Computerized Breast Mass Detection Using Multi-Scale Hessian-Based Analysis for Dynamic Contrast-Enhanced MRI
Computerized Breast Mass Detection Using Multi-Scale Hessian-Based Analysis for Dynamic Contrast-Enhanced MRI
复制标题
DOI：
10.1007/s10278-014-9681-4
复制
发表时间：
2014-10-01
影响因子：
4.4
通讯作者：
Chang, Ruey-Feng
中科院分区：
文献类型：
--
作者：
Huang, Yan-Hao;Chang, Yeun-Chung;Chang, Ruey-Feng
本研究旨在研究一种使用动态对比增强磁共振成像检测乳腺肿块的计算机辅助系统，供临床使用。对 34 名女性的 61 个活检证实的病变（21 个良性病变和 40 个恶性病变）分析了系统的检测性能。使用恶魔变形算法确定乳房区域。通过动力学特征（曲线下面积）和模糊c均值聚类方法识别可疑组织后，基于旋转不变和多尺度斑点特征检测所有乳腺肿块。随后，进一步将肿块与其他检测到的非肿瘤区域（假阳性）区分开。采用自由响应操作特性（FROC）曲线和检出率来评估检测性能。使用组合特征，包括斑点、增强、形态和纹理特征以及 10 倍交叉验证，质量检出率为 100% (61/61)，每例误报 15.15 个，质量检出率为 91.80% (56/61)，每例误报 4.56 个。总之，所提出的计算机辅助检测系统可以帮助放射科医生减少观察者之间的差异以及从大量图像中检测可疑病变相关的成本。我们的结果表明，可以有效地检测到乳腺肿块，并且增强和形态特征对于减少非肿瘤区域很有用。
This study aimed to investigate a computer-aided system for detecting breast masses using dynamic contrast-enhanced magnetic resonance imaging for clinical use. Detection performance of the system was analyzed on 61 biopsy-confirmed lesions (21 benign and 40 malignant lesions) in 34 women. The breast region was determined using the demons deformable algorithm. After the suspicious tissues were identified by kinetic feature (area under the curve) and the fuzzy c-means clustering method, all breast masses were detected based on the rotation-invariant and multi-scale blob characteristics. Subsequently, the masses were further distinguished from other detected non-tumor regions (false positives). Free-response operating characteristics (FROC) curve and detection rate were used to evaluate the detection performance. Using the combined features, including blob, enhancement, morphologic, and texture features with 10-fold cross validation, the mass detection rate was 100 % (61/61) with 15.15 false positives per case and 91.80 % (56/61) with 4.56 false positives per case. In conclusion, the proposed computer-aided detection system can help radiologists reduce inter-observer variability and the cost associated with detection of suspicious lesions from a large number of images. Our results illustrated that breast masses can be efficiently detected and that enhancement and morphologic characteristics were useful for reducing non-tumor regions.