及临床参数可用于诊断和分级 NAFLD 及其并发症。人工智能（AI）正越来越多地被用于开发基于临床、生物标志物或影像学数据的 NAFLD 诊断模型。在这项工作中，我们系统性地综述了基于 US（包括弹性成像）和临床（包括血清学）数据的 AI 辅助 NAFLD 诊断模型的文献。
方法：我们在 Google Scholar、Scopus 和 PubMed 搜索引擎上进行了全面检索，以查找 2005 年 1 月至 2023 年 6 月期间发表的与基于 US 和/或临床参数的 AI 模型诊断 NAFLD 相关的文章，使用的搜索词如下：“非酒精性脂肪性肝病”、“非酒精性脂肪性肝炎”、“深度学习”、“机器学习”、“人工智能”、“超声成像”、“超声检查”、“临床信息”。
结果：我们回顾了 64 篇已发表的模型，这些模型使用 US（包括弹性成像）或临床数据输入来检测 NAFLD、非酒精性脂肪性肝炎和/或纤维化的存在，在某些情况下还可以检测脂肪变性、炎症和/或纤维化的严重程度。总结了已发表模型的性能，并按数据输入和使用的算法进行了分层，这些模型可大致分为机器和深度学习方法。
结论：基于 US 成像和临床数据的 AI 模型可以可靠地检测 NAFLD 及其并发症，从而降低诊断成本和对有创肝活检的需求。这些模型具有高效、准确和易于获取的优势，可作为专家的虚拟助手，加速疾病诊断并降低患者和医疗保健系统的治疗成本。
Comput Methods Programs Biomed. 2024-2
Cochrane Database Syst Rev. 2016-3-2
Cochrane Database Syst Rev. 2023-11-15
Health Technol Assess. 2011-11
Cochrane Database Syst Rev. 2021-7-19
Cochrane Database Syst Rev. 2017-3-30
Cochrane Database Syst Rev. 2022-5-20
World J Gastroenterol. 2025-7-21
BMC Med Imaging. 2025-7-10
Zotero 插件