Computerized diagnosis of breast lesions on ultrasound

Computerized diagnosis of breast lesions on ultrasound
复制标题

DOI:
10.1118/1.1429239
复制
发表时间:
2002-02-01
期刊:
影响因子:
3.8
通讯作者:
Vyborny, CJ
Vyborny, CJ
中科院分区:
医学3区
文献类型:
--
作者:
Horsch, K;Giger, ML;Vyborny, CJ

文献摘要

被引文献

相似文献

我们提出了一种超声乳腺病变的计算机辅助诊断(CAD)方法,该方法基于病变的自动分割和自动提取与病变形状、边缘、纹理和后声学行为相关的四个特征。使用 400 个病例(94 个恶性病变、124 个复杂囊肿和 182 个良性实体病变)的数据库,我们研究了 CAD 方法中每个特征的边际效益以及 CAD 方法在区分恶性病变和各类良性病变方面的性能。最后,对我们的 CAD 方法进行独立验证。在区分恶性和良性病变的任务中,11 项独立试验的平均 A 值为 0.87。 (C) 2002 年美国医学物理学家协会。
We present a computer-aided diagnosis (CAD) method for breast lesions on ultrasound that is based on the automatic segmentation of lesions and the automatic extraction of four features related to the lesion shape, margin, texture, and posterior acoustic behavior. Using a database of 400 cases (94 malignant lesions, 124 complex cysts, and 182 benign solid lesions), we investigate the marginal benefit of each feature in our CAD method and the performance of our CAD method in distinguishing malignant lesions from various classes of benign lesions. Finally, independent validation is performed on our CAD method. Eleven independent trials yielded an average A, value of 0.87 in the task of distinguishing malignant from benign lesions. (C) 2002 American Association of Physicists in Medicine.