-
作为乳腺癌计算机辅助诊断系统的重要环节,肿块分割的结果严重影响到肿块良恶性的判别. 针对现有方法的不足,本文提出了一种基于简化型脉冲耦合神经网络和改进型矢量无边缘活动轮廓模型的乳腺X射线肿块分割方法. 首先,通过数学分析计算SPCNN的相关参数与终止条件,进而利用SPCNN模型分割出肿块的初始轮廓. 然后,针对传统CV模型的不足,进行相应的修正得到改进型矢量CV模型. 最后,结合SPCNN分割出的初始轮廓,利用改进型的矢量CV模型处理ROI分割出肿块. 采用北京大学人民医院乳腺中心提供的临床图像以及DDSM数据库的图像进行对比实验,实验结果表明,本文方法相比较现有方法分割结果更为准确,尤其是在处理东方女性致密性案例时,本文方法更有优势.
-
关键词:
- 计算机辅助诊断 /
- 肿块分割 /
- 简化型脉冲耦合神经网络 /
- 矢量无边缘活动轮廓模型
Mass segmentation plays an important role in computer-aided diagnosis (CAD) system. The segmentation result seriously affects classifying mass as benign and malignant. By combining the simplified pulse coupled neural network (SPCNN) and the improved vector active contour without edge (vector-CV), a novel method of mass segmentation in mammogram is proposed in this paper. First, the parameters and termination conditions of SPCNN are obtained through mathematical analysis and the initial contour is segmented by SPCNN. Then, the vector CV model is accordingly modified to overcome the shortcomings of traditional CV model. Finally, combined with the initial contour, the improved vector-CV is used to segment the mass contour. The experiments implemented on the public digital database for screening mammography (DDSM) and the clinical images which are provided by the Center of Breast Disease of Peking University People’s Hospital indicate that the proposed method is better than the existing methods, especially when dealing with the dense breasts of Oriental female.-
Keywords:
- CAD /
- mass segmentation /
- SPCNN /
- vector-CV
[1] Xiang L Z, Xing D, Guo H, Yang S H 2009 Acta Phys. Sin. 58 4610 (in Chinese) [向良忠, 邢达, 郭华, 杨思华 2009 物理学报58 4610]
[2] Xu X H, Li H 2008 Acta Phys. Sin. 57 4623 (in Chinese)[徐晓辉, 李晖2008 物理学报57 4623]
[3] Xiao X, Xu L, Liu B Y 2013 Acta Phys. Sin. 62 044105 (in Chinese) [肖夏, 徐立, 刘冰雨2013 物理学报62 044105]
[4] Liu G D, Zhang Y R 2011 Acta Phys. Sin. 60 074303 (in Chinese) [刘广东, 张业荣2011 物理学报60 074303]
[5] Yao C, Chen H J, Yang Y Y, Li Y F, Han Z Z, Zhang S J 2013 Acta Phys. Sin. 62 088702 (in Chinese) [姚畅, 陈后金, Yang Yong-Yi, 李艳凤, 韩振中, 张圣君2013 物理学报62 088702]
[6] Liu T S 2004 Guangxi Medical Journal 26 1595 (in Chinese)[刘惕生2004 广西医学26 1595]
[7] Kupinski M A, Giger M L 1998 IEEE Trans. Med. Imag. 17 510
[8] Kobatake H, Murakami M, Takeo H, Nawano S 1999 IEEE Trans. Med. Imag. 18 369
[9] Cao Y, Hao X, Zhu X E, Xia S R 2011 Journal of Zhejiang University (Engineering Science) 45 1753(in Chinese)[曹颖, 郝欣, 朱晓恩, 夏顺仁浙江大学学报(工学版) 45 1753]
[10] Xu W D, Xia S R, Xiao M, Duan H L 2005 Proceedings of the 27th Annual Conference on Medicine and Biology. Shanghai, China September 1-4, 2005 p2543
