肿瘤三级淋巴结构自动化评估的研究进展

摘要

三级淋巴结构（TLS）是形成于非淋巴组织中的异位免疫细胞聚集体，在癌症、自身免疫性疾病及器官移植排斥中具有关键的临床意义。TLS的存在、成熟度及空间分布与肿瘤患者的生存预后及免疫检查点抑制剂的疗效密切相关。在胃癌及结直肠癌中，TLS展现出重要的预后与治疗预测价值。然而，传统人工评估方法耗时费力且主观性强，难以满足大规模临床应用的需求。综述TLS自动化评估的研究进展及其临床应用。

关键词

三级淋巴结构 / 人工智能 / 数字病理 / 免疫治疗预测

参考文献

[1] Guillaume SM , Beccaria CG , Iannacone M , et al. Tertiary lymphoid structures across organs: context, composition, and clinical levers[J]. Immunol Rev, 2025, 335(1): e70063. DOI: 10.1111/imr.70063.

[2] Taniguchi K , Yoshikawa T , Yanagita M . The roles of tertiary lymphoid structures in orchestrating immune responses in peripheral organs[J]. Inflamm Regen, 2025, 45(1): 28. DOI: 10.1186/s41232—025—00393—2.

[3] Cui X , Gu X , Li D , et al. Tertiary lymphoid structures as a biomarker in immunotherapy and beyond: Advancing towards clinical application[J]. Cancer Lett, 2025, 613: 217491. DOI: 10.1016/j.canlet.2025.217491.

[4] Domblides C , Rochefort J , Riffard C , et al. Tumor—associated tertiary lymphoid structures: from basic and clinical knowledge to therapeutic manipulation[J]. Front Immunol, 2021, 12: 698604. DOI: 10.3389/fimmu.2021.698604.

[5] Suzuki H , Maruya Y , Inomata S , et al. Clinical significance and future prospects of tertiary lymphoid structure in lung cancer[J]. Gan To Kagaku Ryoho, 2025, 52(9): 628-632.

[6] Zhang J , Song Z , Zhang Y , et al. Recent advances in biomarkers for predicting the efficacy of immunotherapy in non—small cell lung cancer[J]. Front Immunol, 2025, 16: 1554871. DOI: 10.3389/fimmu.2025.1554871.

[7] Lewis MJ . Predicting best treatment in rheumatoid arthritis[J]. Semin Arthritis Rheum, 2024, 64: 152329. DOI: 10.1016/j.semarthrit.2023.152329.

[8] Zhang Y , Xu M , Ren Y , et al. Tertiary lymphoid structural heterogeneity determines tumour immunity and prospects for clinical application[J]. Mol Cancer, 2024, 23(1): 75. DOI: 10.1186/s12943—024—01980—6.

[9] Papiris SA , Kollintza A , Kitsanta P , et al. Relationship of BAL and lung tissue CD4 ⁺ and CD8 ⁺ T lymphocytes, and their ratio in idiopathic pulmonary fibrosis [J]. Chest, 2005, 128(4): 2971-2977. DOI: 10.1378/chest.128.4.2971.

[10] Vallée A , Drezet A , Arutkin M . Pan—cancer convergence of tumour—immune microenvironment motifs revealed by CyTOF and imaging mass cytometry[J]. Front Immunol, 2025, 16: 1672312. DOI: 10.3389/fimmu.2025.1672312.

[11] Yang M , Che Y , Li K , et al. Detection and quantitative analysis of tumor—associated tertiary lymphoid structures[J]. J Zhejiang Univ SCI B, 2023, 24(9): 779-795. DOI: 10.1631/jzus.B2200605.

[12] Barmpoutis P , Di Capite M , Kayhanian H , et al. Tertiary lymphoid structures (TLS) identification and density assessment on H&E—stained digital slides of lung cancer[J]. PLoS One, 2021, 16(9): e0256907. DOI: 10.1371/journal.pone.0256907.

