摘要
目的探索一种通过尿液高光谱成像技术对肾移植术后排斥反应进行快速、鉴别诊断的方法。方法收集118例肾移植术后受者的尿液样本中高光谱数据信息,构建深度学习模型对排斥反应类型进行诊断和分类。结果构建了一个基于34层残差网络(ResNet-34)的深度学习诊断模型,纳入了118例患者并将其划分为训练集与测试集。根据移植肾穿刺病理结果,将患者尿液样本分为5组:无排斥反应组、T细胞介导的排斥反应组、抗体介导的排斥反应组、混合排斥反应组及肾病复发组。结果显示,该模型对上述5组的诊断灵敏度分别为0.960、0.980、0.930、0.940和0.943,诊断特异度分别为0.983,0.993,0.997,0.989和0.989,总体诊断准确率达95.7%。结论本研究为肾移植术后排斥反应的鉴别诊断提供一种无创、快速、准确的辅助诊断方法。
Objective To explore a method for rapid and differential diagnosis of rejection after kidney transplantation through urine hyperspectral imaging technology.Methods Hyperspectral data information from urine samples of 118 recipients after kidney transplantation was collected,and a deep learning model was constructed to diagnose and classify the types of rejection.Results A deep learning diagnostic model based on the 34-layer residual network(ResNet-34)was constructed,and 118 patients were included and divided into the training set and the test set.Based on the pathological results of the transplanted kidney puncture,the urine samples of the patients were classified into five groups:the non-rejection group,the T-cell-mediated rejection group,the antibody-mediated rejection group,the mixed rejection group and the nephropathy recurrence group.The results showed that the diagnostic sensitivities of the model for the above five groups were 0.960,0.980,0.930,0.940 and 0.943 respectively,and the diagnostic specificities were 0.983,0.993,0.997,0.989 and 0.989 respectively.The overall diagnostic accuracy rate reached 95.7%.Conclusions The study provides a non-invasive,rapid and accurate auxiliary diagnostic method for the differential diagnosis of rejection after kidney transplantation.
作者
杨哲
段启龙
陈艺
廖涛
司晓青
王建宁
Yang Zhe;Duan Qilong;Chen Yi;Liao Tao;Si Xiaoqing;Wang Jianning(Department of Urology,the First Affiliated Hospital of Shandong First Medical University(Qianfoshan Hospital of Shandong Province),Jinan 250000,China)
出处
《器官移植》
2026年第1期116-123,共8页
Organ Transplantation
基金
国家自然科学基金(82373042)
山东省自然科学基金(ZR2025MS1199)
山东大学临床医学科技创新计划(202512028)。
关键词
高光谱成像技术
无创诊断
肾移植
排斥反应
辅助诊断
学习模型
T细胞介导的排斥反应
抗体介导的排斥反应
Hyperspectral imaging technology
Non-invasive diagnosis
Kidney transplantation
Rejection
Auxiliary diagnosis
Learning model
T cell-mediated rejection
Antibody-mediated rejection
