文档介绍：优质
摘要
乳腺癌是中老年妇女中发病率和死亡率最高的恶性肿瘤之一,其早发现及早治疗是提高治愈率和降低死亡率的关键。乳腺钼靶摄影是普查和诊断乳腺癌的最有效方法。但纯人工阅读钼靶片存在易疲劳、耗时多、误诊和漏诊率较大等问题。利用计算机图像处理技术辅助检测,可以提高乳腺癌早期发现率和诊断准确率,使得诊断结果更具有客观性及精确性。
本文以乳房肿块检测展开,依照乳腺钼靶X射线图像去噪、乳腺钼靶X射线图像去噪增强、可疑肿块的分割的次序,进行了乳腺钼靶X线图像乳房肿块的辅助检测研究。
在乳腺钼靶X射线图像去噪方面,针对乳腺钼靶X射线图像的肿块区域和背景区域都有较大噪声,影响阅片的问题,本文提出了基于小波变换的软阈值化去噪方法,在保持诊断影像特征特别是给定轮廓线内的毛刺和小叶征象的前提下,消除了噪声和伪影带来的影响。在乳腺钼靶X射线图像增强方面,本文采取了简单实用的直方图均衡化方法使乳腺钼靶X射线图像对比度低的问题得到了很好的解决。对于可疑肿块的分割,本文采取了基于水平集理论的窄带算法,实现了全自动和半自动的分割处理,通过几十组良性和恶性肿瘤图像数据的测试,程序可以使肿块区域准确地从乳腺区域分割出来。
关键词:乳房肿块;钼靶X射线;小波变换;直方图均衡化;水平集分割
ABSTRACT
Breast cancer is one of the mon malignancies with high incidence and mortality rates among older women. To increase the cure rate and reduce the mortality from this disease, early detection and treatment of breast cancer is the important premise. Mammography is considered as the most reliable and cost-effective method for early screening and diagnosis of breast cancer. But the problems, such as fatigue, time-consuming, higher rates of misdiagnosis and missed diagnosis, will occur if the detection of breast cancer is solely performed by a single radiologist. Computer-aided detection, which is based puter image processing techniques, has the potential to improve the rate of early detection and make diagnosis results more objective and accurate.
This dissertation, rooting from the detection of breast lumps, with the sequence of breast X-ray images denoising, X-ray images enhancement, segmentation of suspicious mass,make a series study about aided detection of breast lumps.
For mammography X-ray image denoising, to reduce the noise in the mammography of breast mass regions and background regions, this dissertation presents a wavelet-based soft-thresholding denoising method, while maintaining diagnostic imaging features, especially within a given contour and the burr under the premise of lobular signs, eliminating the noise and the impact of artifacts. For mammography X-ray in image enhancement, this paper adopted a simple and p