数智病理驱动的诊疗闭环模式创新与工程实现路径研究
Diagnostic-Therapeutic Closed-Loop Model Driven by Digital-Intelligent Pathology: Engineering Pathway and Implementation
在全切片图像、空间组学与自监督预训练等技术的驱动下,数智病理(DIP)正推动病理学由传统经验诊断转向数据智能驱动的工程化新范式。在此基础上,DIP 正构建面向临床与制药需求的一体化工程系统,形成“诊断 ‒ 治疗 ‒ 反馈”的闭环。本文系统探讨DIP 的技术演进,聚焦大规模自监督基础模型、跨模态虚拟染色、病理 ‒ 组学对齐与肿瘤微环境建模等关键进展;总结其在自动化分级、多任务学习、肿瘤微环境解析与基因型 ‒ 表型预测中的核心能力。进一步结合靶点发现、机制研究、毒理评估与精准临床试验等应用实例,阐明 DIP 如何赋能功能表型挖掘、革新药效预测与患者分层,并释放可转化的临床与产业价值。最后,分析数据标准化、跨中心泛化、可解释性与监管治理等面临的关键挑战,展望DIP在多模态、可信人工智能驱动下形成可持续迭代的“诊断 ‒ 治疗 ‒ 反馈”闭环。面向国家生物医药与健康体系建设,DIP有望作为“转化医学工程核心枢纽”,持续推动病理学由“诊断科学”迈向“治疗引擎”。这标志着,DIP已成为连接临床决策与药物研发、支撑我国生物医药产业源头创新与研发提效的关键支撑。
Driven by technologies such as whole-slide imaging (WSI), spatial omics, and self-supervised pretraining, digital-intelligent pathology (DIP) is shifting pathology from traditional experience-based diagnosis toward a new data-intelligence-driven engineering paradigm. Building on these advances, DIP is establishing an integrated engineering system tailored to clinical and pharmaceutical needs, thereby forming a closed loop of diagnosis‒treatment‒Response. This study outlines the technological evolution of DIP, focusing on large-scale self-supervised foundation models, cross-modal virtual staining, pathology‒omics alignment, and tumor microenvironment (TME) modeling. It also outlines DIP's core functions: automated grading, multi-task learning, TME characterization, and genotype-phenotype mapping. Through examples in target discovery, mechanism studies, toxicity assessment, and precision trials, the study demonstrates how DIP enables functional phenotype mining, improves efficacy prediction and patient stratification, and delivers clinical and industrial value. Moreover, it explores challenges regarding data standardization, cross-center generalization, interpretability, and regulatory governance, and envisions DIP evolving, through multimodal and trustworthy artificial intelligence, into a sustainable "diagnosis‒treatment‒Response" loop. For the development of national biopharmaceutical and health systems in China, DIP is positioned as a "core hub for translational medical engineering," steadily advancing pathology from a diagnostic science to a therapeutic engine. This suggests that DIP could become an important link between clinical decision-making and drug R&D, bolstering original innovation and R&D efficiency of China's biopharmaceutical industry.
