影像学及机器学习在代谢功能障碍相关脂肪性肝病中的应用价值

摘要/Abstract

摘要： 代谢功能障碍相关脂肪性肝病(MASLD)已超越病毒性肝炎,成为全球最常见的慢性肝病。伴随着不同程度的肝纤维化,MASLD可能最终进展为肝硬化及肝细胞癌(HCC)。MASLD与心血管疾病、慢性肾脏病、肝脏和肝外恶性肿瘤,以及包括肝功能衰竭和HCC在内的肝脏相关结局的风险增加有关。MASLD带来的高社会经济负担已成为日益严峻的公共卫生问题及健康挑战。因此,早期识别与诊断MASLD及相关的纤维化,对于减少并发症的发生和改善预后具有重要意义。目前,亟需找到有效且可靠的无创评估模型,来早期诊断和评估脂肪性肝炎和肝纤维化,以便及时进行风险分层和管理,防止疾病恶化和并发症的发生。本文就影像学及机器学习(ML)在MASLD中的应用价值进行探讨,从而指导临床决策。

关键词: 影像学, 机器学习, 代谢功能障碍相关脂肪性肝病, 诊断价值

余虹, 郭峰, 笪欣. 影像学及机器学习在代谢功能障碍相关脂肪性肝病中的应用价值[J]. 肝脏, 2025, 30(11): 1577-1579.

