Enhanced diagnostic accuracy for quantitative bone scan using an artificial neural network system: a Japanese multi-center database project.
Enhanced diagnostic accuracy for quantitative bone scan using an artificial neural network system: a Japanese multi-center database project.
复制标题
DOI：
10.1186/2191-219x-3-83
复制
发表时间：
2013-12-26
期刊：
影响因子：
3.2
通讯作者：
Edenbrandt L
中科院分区：
文献类型：
--
作者：
Nakajima K;Nakajima Y;Horikoshi H;Ueno M;Wakabayashi H;Shiga T;Yoshimura M;Ohtake E;Sugawara Y;Matsuyama H;Edenbrandt L
基于人工神经网络(ANN)的骨扫描指数(BSI)是骨转移数量的标志，已被证明可以提高诊断的准确性和重复性，但可能会受到训练数据库的影响。本研究的目的是利用大量的日语数据库对该软件进行修订，并与原始的瑞典训练数据库进行比较，以验证其诊断准确性。使用瑞典训练数据库(n = 789)，用EXINIbone(EB；EXINI诊断)计算BSI。使用来自单一机构的日语培训数据库的软件(BONENAVI第1版，bn1，n = 904)与来自9个机构的修订版(第2版，bn2，n = 1,532)进行了比较。另外503例多中心骨扫描证实了诊断的准确性，包括前列腺癌(n = 207)、乳腺癌(n = 166)和其他癌症类型的患者。计算ANN值(异常概率)和BSI。进行受试者工作特性(ROC)和净重分类改进(NRI)分析。基于ANN值的ROC分析表明，从EB到BN1和BN2，ROC有了显著的改善。在男性(n = 296)中，EB的曲线下面积(AUC)为0.877，BN1的曲线下面积(AUC)为0.912(p = 不显著(Ns)对EB)，Bn2的曲线下面积(AUC)为0.934(p = 0.007对EB)。在女性(n = 207)中，EB的AUC值为0.831，BN1的AUC值为0.910(p = 0.016 vs.EB)，Bn2的AUC值为0.932(p <； 0.0001 vs.EB)。以BN_2为基础的最佳敏感性和特异性男性分别为90%和84%，女性分别为93%和85%。在前列腺癌患者中，AUC与EB、BN1和BN2值相同(0.939、0.949和0.957，p = ns)。乳腺癌患者AUC由EB(0.847)改善为Bn1(0.910，p = ns)和Bn2(0.924，p = 0.039)。神经网络在EB和BN1之间的NRI为17.7%(p = 0.0042)，EB和Bn2之间的NRI为29.6%(p <； 0.0001)。对于BSI，NRI分析显示向下重新分类，总NRI为31.9%(p <； 0.0001)。在计算BSI的软件中，与原始数据库相比，多机构数据库显著改进了对骨转移的识别，表明包括各种癌症在内的足够数量的训练数据库的重要性。
Artificial neural network (ANN)-based bone scan index (BSI), a marker of the amount of bone metastasis, has been shown to enhance diagnostic accuracy and reproducibility but is potentially affected by training databases. The aims of this study were to revise the software using a large number of Japanese databases and to validate its diagnostic accuracy compared with the original Swedish training database. The BSI was calculated with EXINIbone (EB; EXINI Diagnostics) using the Swedish training database (n = 789). The software using Japanese training databases from a single institution (BONENAVI version 1, BN1, n = 904) and the revised version from nine institutions (version 2, BN2, n = 1,532) were compared. The diagnostic accuracy was validated with another 503 multi-center bone scans including patients with prostate (n = 207), breast (n = 166), and other cancer types. The ANN value (probability of abnormality) and BSI were calculated. Receiver operating characteristic (ROC) and net reclassification improvement (NRI) analyses were performed. The ROC analysis based on the ANN value showed significant improvement from EB to BN1 and BN2. In men (n = 296), the area under the curve (AUC) was 0.877 for EB, 0.912 for BN1 (p = not significant (ns) vs. EB) and 0.934 for BN2 (p = 0.007 vs. EB). In women (n = 207), the AUC was 0.831 for EB, 0.910 for BN1 (p = 0.016 vs. EB), and 0.932 for BN2 (p < 0.0001 vs. EB). The optimum sensitivity and specificity based on BN2 was 90% and 84% for men and 93% and 85% for women. In patients with prostate cancer, the AUC was equally high with EB, BN1, and BN2 (0.939, 0.949, and 0.957, p = ns). In patients with breast cancer, the AUC was improved from EB (0.847) to BN1 (0.910, p = ns) and BN2 (0.924, p = 0.039). The NRI using ANN between EB and BN1 was 17.7% (p = 0.0042), and that between EB and BN2 was 29.6% (p < 0.0001). With respect to BSI, the NRI analysis showed downward reclassification with total NRI of 31.9% ( p < 0.0001). In the software for calculating BSI, the multi-institutional database significantly improved identification of bone metastasis compared with the original database, indicating the importance of a sufficient number of training databases including various types of cancers.