Banik Shantanu, Rangayyan Rangaraj M, Desautels J E Leo
Department of Electrical and Computer Engineering, Schulich School of Engineering, University of Calgary, 2500 University Drive NW, Calgary, Alberta, Canada T2N1N4.
Annu Int Conf IEEE Eng Med Biol Soc. 2009;2009:6667-70. doi: 10.1109/IEMBS.2009.5334517.
Architectural distortion is a commonly missed sign of breast cancer. This paper investigates the detection of architectural distortion, in mammograms of interval-cancer cases taken prior to the diagnosis of breast cancer, using Gabor filters, phase portrait analysis, fractal dimension, and texture analysis. The methods were used to detect initial candidates for sites of architectural distortion in prior mammograms of interval-cancer and also normal cases. A total of 4212 regions of interest (ROIs) were automatically obtained from 106 prior mammograms of 56 interval-cancer cases, including 262 ROIs related to architectural distortion, and from 52 prior mammograms of 13 normal cases. For each ROI, the fractal dimension and Haralick's texture features were computed. Feature selection was performed using stepwise logistic regression and in terms of the area under the receiver operating characteristics (ROC) curve (AUC). The best results achieved, in terms of AUC, are 0.75 with the Bayesian classifier, 0.71 with Fisher linear discriminant analysis, and 0.76 with an artificial neural network (ANN) based on radial basis functions (RBF). Analysis of the performance of the methods with free-response receiver operating characteristics indicated a sensitivity of 0.80 at 10.5 false positives per image.
结构扭曲是乳腺癌常见的漏诊征象。本文研究了利用伽柏滤波器、相图分析、分形维数和纹理分析，在乳腺癌诊断之前拍摄的间期癌病例的乳腺钼靶片中检测结构扭曲的方法。这些方法被用于在间期癌和正常病例的先前乳腺钼靶片中检测结构扭曲部位的初始候选区域。从56例间期癌病例的106张先前乳腺钼靶片中自动获取了总共4212个感兴趣区域（ROI），其中包括262个与结构扭曲相关的ROI，以及从13例正常病例的52张先前乳腺钼靶片中获取的ROI。对于每个ROI，计算了分形维数和哈拉里克纹理特征。使用逐步逻辑回归并根据接收器操作特征（ROC）曲线下面积（AUC）进行特征选择。就AUC而言，所取得的最佳结果是：贝叶斯分类器为0.75，费舍尔线性判别分析为0.71，基于径向基函数（RBF）的人工神经网络（ANN）为0.76。对具有自由响应接收器操作特征的方法的性能分析表明，在每幅图像10.5个假阳性时，灵敏度为0.80。
