肝病数字活检的关键技术与应用前景

周阳; 陈振伟; 施翰英; 林孔英; 王英超; 曾永毅

doi:10.12449/JCH251102

肝病数字活检的关键技术与应用前景

DOI: 10.12449/JCH251102

周阳¹,
陈振伟²,
施翰英³,
林孔英⁴,
王英超^{1, 5},
曾永毅^4, , ,

1.
福建医科大学孟超肝胆医院生物信息样本库，福州 350025
2.
建医科大学孟超肝胆医院信息科，福州 350025
3.
建医科大学孟超肝胆医院教学办，福州 350025
4.
建医科大学孟超肝胆医院肝胆胰外科，福州 350025
5.
福建省肝病科学研究中心，福州 350025

基金项目:

国家自然科学基金面上项目 (62275050);

国家重点研发计划 (2022YFC2407304);

福建省自然科学基金计划项目 (2025J011318);

福州市科技计划项目 (2024-G-015)

利益冲突声明：本文不存在任何利益冲突。

作者贡献声明：曾永毅负责论文的总体构思与统筹；周阳主导研究设计与初稿撰写；陈振伟负责数据整理与图表制作；施翰英、林孔英参与资料收集与文献综述；王英超负责论文修改与语言润色。

详细信息

通信作者:
曾永毅， lamp197311@126.com （ORCID： 0000-0001-8823-698X）

计量
- 文章访问数: 2
- HTML全文浏览量: 2
- PDF下载量: 2
- 被引次数: 0
出版历程
- 收稿日期: 2025-09-01
- 录用日期: 2025-10-18
- 出版日期: 2025-11-25

Digital biopsy for liver diseases： A review of technological advances and application prospects

1.
a. Biological Information Biobank，Mengchao Hepatobiliary Hospital of Fujian Medical University，Fuzhou 350025，China
2.
Department of Information Technology，Mengchao Hepatobiliary Hospital of Fujian Medical University，Fuzhou 350025，China
3.
Office of Teaching Affairs，Mengchao Hepatobiliary Hospital of Fujian Medical University，Fuzhou 350025，China
4.
Department of Hepatopancreatobiliary Surgery，Mengchao Hepatobiliary Hospital of Fujian Medical University，Fuzhou 350025，China
5.
Liver Disease Research Center of Fujian Province，Fuzhou 350025，China

Research funding:

National Natural Science Foundation of China (62275050);

National Key Research and Development Program of China (2022YFC2407304);

Natural Science Foundation of Fujian Province (2025J011318);

Fuzhou Science and Technology Program (2024-G-015)

More Information

Corresponding author: ZENG Yongyi， lamp197311@126.com （ORCID： 0000-0001-8823-698X）

摘要

摘要: 肝病数字活检是人工智能技术与肝病大数据的深度融合，通过智能分析辅助临床决策与全流程管理。本文综述了以标准化数据治理为基础、多模态医学大模型为核心的人工智能技术体系，涵盖自然语言处理、知识图谱、生成式人工智能与大语言模型在专病数据库建设、诊断、预测、治疗及医疗文书生成等方面的应用，并探讨其在医学教育、科研与管理中的前景。尽管该技术展现出广阔的应用潜力，但在多中心数据整合、算法可解释性、伦理与数据安全等方面仍面临挑战。未来应构建闭环优化、人机协同的智能生态，促进其在“医-教-研-管”全链条的深度应用，助力肝病精准防控与全程健康管理。
- 肝病数字活检平台 /
- 人工智能 /
- 数据库
Abstract: Digital biopsy for liver diseases is characterized by the deep integration of artificial intelligence （AI） technologies and large-scale liver disease data， through which intelligent analytics are applied to support clinical decision-making and full-cycle management. This article reviews the AI technical framework based on standardized data governance and centered on multimodal large medical models， covering the application of natural language processing， knowledge map， generative AI， and large language models in the establishment of databases for specialty diseases， diagnosis， prognosis prediction， treatment， and automated medical documentation. This article also discusses the application prospects of this framework in medical education， scientific research， and healthcare management. Although this technique shows broad application potential， it still faces challenges in areas such as multi-center data integration， model interpretability， ethics， and data security. In the future， a smart ecosystem with closed-loop optimization and human-AI collaboration should be established to promote the comprehensive implementation of digital biopsy in the whole process of medicine， education， research， and management， thereby providing help for the precise prevention and control and holistic health management of liver diseases.
- Liver Disease Digital Biopsy Platform /
- Artificial Intelligence /
- Databases