[13] Karri S , Aviel—Ronen S , Firer MA . Fractal and textural imaging identify new subgroups of patients with colorectal cancer based on biophysical properties of the cancer cells[J]. Pathol Res Pract, 2022, 238: 154040. DOI: 10.1016/j.prp.2022.154040.

[14] Li J , Shen Z , Liu D , et al. A novel prognostic model for lung squamous cell carcinoma based on multi—omics analysis and machine learning[J]. PLoS One, 2025, 20(12): e0336792. DOI: 10.1371/journal.pone.0336792.

[15] Wei Q , Jiang X , Miao X , et al. Molecular subtypes of lung adenocarcinoma patients for prognosis and therapeutic response prediction with machine learning on 13 programmed cell death patterns[J]. J Cancer Res Clin Oncol, 2023, 149(13): 11351-11368. DOI: 10.1007/s00432—023—05000—w.

[16] Kakraba S , Ayyadevara S , Yadem Clement A , et al. Machine learning—enhanced quantitative structure—activity relationship modeling for DNA polymerase inhibitor discovery: algorithm development and validation[J]. JMIR AI, 2025, 4: e77890— e77890. DOI: 10.2196/77890.

[17] Lin Y , Yu Y , Wang Q , et al. Machine learning model for predicting tertiary lymphoid structures and treatment response in triple—negative breast cancer[J]. NPJ Precis Oncol, 2025, 9(1): 216. DOI: 10.1038/s41698—025—01012—6.

[18] Liu X , Li D , Zhang Y , et al. Multi—algorithm—integrated tertiary lymphoid structure gene signature for immune landscape characterization and prognosis in colorectal cancer patients[J]. Biomedicines, 2024, 12(11): 2644. DOI: 10.3390/biomedicines12112644.

[19] Xu X , Jaberi—Douraki M , Wallace NA . Predicting the prognostic value of POLI expression in different cancers via a machine learning approach[J]. Int J Mol Sci, 2022, 23(15): 8571. DOI: 10.3390/ijms23158571.

[20] Li Z , Jiang Y , Li B , et al. Development and validation of a machine learning model for detection and classification of tertiary lymphoid structures in gastrointestinal cancers[J]. JAMA Netw Open, 2023, 6(1): e2252553. DOI: 10.1001/jamanetworkopen.2022.52553.

[21] Li S , Wang Z , Huang HD , et al. Machine learning—based characterization and identification of tertiary lymphoid structures using spatial transcriptomics data[J]. Int J Mol Sci, 2024, 25(7): 3887. DOI: 10.3390/ijms25073887.

[22] Koksoy AA , Salvatierra ME , MOSAIC Team, et al. TLS_Finder: an algorithm for identifying tertiary lymphoid structures using immune cell spatial coordinates[EB]. bioRxiv(preprint), 2024, 12.26.630405. DOI: 10.1101/2024.12.26.630405.

[23] Chen Z , Wang X , Jin Z , et al. Deep learning on tertiary lymphoid structures in hematoxylin—eosin predicts cancer prognosis and immunotherapy response[J]. npj Precis Oncol, 2024, 8(1): 73. DOI: 10.1038/s41698—024—00579—w.

[24] Van Rijthoven M , Obahor S , Pagliarulo F , et al. Multi—resolution deep learning characterizes tertiary lymphoid structures and their prognostic relevance in solid tumors[J]. Commun Med, 2024, 4(1): 5. DOI: 10.1038/s43856—023—00421—7.

[25] Zhao Z , Chen D , Wang R , et al. Multiview deep—learning—enabled histopathology for prognostic and therapeutic stratification in stage II colorectal cancer: a retrospective multicenter study[J]. PLoS Med, 2026, 23(1): e1004614. DOI: 10.1371/journal.pmed.1004614.

[26] Ghamry—Barrin S , Dieu—Nosjean MC , Panouillot M . Automated quantification of tertiary lymphoid structures in human tumor samples using immunofluorescence and AI—powered analysis pipeline[M]// Dieu—Nosjean MC . Tertiary lymphoid structures: Vol. 2864. New York, NY: Springer US, 2025: 205-229.

