Dept. of Electr. & Comput. Eng., Calgary Univ., Alta.
IEEE Trans Med Imaging. 1994;13(2):263-74. doi: 10.1109/42.293919.
The authors have developed a set of shape factors to measure the roughness of contours of calcifications in mammograms and for use in their classification as malignant or benign. The analysis of mammograms is performed in three stages. First, a region growing technique is used to obtain the contours of calcifications. Then, three measures of shape features, including compactness, moments, and Fourier descriptors are computed for each region. Finally, their applicability for classification is studied by using the three shape measures to form feature vectors. Classification of 143 calcifications from 18 biopsy-proven cases as benign or malignant using the three measures with the nearest-neighbor method was 100% accurate.
作者开发了一组形状因子来测量乳腺 X 线照片中钙化轮廓的粗糙度,并将其用于分类为恶性或良性。乳腺 X 线照片的分析分三个阶段进行。首先,使用区域生长技术获得钙化的轮廓。然后,计算每个区域的三个形状特征度量,包括紧凑度、矩和傅里叶描述符。最后,通过使用三个形状度量形成特征向量来研究它们在分类中的适用性。使用最近邻法对 18 例经活检证实的病例中的 143 个钙化进行分类,这三个度量的准确率为 100%。