HTML全文

图 1 肝病数字活检技术体系

Figure 1. Technical framework of liver disease digital biopsy

下载: 全尺寸图片幻灯片

表 1 数据治理环节的关键技术与应用

Table 1. Key technologies and applications in data governance

治理环节	关键技术与应用场景	参考文献
数据清洗与标准化	NLP负责从原始文本中提取实体和关系；知识图谱依托标准词汇体系实现语义整合与知识推理	［5-7］
质量控制与溯源	区块链与分布式账本技术用于数据溯源与审计；知识图谱编码医学规则，自动发现逻辑冲突（如用药与诊断不符）； NLP负责利用数据自身结构学习高质量表示，提升异常检测精度	［8-10］
模型迭代	基础模型通过对海量数据预训练，可持续监控数据质量与算法偏差；数字孪生构建虚拟数据环境，用于安全、低成本地仿真和验证治理策略迭代	［11-12］
隐私与安全	联邦学习实现“数据不动模型动”的多中心协同治理； GAN生成高质量合成数据，替代敏感原始数据用于开发和测试；二者结合能杜绝隐私泄露	［13-15］
注：NLP，自然语言处理；GAN，生成对抗网络。

下载: 导出CSV

表 2 AI辅助的临床任务体系中的关键技术与应用

Table 2. Key technologies and applications in the AI-assisted clinical task system

AI辅助的医学任务	关键技术与应用场景	参考文献
临床辅助决策	计算机视觉聚焦于肝脏影像（CT/MRI）中病灶的自动检测、定位与分类；知识图谱提供鉴别诊断支持；生成式AI生成初步诊断意见与治疗建议	［29-31］
风险预测与患者管理	卷积神经网络预测肝纤维化进展、肝硬化失代偿、肝细胞癌发生风险，对患者进行动态风险分层；基于时序建模进行健康风险自动化预警，并利用NLP技术生成个性化的健康管理方案	［32-34］
医疗文书自动化生成	大语言模型、生成式AI与多模态技术可自动整合患者病史与检查结果，并生成包括影像诊断报告、门诊病历、病程记录及出院小结在内的医学文书	［35-37］

下载: 导出CSV

参考文献(50)