[27] Le Rochais M , Brahim I , Zeghlache R , et al. Automated classification of tertiary lymphoid structures in colorectal cancer using TLS—PAT artificial intelligence tool[J]. Sci Rep, 2025, 15(1): 9845. DOI: 10.1038/s41598—025—94664—0.

[28] Suzuki H , Hamada K , Hamanishi J , et al. Artificial intelligence—based spatial analysis of tertiary lymphoid structures and clinical significance for endometrial cancer[J]. Cancer Immunol Immunother, 2025, 74(3): 84. DOI: 10.1007/s00262—024—03929—6.

[29] Cox BP , Hannan RT , Batrash N , et al. Local, quantitative morphometry of fibroproliferative lung injury using laminin[J]. Am J Respir Cell Mol Biol, 2024, 71(1): 23-29. DOI: 10.1165/rcmb.2023—0294MA.

[30] Wu W , Xun Z , Han Y , et al. Artificial intelligence and multimodality data integration decipher tertiary lymphoid structure maturity in gastric cancer[J]. Cancer Res, 2025, 85(24): 5128-5140. DOI: 10.1158/0008—5472.CAN—25—1793.

[31] Hou X , Li X , Han Y , et al. Triple‐negative breast cancer survival prediction using artificial intelligence through integrated analysis of tertiary lymphoid structures and tumor budding[J]. Cancer, 2024, 130(S8): 1499-1512. DOI: 10.1002/cncr.35261.

[32] Ji IH , Lee JH , Kang MJ , et al. Artificial intelligence—based anomaly detection technology over encrypted traffic: a systematic literature review[J]. Sens, 2024, 24(3): 898. DOI: 10.3390/s24030898.

[33] Gao Q , Yao S , Du D , et al. Multimodal intelligent prediction model for in vitro fertilization[J]. NPJ Digital Med, 2026, 9(1): 147. DOI: 10.1038/s41746—025—02331—5.

[34] Kumar D , Bakariya B , Verma C , et al. LivXAI—net: an explainable AI framework for liver disease diagnosis with IoT—based real—time monitoring support[J]. Comput Methods Programs Biomed, 2025, 270: 108950. DOI: 10.1016/j.cmpb.2025.108950.

[35] Canat G , Duval A , Gidel—Dissler N , et al. A novel deep learning approach to identify embryo morphokinetics in multiple time lapse systems[J]. Sci Rep, 2024, 14(1): 29016. DOI: 10.1038/s41598—024—80565—1.

[36] Dissler N , Nogueira D , Keppi B , et al. Artificial intelligence—powered assisted ranking of sibling embryos to increase first cycle pregnancy rate[J]. Reprod Biomed Online, 2024, 49(1): 103887. DOI: 10.1016/j.rbmo.2024.103887.

[37] Luong TMT , Le NQK . Artificial intelligence in time—lapse system: advances, applications, and future perspectives in reproductive medicine[J]. J Assist Reprod Genet, 2024, 41(2): 239-252. DOI: 10.1007/s10815—023—02973—y.

[38] He M , Ye H , Liu L , et al. Comparative analysis of tertiary lymphoid structures for predicting survival of colorectal cancer: a whole—slide images—based study[J]. Precis Clin Med, 2024, 7(4): pbae030. DOI: 10.1093/pcmedi/pbae030.

[39] Guo X , Liu T , Yang Y , et al. Automatic segmentation of type A aortic dissection on computed tomography images using deep learning approach[J]. Diagnostics, 2024, 14(13): 1332. DOI: 10.3390/diagnostics14131332.

[40] Barb A , Fenesan M , Pirtea M , et al. Reassessing breast cancer—associated fibroblasts (CAFs) interactions with other stromal components and clinico—pathologic parameters by using immunohistochemistry and digital image analysis (DIA)[J]. Cancers, 2023, 15(15): 3823. DOI: 10.3390/cancers15153823.

