Detecting and classifying linear structures in mammograms using random forests.
Detecting and classifying linear structures in mammograms using random forests.
复制标题
使用随机森林对乳房 X 光照片中的线性结构进行检测和分类。
DOI：
10.1007/978-3-642-22092-0_42
复制
发表时间：
2011
期刊：
影响因子：
--
通讯作者：
Berks M
中科院分区：
文献类型：
--
作者：
Berks M
曲线结构的检测和分类在许多图像解译任务中具有重要意义。我们专注于在乳房X光照片中检测这种结构并确定它是正常还是异常的挑战性问题。我们采用了一种基于双树复小波表示和随机森林分类的判别学习方法。我们给出了我们的方法与文献中的三种主要方法以及这些方法的基于学习的变体的定量比较结果。我们的结果表明，我们的新方法比其他任何方法都有更好的结果，在ROC曲线下的面积Az=0.923用于曲线结构检测，Az=0.761用于区分正常和异常结构(针刺)。详细的分析表明，部分改进归因于区分学习，另一部分归功于DT-CWT表示，它提供了局部相位信息和良好的角度分辨率。
Detecting and classifying curvilinear structure is important in many image interpretation tasks. We focus on the challenging problem of detecting such structure in mammograms and deciding whether it is normal or abnormal. We adopt a discriminative learning approach based on a Dual-Tree Complex Wavelet representation and random forest classification. We present results of a quantitative comparison of our approach with three leading methods from the literature and with learning-based variants of those methods. We show that our new approach gives significantly better results than any of the other methods, achieving an area under the ROC curve Az = 0.923 for curvilinear structure detection, and Az = 0.761 for distinguishing between normal and abnormal structure (spicules). A detailed analysis suggests that some of the improvement is due to discriminative learning, and some due to the DT-CWT representation, which provides local phase information and good angular resolution.