Bharadwaj Akshay S, Celenk Mehmet
Annu Int Conf IEEE Eng Med Biol Soc. 2015;2015:6382-5. doi: 10.1109/EMBC.2015.7319853.
Breast cancer is one of the most common causes of death in women aged 40 and above. Early detection of breast cancer has been one of the prime topics of research in biomedical engineering area. Micro-calcifications (MCs) are the indicators of early stages of breast cancer, and the detection of these MCs will, in turn, lead to diagnosis and treatment of breast cancer at its earliest stages. This paper proposes a new method to detect MCs in a digital mammogram. The approach starts with the segmentation of the digital mammogram to isolate the breast region, using fuzzy C means clustering algorithm. The segmented image is then further segmented using top-hat transform to localize the region of interest. A watershed transform is used to isolate the region of interest from rest of the image. The Gibbs random fields are employed to analyze the pixels in conjunction with the devised clique patterns and detect MCs in the image. A thresholding is performed on the processed image where the MCs are detected. The proposed algorithm is highly effective in reducing the region of interest to the region which has a high probability of finding a calcification or MC. It has an overall detection rate of 94.4% and accuracy of 88.2% with a false negative detection rate of 5.6%, respectively.
乳腺癌是40岁及以上女性最常见的死因之一。乳腺癌的早期检测一直是生物医学工程领域的主要研究课题之一。微钙化是乳腺癌早期阶段的指标，检测这些微钙化将进而实现乳腺癌的早期诊断和治疗。本文提出了一种在数字化乳腺钼靶片中检测微钙化的新方法。该方法首先使用模糊C均值聚类算法对数字化乳腺钼靶片进行分割以分离出乳腺区域。然后，使用顶帽变换对分割后的图像进一步分割以定位感兴趣区域。分水岭变换用于将感兴趣区域与图像的其余部分隔离开来。吉布斯随机场结合设计的团块模式用于分析像素并检测图像中的微钙化。在检测到微钙化的处理后的图像上进行阈值处理。所提出的算法在将感兴趣区域缩小到极有可能发现钙化或微钙化的区域方面非常有效。它的总体检测率为94.4%，准确率为88.2%，假阴性检测率分别为5.6%。