[1]	SCHATTENBERG JM, CHALASANI N, ALKHOURI N. Artificial intelligence applications in hepatology[J]. Clin Gastroenterol Hepatol, 2023, 21( 8): 2015- 2025. DOI: 10.1016/j.cgh.2023.04.007.
[2]	CAZZANIGA G, L'IMPERIO V, BONOLDI E, et al. Automating liver biopsy segmentation with a robust, open-source tool for pathology research: The HOTSPoT model[J]. NPJ Digit Med, 2025, 8( 1): 455. DOI: 10.1038/s41746-025-01870-1.
[3]	WAQAS A, BUI MM, GLASSY EF, et al. Revolutionizing digital pathology with the power of generative artificial intelligence and foundation models[J]. Lab Invest, 2023, 103( 11): 100255. DOI: 10.1016/j.labinv.2023.100255.
[4]	HE R, SARWAL V, QIU XR, et al. Generative AI models in time-varying biomedical data: Scoping review[J]. J Med Internet Res, 2025, 27: e59792. DOI: 10.2196/59792.
[5]	BOSMA JS, DERCKSEN K, BUILTJES L, et al. The DRAGON benchmark for clinical NLP[J]. NPJ Digit Med, 2025, 8: 289. DOI: 10.1038/s41746-025-01626-x.
[6]	FEI H, REN YF, ZHANG Y, et al. Enriching contextualized language model from knowledge graph for biomedical information extraction[J]. Brief Bioinform, 2021, 22( 3): bbaa110. DOI: 10.1093/bib/bbaa110.
[7]	KALYAN KS, SANGEETHA S. BertMCN: Mapping colloquial phrases to standard medical concepts using BERT and highway network[J]. Artif Intell Med, 2021, 112: 102008. DOI: 10.1016/j.artmed.2021.102008.
[8]	OZONZE O, SCOTT PJ, HOPGOOD AA. Automating electronic health record data quality assessment[J]. J Med Syst, 2023, 47( 1): 23. DOI: 10.1007/s10916-022-01892-2.
[9]	SCOTT HF, BRILLI RJ, PAUL R, et al. Evaluating pediatric sepsis definitions designed for electronic health record extraction and multicenter quality improvement[J]. Crit Care Med, 2020, 48( 10): e916- e926. DOI: 10.1097/CCM.0000000000004505.
[10]	RISKIN DJ, MONDA KL, GAGNE JJ, et al. Implementing accuracy, completeness, and traceability for data reliability[J]. JAMA Netw Open, 2025, 8( 3): e250128. DOI: 10.1001/jamanetworkopen.2025.0128.
[11]	RIZZO M. AI in neurology: Everything, everywhere, all at once part 3: Surveillance, synthesis, simulation, and systems[J]. Ann Neurol, 2025, 98( 4): 651- 667. DOI: 10.1002/ana.27230.
[12]	STETSON PD, CHOY J, SUMMERVILLE N, et al. Responsible artificial intelligence governance in oncology[J]. NPJ Digit Med, 2025, 8( 1): 407. DOI: 10.1038/s41746-025-01794-w.
[13]	KOUTSOUBIS N, WAQAS A, YILMAZ Y, et al. Privacy-preserving federated learning and uncertainty quantification in medical imaging[J]. Radiol Artif Intell, 2025, 7( 4): e240637. DOI: 10.1148/ryai.240637.
[14]	LIU JH, CHEN C, QU YY, et al. RASS: Enabling privacy-preserving and authentication in online AI-driven healthcare applications[J]. ISA Trans, 2023, 141: 20- 29. DOI: 10.1016/j.isatra.2023.03.049.
[15]	LI J, CAIRNS BJ, LI JS, et al. Generating synthetic mixed-type longitudinal electronic health records for artificial intelligent applications[J]. NPJ Digit Med, 2023, 6( 1): 98. DOI: 10.1038/s41746-023-00834-7.
[16]	ISGUT M, GLOSTER L, CHOI K, et al. Systematic review of advanced AI methods for improving healthcare data quality in post COVID-19 era[J]. IEEE Rev Biomed Eng, 2023, 16: 53- 69. DOI: 10.1109/RBME.2022.3216531.
[17]	ANAYA G, PETTEE GABRIEL K, ST-ONGE MP, et al. Optimal instruments for measurement of dietary intake, physical activity, and sleep among adults in population-based studies: Report of a national heart, lung, and blood institute workshop[J]. J Am Heart Assoc, 2024, 13( 21): e035818. DOI: 10.1161/JAHA.124.035818.
