人工智能联合多模态成像构建肝内胆管癌淋巴结转移精准外科诊疗新体系

Artificial intelligence combined with multimodal imaging in establishing a new precision surgical diagnosis and treatment system for lymph node metastasis in intrahepatic cholangiocarcinoma

摘要

摘要：肝内胆管癌(intrahepatic cholangiocarcinoma, ICC)作为原发性肝脏恶性肿瘤,尽管发病率低于肝细胞癌(hepatocellular carcinoma, HCC),但其预后极差,根治性切除术后5年复发率高达60%以上,而淋巴结转移(lymph node metastasis, LNM)是导致复发和生存率低的关键因素。当前ICC术中淋巴结清扫(lymphadenectomy, LND)的临床应用存在显著争议:常规LND可能增加手术风险并影响免疫治疗效果,而选择性LND的实施亟需术前精准的LNM预测和术中淋巴结可视化技术的支持。然而,传统影像学手段(如CT、MRI)对LNM的敏感性和特异性不足(敏感性45%～50%,特异性86.4%～88%),难以满足精准诊疗需求。本文聚焦于整合人工智能与新型成像技术构建并解决这一难题的研究框架:在术前诊断中,通过影像组学(radiomics)、生境分析(habitat analysis)及深度学习模型(如CNN、Transformer),从多模态影像中提取肿瘤异质性特征和淋巴结转移风险标志物,构建高精度LNM预测系统。通过“术前AI预测-术中精准显影”的全流程技术整合,提出“选择性LND”策略,旨在为LNM高风险患者提供精准清扫依据,同时避免低风险患者过度手术损伤,最终优化ICC个体化治疗决策。

Abstract

ABSTRACT: Intrahepatic cholangiocarcinoma (ICC), as a primary liver malignancy, has a lower incidence than hepatocellular carcinoma (HCC). However, its prognosis is extremely poor, with a recurrence rate of over 60% within five years after radical resection. Lymph node metastasis (LNM) is a key factor leading to recurrence and low survival rates. Currently, there are significant controversies regarding the clinical application of intraoperative lymphadenectomy (LND) for ICC. Routine LND may increase surgical risks and affect the efficacy of immunotherapy. The implementation of selective LND urgently requires accurate preoperative prediction of LNM and intraoperative lymph node visualization techniques. Nevertheless, traditional imaging methods (such as CT and MRI) have insufficient sensitivity and specificity for LNM (sensitivity: 45%-50%, specificity: 86.4%-88%), making it difficult to meet the needs of precise diagnosis and treatment. This paper focuses on constructing a research framework to solve this problem by integrating artificial intelligence and novel imaging technologies. In preoperative diagnosis, through radiomics, habitat analysis, and deep-learning models (such as CNN and Transformer), tumor heterogeneity features and lymph node metastasis risk markers are extracted from multimodal images to build a high-precision LNM prediction system. Through the full-process technical integration of “preoperative AI prediction-intraoperative precise visualization”, the “selective LND” strategy is proposed. This strategy aims to provide a basis for precise lymph node dissection in patients at high risk of LNM while avoiding excessive surgical damage to low-risk patients, ultimately optimizing the individualized treatment decision-making for ICC. This paper further explores the application potential of multidisciplinary cross-cutting technologies (imaging medicine, artificial intelligence, and molecular probe design) in breaking through the bottleneck of LNM diagnosis, providing theoretical support and technical approaches for improving the precision of ICC surgical treatment and patient prognosis.

关键词

肝内胆管癌 / 淋巴结转移 / 影像组学 / 深度学习 / 近红外二区成像 / 选择性淋巴结清扫

Key words

intrahepatic cholangiocarcinoma / lymph node metastasis / radiomics / deep learning / near-infrared II imaging / selective lymphadenectomy

参考文献

[1] WANG T J, XU C R, ZHANG Z J, et al. Cellular heterogeneity and transcriptomic profiles during intrahepatic cholangiocarcinoma initiation and progression[J]. Hepatology, 2022, 76(5): 1302-1317.

[2] SUNG H, FERLAY J, SIEGEL R L, et al. Global cancer statistics 2020: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries[J]. CA Cancer J Clin, 2021, 71(3): 209-249.

[3] MAVROS M N, ECONOMOPOULOS K P, ALEXIOU V G, et al. Treatment and prognosis for patients with intrahepatic cholangiocarcinoma: systematic review and meta—analysis[J]. JAMA Surg, 2014, 149(6): 565-574.

[4] DEOLIVEIRA M L, CUNNINGHAM S C, CAMERON J L, et al. Cholangiocarcinoma: thirty—one—year experience with 564 patients at a single institution[J]. Ann Surg, 2007, 245(5): 755-762.

[5] MORIS D, PALTA M, KIM C, et al. Advances in the treatment of intrahepatic cholangiocarcinoma: an overview of the current and future therapeutic landscape for clinicians[J]. CA Cancer J Clin, 2023, 73(2): 198-222.

[6] ZHU H, DOG ˇAN B E. American Joint Committee on Cancer's Staging System For Breast Cancer, eighth edition: summary for clinicians[J]. Eur J Breast Health, 2021, 17(3): 234-238.