| [1] |
平轶芳,闫红,卞修武. 人工智能病理在肿瘤精准医疗时代的应用与挑战[J]. 生命科学,2022,34(8):929-940. |
| [2] |
Ping Y F,Yan H,Bian X W. Artificial intelligence pathology in the age of oncology precision medicine:Applications and challenges[J]. Chinese Bulletin of Life Sciences,2022,34(8):929-940. |
| [3] |
彭先稳,班宁溥,缐霂, 人工智能在血液病理诊断中的应用进展[J]. 临床与实验病理学杂志,2025,41(8):1057-1061. |
| [4] |
Peng X W,Ban N P,Xian M,et al. Progress of artificial intelligence application in hematopathology diagnosis[J]. Chinese Journal of Clinical and Experimental Pathology,2025,41(8):1057-1061. |
| [5] |
程亚林,郭颖,杨鑫鑫, 人工智能在头颈鳞状细胞癌病理实践中的应用进展[J]. 临床与实验病理学杂志,2025,41(4):498-503. |
| [6] |
Cheng Y L,Guo Y,Yang X X,et al. Advances in the application of artificial intelligence in the pathological practice of head and neck squamous cell carcinoma[J]. Chinese Journal of Clinical and Experimental Pathology,2025,41(4):498-503. |
| [7] |
杨卓文,郑智中,李斌, 人工智能系统在预测肺结节良恶性和病理分型中的临床应用[J]. 中国胸心血管外科临床杂志,2025,32(8):1086-1095. |
| [8] |
Yang Z W,Zheng Z Z,Li B,et al. Clinical application of an artificial intelligence system in predicting benign or malignant pulmonary nodules and pathological subtypes[J]. Chinese Journal of Clinical Thoracic and Cardiovascular Surgery,2025,32(8):1086-1095. |
| [9] |
黄文君,李巧巧,敬文斌, 不同WHO肺癌病理分类下人工智能对肺结节良恶性的诊断效能 [J]. 临床放射学杂志,2025,44(1):76-81. |
| [10] |
Huang W J,Li Q Q,Jing W B,et al. Diagnostic performance of artificial intelligence on benign and malignant pulmonary nodules under different WHO pathological classifications of lung cancer[J]. Journal of Clinical Radiology,2025,44(1):76-81. |
| [11] |
Liu B J,Polack M,Coudray N,et al. Self-supervised learning reveals clinically relevant histomorphological patterns for therapeutic strategies in colon cancer[J]. Nature Communications,2025,16:2328. |
| [12] |
步宏. 数字病理科和病理人工智能发展现状与展望[J]. 临床与实验病理学杂志,2023,39(7):769-771. |
| [13] |
Bu H. Current status and future perspectives of digital pathology and artificial intelligence in pathology[J]. Chinese Journal of Clinical and Experimental Pathology,2023,39(7):769-771. |
| [14] |
Wang T,Jia X L,Aleksunes L M,et al. Developmental toxicity:Artificial intelligence-powered assessments[J]. Trends in Pharmacological Sciences,2025,46(6):486-502. |
| [15] |
Bai C S,Wu L L,Li R J,et al. Machine learning-enabled drug-induced toxicity prediction[J]. Advanced Science,2025,12(16):2413405. |
| [16] |
Ahn B,Moon D,Kim H S,et al. Histopathologic image-based deep learning classifier for predicting platinum-based treatment responses in high-grade serous ovarian cancer[J]. Nature Communications,2024,15:4253. |
| [17] |
Zhang P,Gao C F,Zhang Z Y,et al. Systematic inference of super-resolution cell spatial profiles from histology images[J]. Nature Communications,2025,16:1838. |
| [18] |
Alsaedi S,Gao X,Gojobori T. Beyond digital twins:The role of foundation models in enhancing the interpretability of multiomics modalities in precision medicine[J]. FEBS Open Bio,2025,15(8):1192-1208. |
| [19] |
陈晓红,刘浏,牛雅娟, 数智病理平台构建及服务模式研究[J]. 中国工程科学,2025,27(2):304-314. |
| [20] |
Chen X H,Liu L,Niu Y J,et al. Digital intelligence pathology platform and its service pattern[J]. Strategic Study of CAE,2025,27(2):304-314. |
| [21] |
焦一平,王向学,徐军. 计算病理学应用研究进展与挑战[J]. 协和医学杂志,2022,13(4):535-541. |
| [22] |
Jiao Y P,Wang X X,Xu J. Advances and challenges in applied computational pathology[J]. Medical Journal of Peking Union Medical College Hospital,2022,13(4):535-541. |
| [23] |
Duggento A,Conti A,Mauriello A,et al. Deep computational pathology in breast cancer[J]. Seminars in Cancer Biology,2021,72:226-237. |
| [24] |
Dang C R,Qi Z,Xu T,et al. Deep learning‒powered whole slide image analysis in cancer pathology[J]. Laboratory Investigation,2025,105(7):104186. |