[18]	BRADSHAW TJ, BROSCH-LENZ J, URIBE C, et al. Recommendations for standardizing nuclear medicine terminology and data in the era of theranostics and artificial intelligence[J]. J Nucl Med, 2025, 66( 9): 1471- 1479. DOI: 10.2967/jnumed.124.269424.
[19]	COSTELLO J, KAUR M, REFORMAT MZ, et al. Leveraging knowledge graphs and natural language processing for automated web resource labeling and knowledge mobilization in neurodevelopmental disorders: Development and usability study[J]. J Med Internet Res, 2023, 25: e45268. DOI: 10.2196/45268.
[20]	SHI J, BENDIG D, VOLLMAR HC, et al. Mapping the bibliometrics landscape of AI in medicine: Methodological study[J]. J Med Internet Res, 2023, 25: e45815. DOI: 10.2196/45815.
[21]	EDFELDT K, EDWARDS AM, ENGKVIST O, et al. A data science roadmap for open science organizations engaged in early-stage drug discovery[J]. Nat Commun, 2024, 15( 1): 5640. DOI: 10.1038/s41467-024-49777-x.
[22]	XI JN, SUN DH, CHANG C, et al. An omics-to-omics joint knowledge association subtensor model for radiogenomics cross-modal modules from genomics and ultrasonic images of breast cancers[J]. Comput Biol Med, 2023, 155: 106672. DOI: 10.1016/j.compbiomed.2023.106672.
[23]	AN D, LIM M, LEE S. Challenges for data quality in the clinical data life cycle: Systematic review[J]. J Med Internet Res, 2025, 27: e60709. DOI: 10.2196/60709.
[24]	GIEREND K, FREIESLEBEN S, KADIOGLU D, et al. The status of data management practices across German medical data integration centers: Mixed methods study[J]. J Med Internet Res, 2023, 25: e48809. DOI: 10.2196/48809.
[25]	LIGHTERNESS A, ADCOCK M, SCANLON LA, et al. Data quality-driven improvement in health care: Systematic literature review[J]. J Med Internet Res, 2024, 26: e57615. DOI: 10.2196/57615.
[26]	SYED R, EDEN R, MAKASI T, et al. Digital health data quality issues: Systematic review[J]. J Med Internet Res, 2023, 25: e42615. DOI: 10.2196/42615.
[27]	HE YT, HUANG FX, JIANG XR, et al. Foundation model for advancing healthcare: Challenges, opportunities and future directions[J]. IEEE Rev Biomed Eng, 2025, 18: 172- 191. DOI: 10.1109/RBME.2024.3496744.
[28]	SCHWABE D, BECKER K, SEYFERTH M, et al. The METRIC-framework for assessing data quality for trustworthy AI in medicine: A systematic review[J]. NPJ Digit Med, 2024, 7( 1): 203. DOI: 10.1038/s41746-024-01196-4.
[29]	TIWARI P, ZHU HY, PANDEY HM. DAPath: Distance-aware knowledge graph reasoning based on deep reinforcement learning[J]. Neural Netw, 2021, 135: 1- 12. DOI: 10.1016/j.neunet.2020.11.012.
[30]	PENG CY, XIA F, NASERIPARSA M, et al. Knowledge graphs: Opportunities and challenges[J]. Artif Intell Rev, 2023, 56( 11): 13071- 13102. DOI: 10.1007/s10462-023-10465-9.
[31]	BHUYAN SS, SATEESH V, MUKUL N, et al. Generative artificial intelligence use in healthcare: Opportunities for clinical excellence and administrative efficiency[J]. J Med Syst, 2025, 49( 1): 10. DOI: 10.1007/s10916-024-02136-1.
[32]	HE JZ, TIBO A, JANET JP, et al. Evaluation of reinforcement learning in transformer-based molecular design[J]. J Cheminform, 2024, 16( 1): 95. DOI: 10.1186/s13321-024-00887-0.
[33]	ATANCE SR, DIEZ JV, ENGKVIST O, et al. De novo drug design using reinforcement learning with graph-based deep generative models[J]. J Chem Inf Model, 2022, 62( 20): 4863- 4872. DOI: 10.1021/acs.jcim.2c00838.