[41] Cho YJ , Hwang I , Park S , et al. Prognostic effect of tertiary lymphoid structures in epstein—barr virus—associated gastric carcinomas measured by digital image analysis[J]. Lab Invest, 2024, 104(7): 102071. DOI: 10.1016/j.labinv.2024.102071.

[42] Berthe J , Poudel P , Segerer FJ , et al. Exploring the impact of tertiary lymphoid structures maturity in NSCLC: insights from TLS scoring[J]. Front Immunol, 2024, 15: 1422206. DOI: 10.3389/fimmu.2024.1422206.

[43] Le Rochais M , Morvan M , Bouzeloc S , et al. A tertiary lymphoid structures—based pathological score predicts survival and recurrence in colorectal Cancer patients[J]. Immunobiology, 2025, 230(3): 152911. DOI: 10.1016/j.imbio.2025.152911.

[44] Ling Y , Zhong J , Weng Z , et al. The prognostic value and molecular properties of tertiary lymphoid structures in oesophageal squamous cell carcinoma[J]. Clin Transl Med, 2022, 12(10): e1074. DOI: 10.1002/ctm2.1074.

[45] Deng M , Liu X , Jiang Y , et al. Tertiary lymphoid structures’ pattern and prognostic value in primary adenocarcinoma of jejunum and ileum[J]. World J Surg Oncol, 2024, 22(1): 261. DOI: 10.1186/s12957—024—03543—x.

[46] Westbom—Fremer S , Tran L , Ebbesson A , et al. Tertiary lymphoid structures in high—grade serous tubo—ovarian carcinoma: anatomical site matters[J]. Cancer Immunol, Immunother, 2025, 74(2): 56. DOI: 10.1007/s00262—024—03911—2.

[47] Liu X , Deng J , Yu B , et al. Tertiary lymphoid structures—driven immune infiltration patterns and their association with survival in neuroblastoma[J]. PeerJ, 2025, 13: e19767. DOI: 10.7717/peerj.19767.

[48] Ruiz—Torres DA , Bryan ME , Hirayama S , et al. Spatial characterization of tertiary lymphoid structures as predictive biomarkers for immune checkpoint blockade in head and neck squamous cell carcinoma[J]. Onco Immunology, 2025, 14(1): 2466308. DOI: 10.1080/2162402X.2025.2466308.

[49] Lin YJ , Ou DL , Su YY , et al. Nivolumab plus ipilimumab for potentially resectable hepatocellular carcinoma: Long—term efficacy and biomarker exploration[J]. J Hepatol, 2026, 84(2): 316-328. DOI: 10.1016/j.jhep.2025.08.035.

[50] 李治楷， 王建波 . 成熟三级淋巴结构与胃癌新辅助免疫治疗疗效及预后的关系[J]. 中国现代普通外科进展， 2025， 28（8）： 607-611.

[51] Peng Y , Chen M , Liang T , et al. Distribution and maturity of tertiary lymphoid structures predict recurrence—free survival in cervical cancer[J]. Int J Gynecol Cancer, 2026, 36(1): 102718. DOI: 10.1016/j.ijgc.2025.102718.

[52] Long S , Li M , Chen J , et al. Spatial patterns and MRI—based radiomic prediction of high peritumoral tertiary lymphoid structure density in hepatocellular carcinoma: a multicenter study[J]. J ImmunoTher Cancer, 2024, 12(12): e009879. DOI: 10.1136/jitc—2024—009879.

[53] Datta RR , Schran S , Persa OD , et al. Post—transplant malignancies show reduced T—cell abundance and tertiary lymphoid structures as correlates of impaired cancer immunosurveillance[J]. Clin Cancer Res, 2022, 28(8): 1712-1723. DOI: 10.1158/1078—0432.CCR—21—3746.

[54] Ahmed A , Halama N . Tertiary lymphoid structures in colorectal cancer liver metastases: association with immunological and clinical parameters and chemotherapy response[J]. Anticancer Res, 2020, 40(11): 6367-6373. DOI: 10.21873/anticanres.14657.