| [25] |
Masjoodi S,Anbardar M H,Shokripour M,et al. Whole slide imaging (WSI) in pathology:Emerging trends and future applications in clinical diagnostics,medical education,and pathology[J]. Iranian Journal of Pathology,2025,20(3):257-265. |
| [26] |
Schouten D,Nicoletti G,Dille B,et al. Navigating the landscape of multimodal AI in medicine:A scoping review on technical challenges and clinical applications[J]. Medical Image Analysis,2025,105:103621. |
| [27] |
Gim N,Ferguson A N,Blazes M,et al. The March to harmonized imaging standards for retinal imaging [J]. Progress in Retinal and Eye Research,2025,107:101363. |
| [28] |
Hanser T. Federated learning for molecular discovery[J]. Current Opinion in Structural Biology,2023,79:102545. |
| [29] |
Chen R J,Wang J J,Williamson D F K,et al. Algorithmic fairness in artificial intelligence for medicine and healthcare[J]. Nature Biomedical Engineering,2023,7(6):719-742. |
| [30] |
Cireşan D C,Giusti A,Gambardella L M,et al. Mitosis detection in breast cancer histology images with deep neural networks[C]//Medical Image Computing and Computer-Assisted Intervention ‒ MICCAI 2013,2013:411-418. |
| [31] |
Litjens G,Kooi T,Bejnordi B E,et al. A survey on deep learning in medical image analysis[J]. Medical Image Analysis,2017,42:60-88. |
| [32] |
Campanella G,Hanna M G,Geneslaw L,et al. Clinical-grade computational pathology using weakly supervised deep learning on whole slide images[J]. Nature Medicine,2019,25(8):1301-1309. |
| [33] |
Lu M Y,Williamson D F K,Chen T Y,et al. Data-efficient and weakly supervised computational pathology on whole-slide images[J]. Nature Biomedical Engineering,2021,5(6):555-570. |
| [34] |
Shao Z,Bian H,Chen Y,et al. Transmil:Transformer based correlated multiple instance learning for whole slide image classification[PP/OL]. arXiv(2021-10-31)[2026-02-02].https://arxiv.org/abs/2106.00908. DOI:10.48550/arXiv.2106.00908. |
| [35] |
Xu H M,Xu Q,Cong F Y,et al. Vision transformers for computational histopathology[J]. IEEE Reviews in Biomedical Engineering,2024,17:63-79. |
| [36] |
杨帆. 多模态医学数据融合技术及应用[J]. 山东大学学报(医学版),2025,63(8):17-40. |
| [37] |
Yang F. Multimodal medical data fusion technology and its application[J]. Journal of Shandong University (Health Science),2025,63(8):17-40. |
| [38] |
Campanella G,Chen S J,Singh M,et al. A clinical benchmark of public self-supervised pathology foundation models[J]. Nature Communications,2025,16:3640. |
| [39] |
Yang Z J,Guo C Y,Li J Y,et al. An explainable multimodal artificial intelligence model integrating histopathological microenvironment and EHR phenotypes for germline genetic testing in breast cancer[J]. Advanced Science,2025,12(31):e02833. |
| [40] |
Arango-Argoty G,Kipkogei E,Stewart R,et al. Pretrained transformers applied to clinical studies improve predictions of treatment efficacy and associated biomarkers[J]. Nature Communications,2025,16:2101. |
| [41] |
Howard F M,Hieromnimon H M,Ramesh S,et al. Generative adversarial networks accurately reconstruct pan-cancer histology from pathologic,genomic,and radiographic latent features[J]. Science Advances,2024,10(46):eadq0856. |
| [42] |
Xu H W,Usuyama N,Bagga J,et al. A whole-slide foundation model for digital pathology from real-world data[J]. Nature,2024,630(8015):181-188. |
| [43] |
Lu M Y,Chen B W,Williamson D F K,et al. A visual-language foundation model for computational pathology[J]. Nature Medicine,2024,30(3):863-874. |
| [44] |
Kipf T N,Welling M. Semi-supervised classification with graph convolutional networks[PP/OL]. arXiv(2016-11-03)[2026-02-02].https://arxiv.org/abs/1609.02907. DOI:10.48550/arXiv.1609.02907. |
| [45] |
