Screening programs use mammography as primary diagnostic tool for detecting breast cancer at an early stage. The diagnosis of some lesions, such as microcalcifications, is still difficult today for radiologists. In this paper, we proposed an automatic binary model for discriminating tissue in digital mammograms, as support tool for the radiologists. In particular, we compared the contribution of different methods on the feature selection process in terms of the learning performances and selected features. For each ROI, we extracted textural features on Haar wavelet decompositions and also interest points and corners detected by using Speeded Up Robust Feature (SURF) and Minimum Eigenvalue Algorithm (MinEigenAlg). Then a Random Forest binary classifier is trained on a subset of a sub-set features selected by two different kinds of feature selection techniques, such as filter and embedded methods. We tested the proposed model on 260 ROIs extracted from digital mammograms of the BCDR public database. The best prediction performance for the normal/abnormal and benign/malignant problems reaches a median AUC value of 98.16% and 92.08%, and an accuracy of 97.31% and 88.46%, respectively. The experimental result was comparable with related work performance. The best performing result obtained with embedded method is more parsimonious than the filter one. The SURF and MinEigen algorithms provide a strong informative content useful for the characterization of microcalcification clusters.

中文翻译：

---

一种用于乳房微钙化诊断的多尺度纹理分析的机器学习方法。

筛查程序使用乳房X线摄影作为早期诊断乳腺癌的主要诊断工具。如今，放射科医生仍然很难诊断某些病变，例如微钙化。在本文中，我们提出了一种用于识别数字化X线照片中组织的自动二进制模型，作为放射科医生的支持工具。特别是，我们根据学习性能和所选特征比较了不同方法对特征选择过程的贡献。对于每个ROI，我们提取了有关Haar小波分解的纹理特征，还提取了使用加速鲁棒特征（SURF）和最小特征值算法（MinEigenAlg）检测到的兴趣点和角点。然后，在通过两种不同类型的特征选择技术（例如过滤器和嵌入式方法）选择的子集特征的子集上训练随机森林二进制分类器。我们在从BCDR公共数据库的数字乳房X线照片提取的260个ROI上测试了建议的模型。正常/异常和良性/恶性问题的最佳预测性能分别达到AUC中值98.16％和92.08％，准确度分别为97.31％和88.46％。实验结果与相关工作表现相当。用嵌入式方法获得的最佳性能结果比过滤器效果更简单。SURF和MinEigen算法提供了丰富的信息内容，可用于表征微钙化簇。我们在从BCDR公共数据库的数字乳房X线照片提取的260个ROI上测试了建议的模型。正常/异常和良性/恶性问题的最佳预测性能分别达到AUC中值98.16％和92.08％，准确度分别为97.31％和88.46％。实验结果与相关工作表现相当。用嵌入式方法获得的最佳性能结果比过滤器效果更简单。SURF和MinEigen算法提供了丰富的信息内容，可用于微钙化簇的表征。我们在从BCDR公共数据库的数字乳房X线照片提取的260个ROI上测试了建议的模型。正常/异常和良性/恶性问题的最佳预测性能分别达到AUC中值98.16％和92.08％，准确度分别为97.31％和88.46％。实验结果与相关工作表现相当。用嵌入式方法获得的最佳性能结果比过滤器效果更简单。SURF和MinEigen算法提供了丰富的信息内容，可用于表征微钙化簇。实验结果与相关工作表现相当。用嵌入式方法获得的最佳性能结果比过滤器效果更简单。SURF和MinEigen算法提供了丰富的信息内容，可用于微钙化簇的表征。实验结果与相关工作表现相当。用嵌入式方法获得的最佳性能结果比过滤器效果更简单。SURF和MinEigen算法提供了丰富的信息内容，可用于表征微钙化簇。