Kinoshita Sérgio Koodi, de Azevedo-Marques Paulo Mazzoncini, Pereira Roberto Rodrigues, Rodrigues Jośe Antônio Heisinger, Rangayyan Rangaraj Mandayam
Image Science and Medical Physics Center, Internal Medicine Department, Faculty of Medicine of Ribeirao Preto, University of Sao Paulo, avenida dos Bandeirantes, 3900, 14048-900, Ribeirão Preto, São Paulo, Brazil.
J Digit Imaging. 2007 Jun;20(2):172-90. doi: 10.1007/s10278-007-9004-0. Epub 2007 Feb 22.
This paper describes part of content-based image retrieval (CBIR) system that has been developed for mammograms. Details are presented of methods implemented to derive measures of similarity based upon structural characteristics and distributions of density of the fibroglandular tissue, as well as the anatomical size and shape of the breast region as seen on the mammogram. Well-known features related to shape, size, and texture (statistics of the gray-level histogram, Haralick's texture features, and moment-based features) were applied, as well as less-explored features based in the Radon domain and granulometric measures. The Kohonen self-organizing map (SOM) neural network was used to perform the retrieval operation. Performance evaluation was done using precision and recall curves obtained from comparison between the query and retrieved images. The proposed methodology was tested with 1,080 mammograms, including craniocaudal and mediolateral-oblique views. Precision rates obtained are in the range from 79% to 83% considering the total image set. Considering the first 50% of the retrieved mages, the precision rates are in the range from 78% to 83%; the rates are in the range from 79% to 86% considering the first 25% of the retrieved images. Results obtained indicate the potential of the implemented methodology to serve as a part of a CBIR system for mammography.
本文描述了已开发的用于乳腺X光片的基于内容的图像检索（CBIR）系统的部分内容。文中详细介绍了基于乳腺纤维腺组织的结构特征、密度分布以及乳腺X光片中所见乳腺区域的解剖大小和形状来推导相似性度量的方法。应用了与形状、大小和纹理相关的知名特征（灰度直方图统计、哈拉里克纹理特征和基于矩的特征），以及基于拉东域和粒度测量的较少探索的特征。使用科霍宁自组织映射（SOM）神经网络执行检索操作。通过查询图像与检索图像之间比较得到的精确率和召回率曲线进行性能评估。所提出的方法用1080张乳腺X光片进行了测试，包括头尾位和内外斜位视图。考虑整个图像集，获得的精确率在79%至83%的范围内。考虑检索图像的前50%，精确率在78%至83%的范围内；考虑检索图像的前25%，精确率在79%至86%的范围内。所获结果表明所实施方法作为乳腺X光摄影CBIR系统一部分的潜力。