Hamilton W L,Ying R,Leskovec J. Inductive representation learning on large graphs[PP/OL]. arXiv(2017-11-08)[2026-02-02].https://arxiv.org/abs/1706.02216. DOI:10.48550/arXiv.1706.02216. |
| [46] |
Pang M X,Roy T K,Wu X D,et al. CelloType:A unified model for segmentation and classification of tissue images[J]. Nature Methods,2025,22(2):348-357. |
| [47] |
Xu K,Hu W,Leskovec J,Jegelka S. How powerful are graph neural networks?[PP/OL]. arXiv (2018-12-26)[2026-02-02]. https://arxiv.org/abs/1810.00826. DOI:10.48550/arXiv.1810.00826. |
| [48] |
Hou W T,Yu L Q,Lin C X,et al. H2-MIL:Exploring hierarchical representation with heterogeneous multiple instance learning for whole slide image analysis[J]. Proceedings of the AAAI Conference on Artificial Intelligence,2022,36(1):933-941. |
| [49] |
Vanguri R S,Luo J,Aukerman A T,et al. Multimodal integration of radiology,pathology and genomics for prediction of response to PD-(L)1 blockade in patients with non-small cell lung cancer[J]. Nature Cancer,2022,3(10):1151-1164. |
| [50] |
Yuan W,Chen Y J,Zhu B Y,et al. Pancancer outcome prediction via a unified weakly supervised deep learning model[J]. Signal Transduction and Targeted Therapy,2025,10:285. |
| [51] |
Han L L,Zhao H. Heterogeneous network representation learning via multiple attention mechanisms[J]. Knowledge-Based Systems,2025,330:114747. |
| [52] |
Brussee S,Buzzanca G,Schrader A M R,et al. Graph neural networks in histopathology:Emerging trends and future directions[J]. Medical Image Analysis,2025,101:103444. |
| [53] |
Ektefaie Y,Dasoulas G,Noori A,et al. Multimodal learning with graphs[J]. Nature Machine Intelligence,2023,5(4):340-350. |
| [54] |
Wang Y N,Wang Y G,Hu C Y,et al. Cell graph neural networks enable the precise prediction of patient survival in gastric cancer[J]. npj Precision Oncology,2022,6:45. |
| [55] |
Elhanani O,Ben-Uri R,Keren L. Spatial profiling technologies illuminate the tumor microenvironment [J]. Cancer Cell,2023,41(3):404-420. |
| [56] |
Risom T,Glass D R,Averbukh I,et al. Transition to invasive breast cancer is associated with progressive changes in the structure and composition of tumor stroma[J]. Cell,2022,185(2):299-310.e18. |
| [57] |
Shiao S L,Gouin K H III,Ing N,et al. Single-cell and spatial profiling identify three response trajectories to pembrolizumab and radiation therapy in triple negative breast cancer[J]. Cancer Cell,2024,42(1):70-84.e8. |
| [58] |
Pati P,Karkampouna S,Bonollo F,et al. Accelerating histopathology workflows with generative AI-based virtually multiplexed tumour profiling[J]. Nature Machine Intelligence,2024,6(9):1077-1093. |
| [59] |
Chen F Q,Zhang R R,Zheng B Y,et al. Pathological semantics-preserving learning for H&E-to-IHC virtual staining[C]//Medical Image Computing and Computer Assisted Intervention ‒ MICCAI 2024,2024:384-394. |
| [60] |
Park J,Shin S J,Kim G,et al. Revealing 3D microanatomical structures of unlabeled thick cancer tissues using holotomography and virtual H&E staining [J]. Nature Communications,2025,16:4781. |
| [61] |
Cui C,Liu H,Liu Q,et al. Survival Prediction of Brain Cancer with Incomplete Radiology,Pathology,Genomic,and Demographic Data[C]//Medical Image Computing and Computer Assisted Intervention ‒ MICCAI 2022,2022:626-635. |
| [62] |
Chen R J,Lu M Y,Williamson D F K,et al. Pan-cancer integrative histology-genomic analysis via multimodal deep learning[J]. Cancer Cell,2022,40(8):865-878.e6. |
| [63] |
Jaume G,Oldenburg L,Vaidya A,et al. Transcriptomics-guided slide representation learning in computational pathology[PP/OL]. arXiv (2024-05-18)[2026-02-02].https://arxiv.org/abs/2405.11618. DOI:10.48550/arXiv.2405.11618. |
| [64] |
Chen W Q,Zhang P Z,Tran T N,et al. A visual-omics foundation model to bridge histopathology with spatial transcriptomics[J]. Nature Methods,2025,22(7):1568-1582. |
