de Oliveira Júlia Epischina Engrácia, de Albuquerque Araújo Arnaldo, Deserno Thomas M
Júlia Epischina Engrácia de Oliveira, Arnaldo de Albuquerque Araújo, Department of Computer Science, Universidade Federal de Minas Gerais, 31270-901, Belo Horizonte, MG, Brazil.
World J Radiol. 2011 Jan 28;3(1):24-31. doi: 10.4329/wjr.v3.i1.24.
To present a content-based image retrieval (CBIR) system that supports the classification of breast tissue density and can be used in the processing chain to adapt parameters for lesion segmentation and classification.
Breast density is characterized by image texture using singular value decomposition (SVD) and histograms. Pattern similarity is computed by a support vector machine (SVM) to separate the four BI-RADS tissue categories. The crucial number of remaining singular values is varied (SVD), and linear, radial, and polynomial kernels are investigated (SVM). The system is supported by a large reference database for training and evaluation. Experiments are based on 5-fold cross validation.
Adopted from DDSM, MIAS, LLNL, and RWTH datasets, the reference database is composed of over 10 000 various mammograms with unified and reliable ground truth. An average precision of 82.14% is obtained using 25 singular values (SVD), polynomial kernel and the one-against-one (SVM).
Breast density characterization using SVD allied with SVM for image retrieval enable the development of a CBIR system that can effectively aid radiologists in their diagnosis.
提出一种基于内容的图像检索（CBIR）系统，该系统支持乳腺组织密度分类，并可用于处理链中以调整病变分割和分类的参数。
使用奇异值分解（SVD）和直方图通过图像纹理对乳腺密度进行表征。通过支持向量机（SVM）计算模式相似度以区分四种BI-RADS组织类别。改变剩余奇异值的关键数量（SVD），并研究线性、径向和多项式核（SVM）。该系统由一个大型参考数据库支持，用于训练和评估。实验基于五折交叉验证。
参考数据库采用DDSM、MIAS、LLNL和RWTH数据集，由超过10000张各种乳腺X线照片组成，具有统一且可靠的地面真值。使用25个奇异值（SVD）、多项式核和一对一（SVM）获得的平均精度为82.14%。
将SVD与SVM相结合用于图像检索的乳腺密度表征能够开发出一种CBIR系统，该系统可以有效地帮助放射科医生进行诊断。
