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OA
Artificial intelligence combined with multimodal imaging in establishing a new precision surgical diagnosis and treatment system for lymph node metastasis in intrahepatic cholangiocarcinoma
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(hepa-tocellular 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.
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.
王傅民;任耀星;韩大为;陆镜明;吕毅;张谞丰
西安交通大学第一附属医院肝胆外科,陕西 西安 710061||西安交通大学未来技术学院,陕西 西安 710049西安交通大学第一附属医院肝胆外科,陕西 西安 710061||西安交通大学未来技术学院,陕西 西安 710049西安交通大学第一附属医院肝胆外科,陕西 西安 710061||西安交通大学未来技术学院,陕西 西安 710049西安交通大学第一附属医院肝胆外科,陕西 西安 710061||西安交通大学未来技术学院,陕西 西安 710049西安交通大学第一附属医院肝胆外科,陕西 西安 710061||西安交通大学未来技术学院,陕西 西安 710049西安交通大学第一附属医院肝胆外科,陕西 西安 710061||西安交通大学未来技术学院,陕西 西安 710049
医药卫生
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
intrahepatic cholangiocarcinomalymph node metastasisradiomicsdeep learningnear-infrared II imagingselective lymphadenectomy
《西安交通大学学报（医学版）》 2026 (3)
447-454,8
国家自然科学基金国际(地区)合作与交流项目(No.W2511094)Supported by International(Regional)Cooperation and Exchange Project of the National Natural Science Foundation of China(No.W2511094)
评论