Self-organizing map for cluster analysis of a breast cancer database
Self-organizing map for cluster analysis of a breast cancer database
复制标题
DOI：
10.1016/s0933-3657(03)00003-4
复制
发表时间：
2003-02-01
影响因子：
7.5
通讯作者：
Floyd, CE
中科院分区：
文献类型：
--
作者：
Markey, MK;Lo, JY;Floyd, CE
这项研究的目的是在一个不同种类的乳腺癌计算机辅助诊断数据库中识别和表征集群。识别数据库中的亚组可以帮助阐明临床趋势，并促进未来的模型建立。自组织映射(SOM)被用来在一个大型(2258例)、基于乳房X光检查结果(BI-RADS(TM))和患者年龄的不同计算机辅助诊断数据库中识别簇。然后，通过使用约束满足神经网络(CSNN)确定的原型来表征所得到的集群。这些簇显示了临床亚型的逻辑分离，如建筑扭曲、肿块和钙化。此外，肿块和钙化的大类被分层为几个簇(七个用于肿块，三个用于钙化)。恶性病例的比例在不同集群之间有显著差异(从6%到83%不等)。前馈反向传播人工神经网络(BP-ANN)被用来识别可能需要随访而不是活检的可能的良性病变。BP-ANN的性能在SOM确定的集群中差异很大。特别是，确定了一组(#6)大量病例(6%是恶性的)，占BP-ANN提出的后续建议的79%。基于簇#6的轮廓的分类规则的执行与BP-ANN相当，提供了大约25%的特异度和98%的灵敏度。这一表现被证明可以推广到一大组(2177个)等待模型验证的案例。(C)2003 Elsevier Science B.V.保留所有权利。
The purpose of this study was to identify and characterize clusters in a heterogeneous breast cancer computer-aided diagnosis database. Identification of subgroups within the database could help elucidate clinical trends and facilitate future model building. A self-organizing map (SOM) was used to identify clusters in a large (2258 cases), heterogeneous computer-aided diagnosis database based on mammographic findings (BI-RADS(TM)) and patient age. The resulting clusters were then characterized by their prototypes determined using a constraint satisfaction neural network (CSNN). The clusters showed logical separation of clinical subtypes such as architectural distortions, masses, and calcifications. Moreover, the broad categories of masses and calcifications were stratified into several clusters (seven for masses and three for calcifications). The percent of the cases that were malignant was notably different among the clusters (ranging from 6 to 83%). A feed-forward back-propagation artificial neural network (BP-ANN) was used to identify likely benign lesions that may be candidates for follow up rather than biopsy. The performance of the BP-ANN varied considerably across the clusters identified by the SOM. in particular, a cluster (#6) of mass cases (6% malignant) was identified that accounted for 79% of the recommendations for follow up that would have been made by the BP-ANN. A classification rule based on the profile of cluster #6 performed comparably to the BP-ANN, providing approximately 25% specificity at 98% sensitivity. This performance was demonstrated to generalize to a large (2177) set of cases held-out for model validation. (C) 2003 Elsevier Science B.V. All rights reserved.