| [65] |
Tiwari A,Mishra S,Kuo T R. Current AI technologies in cancer diagnostics and treatment[J]. Molecular Cancer,2025,24(1):159. |
| [66] |
Ding K X,Zhou M,Wang H,et al. Spatially aware graph neural networks and cross-level molecular profile prediction in colon cancer histopathology:A retrospective multi-cohort study[J]. The Lancet Digital Health,2022,4(11):e787-e795. |
| [67] |
Liao Y H,Chen X H,Hu S P,et al. Artificial intelligence for predicting HER2 status of gastric cancer based on whole-slide histopathology images:A retrospective multicenter study[J]. Advanced Science,2025,12(10):e2408451. |
| [68] |
Dara S,Dhamercherla S,Jadav S S,et al. Machine learning in drug discovery:A review[J]. Artificial Intelligence Review,2022,55(3):1947-1999. |
| [69] |
Seal S,Trapotsi M A,Spjuth O,et al. Cell painting:A decade of discovery and innovation in cellular imaging[J]. Nature Methods,2025,22(2):254-268. |
| [70] |
Chen L,Wu B F,Mo L,et al. High-content screening identifies ganoderic acid A as a senotherapeutic to prevent cellular senescence and extend healthspan in preclinical models[J]. Nature Communications,2025,16:2878. |
| [71] |
Jasti J,Zhong H,Panwar V,et al. Histopathology based AI model predicts anti-angiogenic therapy response in renal cancer clinical trial[J]. Nature Communications,2025,16:2610. |
| [72] |
Shmatko A,Jung A W,Gaurav K,et al. Learning the natural history of human disease with generative transformers[J]. Nature,2025,647(8088):248-256. |
| [73] |
Park D,Lee Y M,Eo T,et al. Multimodal AI model for preoperative prediction of axillary lymph node metastasis in breast cancer using whole slide images[J]. npj Precision Oncology,2025,9:131. |
| [74] |
Patkar S,Chen A,Basnet A,et al. Predicting the tumor microenvironment composition and immunotherapy response in non-small cell lung cancer from digital histopathology images[J]. npj Precision Oncology,2024,8:280. |
| [75] |
陈晓红,刘晓亮,王俊普,从AI驱动到元宇宙赋能:病理诊断管理模式创新与扩展[J/OL].中国管理科学,2025-06-16.https://doi-org-s-11.libdb.csu.edu.cn/10.16381/j.cnki.issn1003-207x.2023.1211. |
| [76] |
Chen X H,Liu X L,Wang J P,et al. From AI-driven to metaverse-empowered:Innovation and expansion of pathological diagnosis management models [J/OL].Chinese Journal of Management Science,2025-06-16. https://doi-org-s-11.libdb.csu.edu.cn/10.16381/j.cnki.issn1003-207x.2023.1211. |
| [77] |
Mao N,Dai Y,Zhou H,et al. A multimodal and fully automated system for prediction of pathological complete response to neoadjuvant chemotherapy in breast cancer[J]. Science Advances,2025,11(18):eadr1576. |
| [78] |
Srinidhi C L,Ciga O,Martel A L. Deep neural network models for computational histopathology:A survey[J]. Medical Image Analysis,2021,67:101813. |
| [79] |
刘浏,张馨,张琪琪, 医疗领域大模型伦理风险识别、治理及前瞻研究[J]. 中国工程科学,2025,27(6):54-67. |
| [80] |
Liu L,Zhang X,Zhang Q Q,et al. Ethical risk identification,governance,and foresight of medical foundation models[J]. Strategic Study of CAE,2025,27(6):54-67. |
| [81] |
宋春龙,卢金波. 生成式人工智能审判应用与风险规制探究[J]. 湖北师范大学学报(哲学社会科学版),2025,45(5):10-17. |
| [82] |
Song C L,Lu J B. Research on the application and risk regulation of generative artificial intelligence in judicial trials[J]. Journal of Hubei Normal University (Philosophy and Social Science),2025,45(5):10-17. |
| [83] |
何精华. 智能革命与治理转型:生成式AI赋能公共决策的理论建构与制度创新[J]. 上海市社会主义学院学报,2025(3):16-49. |
| [84] |
He J H. Intelligent revolution and governance transformation:Theoretical framework and institutional innovation of generative AI-empowered public decision-making[J]. Journal of Shanghai Institute of Socialism,2025(3):16-49. |
芙蓉实验室项目(2024PT5111)
FuRong Laboratory Project(2024PT5111)
/
| 〈 |
|
〉 |