基于深度学习的核素骨显像联合血清肿瘤坏死因子-α、骨钙素N端中分子片段对肺癌骨转移的诊断价值  

Diagnosis Value of Deep Learning-Based Radionuclide Bone Imaging Combined with Serum Tumor Necrosis Factor-α and N-terminal Mid-fragment of Osteocalcin for Bone Metastasis of Lung Cancer

作　　者：金玉新[1] Jin Yu-xin(Nuclear Medicine Department,The 1st People's Hospital of Baiyin,Baiyin 730900,Gansu Province,China)

机构地区：[1]白银市第一人民医院核医学科,甘肃白银730900

出　　处：《中国社区医师》2023年第12期95-97,共3页Chinese Community Doctors

摘　　要：目的:探讨基于深度学习的核素骨显像联合血清肿瘤坏死因子-α(TNF-α)、骨钙素N端中分子片段(N-MID)对肺癌骨转移的诊断价值。方法:选取2019年2月—2022年2月白银市第一人民医院收治的80例肺癌患者进行回顾性分析,根据病理学诊断结果是否伴有骨转移分为两组,37例无骨转移患者纳入对照组,43例伴有骨转移患者纳入观察组。所有患者行^(99)Tc^(m)-亚甲基二磷酸盐(^(99)Tc^(m)-MDP)骨显像及血清标志物(TNF-α、N-MID)检测。比较两组血清标志物水平,分析^(99)Tc^(m)-MDP骨显像、血清标志物(TNF-α、N-MID)以及二者联合对肺癌骨转移的诊断结果及价值。结果:观察组TNF-α、N-MID水平高于对照组,差异有统计学意义(P=0.000)。联合诊断的假阳性、假阴性率低于单项检测诊断,差异有统计学意义(P<0.05)。^(99)Tc^(m)-MDP骨显像、血清标志物二者联合检测的受试者工作特征曲线下面积、敏感度、特异度高于^(99)Tc^(m)-MDP骨显像、血清标志物单独检测,差异有统计学意义(P<0.001)。结论:基于深度学习的核素骨显像联合血清标志物能够提升对肺癌骨转移的诊断效能,值得临床推广。Objective:To investigate the diagnosis value of deep learning-based radionuclide bone imaging combined with serum tumor necrosis factor-α(TNF-α)and N-terminal mid-fragment of osteocalcin(N-MID)for bone metastasis of lung cancer.Methods:A total of 80 patients with lung cancer admitted to The 1st People's Hospital of Baiyin from February 2019 to February 2022 were selected for retrospective analysis.They were divided into two groups according to whether there was bone metastasis in the pathological diagnosis results.The 37 patients without bone metastasis were included in the control group,and 43 patients with bone metastasis were included in the observation group.All patients underwent ^(99)Tc m-methylene diphosphonate(^(99)Tc^(m)-MDP)bone imaging and serum markers(TNF-α,N-MID)test.The levels of serum markers in two groups were compared.The diagnosis results and value of ^(99)Tc^(m)-MDP bone imaging,serum markers(TNF-α,N-MID)and the combination of the two for bone metastasis of lung cancer were analyzed.Results:The levels of TNF-αand N-MID in the observation group were higher than those in the control group,and the differences were statistically significant(P=0.000).The false positive and false negative rates of the combined diagnosis were lower than those of single detection diagnosis,and the difference was statistically significant(P<0.05).The area under the receiver operating characteristic curve,sensitivity,and specificity of the combined detection of ^(99)Tc^(m)-MDP bone imaging and serum markers were higher than those of single detection of ^(99)Tc^(m)-MDP bone imaging and serum markers,and the differences were statistically significant(P<0.001).Conclusion:The deep learning-based radionuclide bone imaging combined with serum markers can improve the diagnostic efficacy of bone metastasis of lung cancer,and is worthy of clinical promotion.

关 键 词：核素骨显像 血清肿瘤坏死因子-Α 骨钙素N端中分子片段 肺癌骨转移 

分 类 号：R734.2[医药卫生—肿瘤]