Su Yanni, Wang Yuanyuan, Jiao Jing, Guo Yi
Department of Electronic Engineering, Fudan University, Shanghai 200433, China.
Open Med Inform J. 2011;5(Suppl 1):26-37. doi: 10.2174/1874431101105010026. Epub 2011 Jul 27.
Due to severe presence of speckle noise, poor image contrast and irregular lesion shape, it is challenging to build a fully automatic detection and classification system for breast ultrasonic images. In this paper, a novel and effective computer-aided method including generation of a region of interest (ROI), segmentation and classification of breast tumor is proposed without any manual intervention. By incorporating local features of texture and position, a ROI is firstly detected using a self-organizing map neural network. Then a modified Normalized Cut approach considering the weighted neighborhood gray values is proposed to partition the ROI into clusters and get the initial boundary. In addition, a regional-fitting active contour model is used to adjust the few inaccurate initial boundaries for the final segmentation. Finally, three textures and five morphologic features are extracted from each breast tumor; whereby a highly efficient Affinity Propagation clustering is used to fulfill the malignancy and benign classification for an existing database without any training process. The proposed system is validated by 132 cases (67 benignancies and 65 malignancies) with its performance compared to traditional methods such as level set segmentation, artificial neural network classifiers, and so forth. Experiment results show that the proposed system, which needs no training procedure or manual interference, performs best in detection and classification of ultrasonic breast tumors, while having the lowest computation complexity.
由于斑点噪声严重、图像对比度差以及病变形状不规则，为乳腺超声图像构建一个全自动检测和分类系统具有挑战性。本文提出了一种新颖且有效的计算机辅助方法，无需任何人工干预即可实现乳腺肿瘤感兴趣区域（ROI）的生成、分割及分类。通过结合纹理和位置的局部特征，首先利用自组织映射神经网络检测ROI。然后提出一种考虑加权邻域灰度值的改进归一化切割方法，将ROI划分为聚类并得到初始边界。此外，使用区域拟合活动轮廓模型调整少数不准确的初始边界以进行最终分割。最后，从每个乳腺肿瘤中提取三种纹理和五种形态特征；从而使用高效的亲和传播聚类对现有数据库进行恶性和良性分类，无需任何训练过程。该系统通过132例病例（67例良性和65例恶性）进行验证，并将其性能与传统方法（如水平集分割、人工神经网络分类器等）进行比较。实验结果表明，该系统无需训练过程或人工干预，在超声乳腺肿瘤的检测和分类中表现最佳，同时计算复杂度最低。