[7] ZHANG X F, BEAL E W, BAGANTE F, et al. Early versus late recurrence of intrahepatic cholangiocarcinoma after resection with curative intent[J]. Br J Surg, 2018, 105(7): 848-856.

[8] ZHANG X F, LV Y, WEISS M, et al. Should utilization of lymphadenectomy vary according to morphologic subtype of intrahepatic cholangiocarcinoma?[J]. Ann Surg Oncol, 2019, 26(7): 2242-2250.

[9] ZHANG X F, XUE F, DONG D H, et al. Number and station of lymph node metastasis after curative—intent resection of intrahepatic cholangiocarcinoma impact prognosis[J]. Ann Surg, 2021, 274(6): e1187-e1195.

[10] ZHANG X F, CHAKEDIS J, BAGANTE F, et al. Trends in use of lymphadenectomy in surgery with curative intent for intrahepatic cholangiocarcinoma[J]. Br J Surg, 2018, 105(7): 857-866.

[11] CHUN Y S, PAWLIK T M, VAUTHEY J N. 8th edition of the AJCC cancer staging manual: pancreas and hepatobiliary cancers[J]. Ann Surg Oncol, 2018, 25(4): 845-847.

[12] JUTRIC Z, JOHNSTON W C, HOEN H M, et al. Impact of lymph node status in patients with intrahepatic cholangiocarcinoma treated by major hepatectomy: a review of the national cancer database[J]. HPB (Oxford), 2016, 18(1): 79-87.

[13] YEOW M, FONG K Y, ZHAO J J, et al. Value of lymph node dissection in intrahepatic cholangiocarcinoma: a systematic review and meta—analysis[J]. HPB (Oxford), 2024, 26(2): 161-170.

[14] RAHIM M K, OKHOLM T, JONES K B, et al. Dynamic CD8+ T cell responses to cancer immunotherapy in human regional lymph nodes are disrupted in metastatic lymph nodes[J]. Cell, 2023, 186(6): 1127-1143.

[15] MORINE Y, SHIMADA M. The value of systematic lymph node dissection for intrahepatic cholangiocarcinoma from the viewpoint of liver lymphatics[J]. J Gastroenterol, 2015, 50(9): 913-927.

[16] JIANG L, TAN H, PANJE C M, et al. Role of¹⁸F—FDG PET/CT imaging in intrahepatic cholangiocarcinoma[J]. Clin Nucl Med, 2016, 41(1): 1-7.

[17] HU Z, FANG C, LI B, et al. First—in—human liver—tumour surgery guided by multispectral fluorescence imaging in the visible and near—infrared—Ⅰ/Ⅱ windows[J]. Nat Biomed Eng, 2020, 4(3): 259-271.

[18] YANG Y, CHEN M, WANG P, et al. Highly thermal stable RNase A@PbS/ZnS quantum dots as NIR—IIb image contrast for visualizing temporal changes of microvasculature remodelling in flap[J]. J Nanobiotechnol, 2022, 20(1): 128.

[19] YU Y, HE Z, OUYANG J, et al. Magnetic resonance imaging radiomics predicts preoperative axillary lymph node metastasis to support surgical decisions and is associated with tumor microenvironment in invasive breast cancer: a machine learning, multicenter study[J]. EBioMedicine, 2021, 69: 103460.

[20] ZHENG Y, QIU B, LIU S, et al. A transformer—based deep learning model for early prediction of lymph node metastasis in locally advanced gastric cancer after neoadjuvant chemotherapy using pretreatment CT images[J]. EClinicalMedicine, 2024, 75: 102805.

[21] EL—DIWANY R, PAWLIK T M, EJAZ A. Intrahepatic cholangiocarcinoma[J]. Surg Oncol Clin N Am, 2019, 28(4): 587-599.

[22] SHIMADA K, SANO T, NARA S, et al. Therapeutic value of lymph node dissection during hepatectomy in patients with intrahepatic cholangiocellular carcinoma with negative lymph node involvement[J]. Surgery, 2009, 145(4): 411-416.

[23] NOJI T, KONDO S, HIRANO S, et al. CT evaluation of paraaortic lymph node metastasis in patients with biliary cancer[J]. J Gastroenterol, 2005, 40(7): 739-743.

[24] BAE S U, WON K S, SONG B I, et al. Accuracy of F—18 FDG PET/CT with optimal cut—offs of maximum standardized uptake value according to size for diagnosis of regional lymph node metastasis in patients with rectal cancer[J]. Cancer Imaging, 2018, 18(1): 32.

[25] LI X, YANG L, JIANG F, et al. Integration of radiomics and immune—related genes signatures for predicting axillary lymph node metastasis in breast cancer[J]. Clin Breast Cancer, 2025, 25(1): e40-e47.

[26] YIN G T, SONG Y C, LI X F, et al. Prediction of mediastinal lymph node metastasis based on¹⁸F—FDG PET/CT imaging using support vector machine in non—small cell lung cancer[J]. Eur Radiol, 2021, 31(6): 3983-3992.

[27] ZWITTAG P, ASEL C, GABRIEL M, et al. MRI and PET/CT in the assessment of lymph node metastases in head and neck cancer[J]. Sci Rep, 2023, 13(1): 19347.

基金资助

国家自然科学基金国际(地区)合作与交流项目(W2511094)