[11] Yu S S, Tsai C Y, Liu C C 2010 Proceedings of 4th International Conference on New Trends in Information Science and Service Science (NISS). Gyeongju, South Korea May 11-13, 2010 p715
[12] Wang Y, Tao D C, Gao X B, Li X L, Wang B 2011 Pattern Recognition 44 1903
[13] Wang D K, Hou Y Q, Peng J Y 2008 Image processing using partial differential equations (Beijing: Science Press) p103. (in Chinese) [王大凯, 侯榆青, 彭进业2008 图像处理的偏微分方程方法(北京: 科学出版社) 第103 页]
[14] Ma Y D, Li L, Wang Z B 2008 Pulse Coupled Neural Network and Digital Image Processing(Beijing: Science Press) p44 (in Chinese) [马义德, 李廉, 王兆滨脉冲耦合神经网络与数字图像处理(北京: 科学出版社) 第44 页]
[15] Hou K, Bao S L, Ma J F, Chen C 2011 Chin. Phys. B 20 028701
[16] Huang G, Tai Y C, Fang Q 2011 Jilin Medical Journal 32 6979 (in Chinese) [黄贵, 邰亦成, 方琪2011 吉林医学 32 6979]
-
[1] Xiang L Z, Xing D, Guo H, Yang S H 2009 Acta Phys. Sin. 58 4610 (in Chinese) [向良忠, 邢达, 郭华, 杨思华 2009 物理学报58 4610]
[2] Xu X H, Li H 2008 Acta Phys. Sin. 57 4623 (in Chinese)[徐晓辉, 李晖2008 物理学报57 4623]
[3] Xiao X, Xu L, Liu B Y 2013 Acta Phys. Sin. 62 044105 (in Chinese) [肖夏, 徐立, 刘冰雨2013 物理学报62 044105]
[4] Liu G D, Zhang Y R 2011 Acta Phys. Sin. 60 074303 (in Chinese) [刘广东, 张业荣2011 物理学报60 074303]
[5] Yao C, Chen H J, Yang Y Y, Li Y F, Han Z Z, Zhang S J 2013 Acta Phys. Sin. 62 088702 (in Chinese) [姚畅, 陈后金, Yang Yong-Yi, 李艳凤, 韩振中, 张圣君2013 物理学报62 088702]
[6] Liu T S 2004 Guangxi Medical Journal 26 1595 (in Chinese)[刘惕生2004 广西医学26 1595]
[7] Kupinski M A, Giger M L 1998 IEEE Trans. Med. Imag. 17 510
[8] Kobatake H, Murakami M, Takeo H, Nawano S 1999 IEEE Trans. Med. Imag. 18 369
[9] Cao Y, Hao X, Zhu X E, Xia S R 2011 Journal of Zhejiang University (Engineering Science) 45 1753(in Chinese)[曹颖, 郝欣, 朱晓恩, 夏顺仁浙江大学学报(工学版) 45 1753]
[10] Xu W D, Xia S R, Xiao M, Duan H L 2005 Proceedings of the 27th Annual Conference on Medicine and Biology. Shanghai, China September 1-4, 2005 p2543
[11] Yu S S, Tsai C Y, Liu C C 2010 Proceedings of 4th International Conference on New Trends in Information Science and Service Science (NISS). Gyeongju, South Korea May 11-13, 2010 p715
[12] Wang Y, Tao D C, Gao X B, Li X L, Wang B 2011 Pattern Recognition 44 1903
[13] Wang D K, Hou Y Q, Peng J Y 2008 Image processing using partial differential equations (Beijing: Science Press) p103. (in Chinese) [王大凯, 侯榆青, 彭进业2008 图像处理的偏微分方程方法(北京: 科学出版社) 第103 页]
[14] Ma Y D, Li L, Wang Z B 2008 Pulse Coupled Neural Network and Digital Image Processing(Beijing: Science Press) p44 (in Chinese) [马义德, 李廉, 王兆滨脉冲耦合神经网络与数字图像处理(北京: 科学出版社) 第44 页]
[15] Hou K, Bao S L, Ma J F, Chen C 2011 Chin. Phys. B 20 028701
[16] Huang G, Tai Y C, Fang Q 2011 Jilin Medical Journal 32 6979 (in Chinese) [黄贵, 邰亦成, 方琪2011 吉林医学 32 6979]
计量
- 文章访问数: 6902
- PDF下载量: 595
- 被引次数: 0