/ 推荐

参考文献

[1] 范建高,徐小元,南月敏,等.代谢相关(非酒精性)脂肪性肝病防治指南(2024年版)[J].实用肝脏病杂志,2024,27(4):494-510.
[2] Eslam M, Newsome P N, Sarin S K, et al. A new definition for metabolic dysfunction-associated fatty liver disease: an international expert consensus statement[J]. J Hepatol, 2020,73(1):202-209.
[3] Rinella M E, Lazarus J V, Ratziu V, et al. A multisociety Delphi consensus statement on new fatty liver disease nomenclature[J]. J Hepatol, 2023,79(6):1542-1556.
[4] Hagström H, Vessby J, Ekstedt M, et al. 99% of patients with NAFLD meet MASLD criteria and natural history is therefore identical[J]. J Hepatol,2024,80(2):e76-e77.
[5] Miao L, Targher G, Byrne C D, et al. Current status and future trends of the global burden of MASLD[J]. Trends Endocrinol Metab, 2024,35(8):697-707.
[6] McGlynn K A, Petrick J L, El-Serag H B. Epidemiology of hepatocellular carcinoma[J]. Hepatology, 2021,73(Suppl 1):4-13.
[7] Huang D Q, El-Serag H B, Loomba R.Global epidemiology of NAFLD-related HCC: trends, predictions, risk factors and prevention[J]. Nat Rev Gastroenterol Hepatol, 2021,18(4):223-238.
[8] Huang D Q, Terrault N A, Tacke F,et al. Global epidemiology of cirrhosis- aetiology, trends and predictions[J]. Nat Rev Gastroenterol Hepatol, 2023,20(6):388-398.
[9] Vitellius C, Desjonqueres E, Lequoy M,et al. MASLD-related HCC: multicenter study comparing patients with and without cirrhosis[J]. JHEP Rep, 2024,6(10):101160.
[10] Castera L, Friedrich-Rust M, Loomba R. Noninvasive assessment of liver disease in patients with nonalcoholic fatty liver disease[J]. Gastroenterology,2019,156(5):1264-1281.e4.
[11] Rinella M E, Neuschwander-Tetri B A, Siddiqui M S,et al. AASLD Practice Guidance on the clinical assessment and management of nonalcoholic fatty liver disease[J].Hepatology, 2023,77(5):1797-1835.
[12] Archer A J, Belfield K J, Orr J G,et al. EASL clinical practice guidelines: non-invasive liver tests for evaluation of liver disease severity and prognosis[J].Frontline Gastroenterol, 2022,13(5):436-439.
[13] 曾静,范建高.MASLD管理中无创检测替代肝活检添新证据:突破还是挑战?[J].肝脏,2024,29(5):491-493.
[14] Wattacheril J J, Abdelmalek M F, Lim J K, et al. AGA clinical practice update on the role of noninvasive biomarkers in the evaluation and management of nonalcoholic fatty liver disease: expert review[J]. Gastroenterology, 2023,165(4):1080-1088.
[15] Jung J, Loomba R R, Imajo K, et al. MRE combined with FIB-4 (MEFIB) index in detection of candidates for pharmacological treatment of NASH-related fibrosis[J].Gut, 2021,70(10):1946-1953.
[16] Newsome P N, Sasso M, Deeks J J. FibroScan-AST (FAST) score for the non-invasive identification of patients with non-alcoholic steatohepatitis with significant activity and fibrosis: a prospective derivation and global validation study[J].Lancet Gastroenterol Hepatol,2020,5(4):362-373.
[17] Noureddin M, Ntanios F, Malhotra D, et al. Predicting NAFLD prevalence in the United States using National Health and Nutrition Examination Survey 2017-2018 transient elastography data and application of machine learning[J]. Hepatol Commun,2022,6(7):1537-1548.
[18] Hernaez R,Lazo M,Bonekamp S,et a1.Diagnostic accuracy and reliability of ultrasonography for the detection of fatty liver:a meta-analysis[J].Hepatology,2011,54(3): 1082-1090.
[19] Feng X, Ye J, Deng H, et al. An Optimized strategy based on conventional ultrasound for diagnosing metabolic dysfunction-Associated steatotic liver disease[J]. Diagnostics (Basel), 2023,13(23):3503.
[20] 王子谦,王士旭,刘艺行,等.代谢功能障碍相关脂肪性肝病非侵入性诊断研究进展[J].医学新知,2024,34(7):807-816.
[21] Zou H, Ma X, Pan W, et al. Comparing similarities and differences between NAFLD, MAFLD, and MASLD in the general U.S. population[J]. Front Nutr,2024,11:1411802.
[22] Malandris K, Korakas E, Sarakapina A.et al.Accuracy of controlled attenuation parameter for liver steatosis in high-risk patients for MASLD using MRI-proton density fat fraction as reference standard[J]. Dig Dis Sci, 2025, 70(2):814-824.
[23] Byun J,Lee S S,Sung Y S,et a1.CT indices for the diagnosis of hepatic steatosis using non—enhanced CT images:development and validation of diagnostic cut-off values in a large cohort with pathological reference standard[J].Eur Radiol,2019,29(8):4427-4435.
[24] Catania R,Furlan A,Smith A D,et al. Diagnostic value of MRI-derived liver surface nodularity score for the non-invasive quantification of hepatic fibrosis in non-alcoholic fatty liver disease[J]. Eur Radiol,2021,31(1):256-263.
[25] Karlas T, Petroff D, Sasso M, et al. Individual patients data meta-analysis of controlled attenuation paramter (CAP) technology for assessing steatosis[J]. J Hepatol, 2017, 66(5):1022-1030.
[26] Eddaves P J, Sasso M, Allison M, et al. Accuracy of fibroscan controlled attenuation parameter and liver stiffness measurement in assessing steatosis and fibrosis in patients with nonalcoholic fatty liver disease[J]. Gastroenterol, 2019, 156(6):1717-1730.
[27] Liang J X, Ampuero J, Niu H, et al. An individual patient data meta-analysis to determine cut-offs for and confounders of NAFLD-fibrosis staging with magnetic resonance elastography[J]. J Hepatol,2023,79(3): 592-604.
[28] Chen R, Petrazzini B O, Nadkarni G, et al. Machine learning enables single-score assessment of MASLD presence and severity[J].medRxiv,2023:2023.10.24.23297423.
[29] Fan R, Yu N, Li G, et al. Machine-learning model comprising five clinical indices and liver stiffness measurement can accurately identify MASLD-related liver fibrosis[J]. Liver Int,2024 ,44(3):749-759.
[30] Njei B, Osta E, Njei N,et al. An explainable machine learning model for prediction of high-risk nonalcoholic steatohepatitis[J]. Sci Rep, 2024,14(1):8589.
[31] Gil-Rojas S, Suárez M, Martínez-Blanco P, et al. Prognostic impact of metabolic syndrome and steatotic liver disease in hepatocellular carcinoma using machine learning techniques[J]. Metabolites, 2024,14(6):305.
[32] Sarkar S, Alurwar A, Ly C, et al. A machine learning model to predict risk for hepatocellular carcinoma in patients with metabolic dysfunction-associated steatotic liver disease[J]. Gastro Hep Adv, 2024,3(4):498-505.