Biomed Eng Online. 2013;12 Suppl 1(Suppl 1):S3. doi: 10.1186/1475-925X-12-S1-S3. Epub 2013 Dec 9.
Breast cancer is the leading cause of both incidence and mortality in women population. For this reason, much research effort has been devoted to develop Computer-Aided Detection (CAD) systems for early detection of the breast cancers on mammograms. In this paper, we propose a new and novel dictionary configuration underpinning sparse representation based classification (SRC). The key idea of the proposed algorithm is to improve the sparsity in terms of mass margins for the purpose of improving classification performance in CAD systems.
The aim of the proposed SRC framework is to construct separate dictionaries according to the types of mass margins. The underlying idea behind our method is that the separated dictionaries can enhance the sparsity of mass class (true-positive), leading to an improved performance for differentiating mammographic masses from normal tissues (false-positive). When a mass sample is given for classification, the sparse solutions based on corresponding dictionaries are separately solved and combined at score level. Experiments have been performed on both database (DB) named as Digital Database for Screening Mammography (DDSM) and clinical Full Field Digital Mammogram (FFDM) DBs. In our experiments, sparsity concentration in the true class (SCTC) and area under the Receiver operating characteristic (ROC) curve (AUC) were measured for the comparison between the proposed method and a conventional single dictionary based approach. In addition, a support vector machine (SVM) was used for comparing our method with state-of-the-arts classifier extensively used for mass classification.
Comparing with the conventional single dictionary configuration, the proposed approach is able to improve SCTC of up to 13.9% and 23.6% on DDSM and FFDM DBs, respectively. Moreover, the proposed method is able to improve AUC with 8.2% and 22.1% on DDSM and FFDM DBs, respectively. Comparing to SVM classifier, the proposed method improves AUC with 2.9% and 11.6% on DDSM and FFDM DBs, respectively.
The proposed dictionary configuration is found to well improve the sparsity of dictionaries, resulting in an enhanced classification performance. Moreover, the results show that the proposed method is better than conventional SVM classifier for classifying breast masses subject to various margins from normal tissues.
乳腺癌是女性发病率和死亡率的主要原因。出于这个原因，许多研究工作都致力于开发计算机辅助检测（CAD）系统，以便在乳房 X 光片中早期发现乳腺癌。在本文中，我们提出了一种新的基于字典配置的稀疏表示分类（SRC）方法。该算法的关键思想是提高质量边缘的稀疏性，以提高 CAD 系统中的分类性能。
所提出的 SRC 框架的目的是根据质量边缘的类型构建单独的字典。我们方法的基本思想是，分离字典可以增强质量类别的稀疏性（真阳性），从而提高区分乳腺肿块与正常组织的性能（假阳性）。当给定一个肿块样本进行分类时，根据相应的字典分别求解稀疏解，并在得分级别上进行组合。实验分别在名为 Digital Database for Screening Mammography（DDSM）和 Clinical Full Field Digital Mammogram（FFDM）数据库的数据库上进行。在我们的实验中，分别测量了在提出的方法和基于传统单个字典的方法之间的真实类别的稀疏性集中（SCTC）和接收者操作特征（ROC）曲线下的面积（AUC）。此外，还使用支持向量机（SVM）将我们的方法与广泛用于肿块分类的最新分类器进行比较。
与传统的单个字典配置相比，所提出的方法分别能够将 DDSM 和 FFDM 数据库的 SCTC 提高 13.9%和 23.6%。此外，所提出的方法能够分别将 DDSM 和 FFDM 数据库的 AUC 提高 8.2%和 22.1%。与 SVM 分类器相比，所提出的方法分别将 AUC 提高 2.9%和 11.6%。
所提出的字典配置能够很好地提高字典的稀疏性，从而提高分类性能。此外，结果表明，该方法在对来自正常组织的各种边缘的乳腺肿块进行分类时优于传统的 SVM 分类器。