[34]	PARK J, AHN J, CHOI J, et al. Mol-AIR: Molecular reinforcement learning with adaptive intrinsic rewards for goal-directed molecular generation[J]. J Chem Inf Model, 2025, 65( 5): 2283- 2296. DOI: 10.1021/acs.jcim.4c01669.
[35]	YIM WW, FU YJ, ABACHA A BEN, et al. Aci-bench: A novel ambient clinical intelligence dataset for benchmarking automatic visit note generation[J]. Sci Data, 2023, 10: 586. DOI: 10.1038/s41597-023-02487-3.
[36]	KERNBERG A, GOLD JA, MOHAN V. Using ChatGPT-4 to create structured medical notes from audio recordings of physician-patient encounters: Comparative study[J]. J Med Internet Res, 2024, 26: e54419. DOI: 10.2196/54419.
[37]	RAO VM, HLA M, MOOR M, et al. Multimodal generative AI for medical image interpretation[J]. Nature, 2025, 639( 8056): 888- 896. DOI: 10.1038/s41586-025-08675-y.
[38]	DINANI AM, KOWDLEY KV, NOUREDDIN M. Application of artificial intelligence for diagnosis and risk stratification in NAFLD and NASH: The state of the art[J]. Hepatology, 2021, 74( 4): 2233- 2240. DOI: 10.1002/hep.31869.
[39]	AHN JC, RATTAN P, STARLINGER P, et al. AI-Cirrhosis-ECG(ACE) score for predicting decompensation and liver outcomes[J]. JHEP Rep, 2025, 7( 5): 101356. DOI: 10.1016/j.jhepr.2025.101356.
[40]	SU GL, ZHANG P, BELANCOURT PX, et al. Incorporation of quantitative imaging data using artificial intelligence improves risk prediction in veterans with liver disease[J]. Hepatology, 2024, 80( 4): 928- 936. DOI: 10.1097/HEP.0000000000000750.
[41]	ZHAI YP, HAI DR, ZENG L, et al. Artificial intelligence-based evaluation of prognosis in cirrhosis[J]. J Transl Med, 2024, 22( 1): 933. DOI: 10.1186/s12967-024-05726-2.
[42]	SPANN A, STRAUSS AT, DAVIS SE, et al. The role of artificial intelligence in chronic liver diseases and liver transplantation[J]. Gastroenterology, 2025, 169( 3): 456- 470. DOI: 10.1053/j.gastro.2025.05.012.
[43]	FUJIWARA N, FOBAR AJ, RAMAN I, et al. A blood-based prognostic liver secretome signature predicts long-term risk of hepatic decompensation in cirrhosis[J]. Clin Gastroenterol Hepatol, 2022, 20( 5): e1188- e1191. DOI: 10.1016/j.cgh.2021.03.019.
[44]	BEDDIAR DR, OUSSALAH M, SEPPÄNEN T. Automatic captioning for medical imaging(MIC): A rapid review of literature[J]. Artif Intell Rev, 2023, 56( 5): 4019- 4076. DOI: 10.1007/s10462-022-10270-w.
[45]	FINK A, RAU A, REISERT M, et al. Retrieval-augmented generation with large language models in radiology: From theory to practice[J]. Radiol Artif Intell, 2025, 7( 4): e240790. DOI: 10.1148/ryai.240790.
[46]	BELLINI V, RUSSO M, DOMENICHETTI T, et al. Artificial intelligence in operating room management[J]. J Med Syst, 2024, 48( 1): 19. DOI: 10.1007/s10916-024-02038-2.
[47]	XU ZJ, WANG X, ZENG SS, et al. Applying artificial intelligence for cancer immunotherapy[J]. Acta Pharm Sin B, 2021, 11( 11): 3393- 3405. DOI: 10.1016/j.apsb.2021.02.007.
[48]	MUKHERJEE J, SHARMA R, DUTTA P, et al. Artificial intelligence in healthcare: A mastery[J]. Biotechnol Genet Eng Rev, 2024, 40( 3): 1659- 1708. DOI: 10.1080/02648725.2023.2196476.
[49]	MOROSKY CM, BAECHER-LIND L, CHEN KT, et al. Practical applications of artificial intelligence chatbots in obstetrics and gynecology medical education[J]. Am J Obstet Gynecol, 2025, 233( 1): 4- 11. DOI: 10.1016/j.ajog.2025.04.021.
[50]	KARARGYRIS A, UMETON R, SHELLER MJ, et al. Federated benchmarking of medical artificial intelligence with MedPerf[J]. Nat Mach Intell, 2023, 5( 7): 799- 810. DOI: 10.1038/s42256-023-00652-2.