医学图像增强系统设计
|
摘要
为了改善医学图像的视觉效果,提高图像的清晰度,使之更适合于机器的分析处理以及人的视觉特性,并突出病灶点,为病理学诊断和临床诊断提供可靠依据。设计了一个对医学图像十分具有针对性的图像增强系统。针对CT图像的电子噪声提出了基于修正维纳滤波的小波包去噪算法;针对B型超声图像的散斑噪声提出了基于脉冲耦合神经网络(PCNN)模型的小波自适应斑点噪声滤除算法;针对医学图像对比度低,边缘信息模糊等特点,提出了基于小波变换的医学图像增强算法。当噪声方差为0.01时,基于脉冲耦合神经网络(PCNN)模型的小波自适应斑点噪声滤除算法获得的PSNR比经Wiener滤波方法获得的PSNR高出9 dB。系统能快速找到噪声点进行定点去噪,能有效提高医学图像的对比度,增强边缘细节信息,突出病灶点的位置,从而达到较好的处理效果,为医疗工作者观察病症提供更加清晰准确的依据。
In order to improve the visual effects of the medical image and improve image clarity,a targeted image enhancement system for medical images is designed. For the electronic noise of CT images,a wavelet packet denoising algorithm based on amendments Wiener filtering is proposed; For speckle noise of B-mode ultrasound image,a wavelet adaptive speckle reduction algorithm based on the pulse coupled neural network( PCNN) model is proposed. For medical images with low contrast and blur edge,a wavelet-based medical image enhancement algorithm is proposed. The peak signal to noise ratio( PSNR) from the PCNN method is 9dB higher than that from the Wiener filtering when the noise variance is 0. 01. Noise points can be quickly found,and fixed point denoising is carried out,the medical image contrast can be effectively improved,edge details are enhanced,the location of the lesion point is highlighted. It provides a more clear and accurate basis for symptoms observing of health workers.
In order to improve the visual effects of the medical image and improve image clarity,a targeted image enhancement system for medical images is designed. For the electronic noise of CT images,a wavelet packet denoising algorithm based on amendments Wiener filtering is proposed; For speckle noise of B-mode ultrasound image,a wavelet adaptive speckle reduction algorithm based on the pulse coupled neural network( PCNN) model is proposed. For medical images with low contrast and blur edge,a wavelet-based medical image enhancement algorithm is proposed. The peak signal to noise ratio( PSNR) from the PCNN method is 9dB higher than that from the Wiener filtering when the noise variance is 0. 01. Noise points can be quickly found,and fixed point denoising is carried out,the medical image contrast can be effectively improved,edge details are enhanced,the location of the lesion point is highlighted. It provides a more clear and accurate basis for symptoms observing of health workers.
引文
[1]CHEN Rui,MA Yide,ZHENG Xiao,et al.An imaging contrast enhancement algorithm based on PCNN and physiological character of eyesisght[J].Microcomputer Information,2010,26(4):108,111-112.(in Chinese)陈锐,马义德,郑晓,等.基于PCNN和视觉特性的图像对比度增强[J].微计算机信息,2010,26(4):108,111-112.
[2]GUO Yecai,WANG Shaobo.Method of medical ultrasonic image de-noising based on PCNN in the wavelet domain[J].Journal of Anhui University:Natural Science Edition,2010,34(5):54-59.(in Chinese)郭业才,王绍波.基于PCNN的小波域超声医学图像去噪方法[J].安徽大学学报:自然科学版,2010,34(5):54-59.
[3]LI Yunhong,YIN Xin.Image denoising using wavelet packet transform based on correctional Wiener filtering[J].Computer Engineering and Applications,2012,48(21):182-185.(in Chinese)李云红,伊欣.基于修正维纳滤波的小波包变换图像去噪[J].计算机工程与应用,2012,48(21):182-185.
[4]LI Yunhong,YIN Xin.Wave adaptive denoising method based on PCNN[J].Optics and Precision Engineering,2012,20(9):2060-2067.(in Chinese)李云红,伊欣.基于脉冲耦合神经网络模型的小波自适应斑点噪声滤除算法[J].光学精密工程,2012,20(9):2060-2067.
[5]TONG Wuqin,LING Yongshun,HUANG Chaochao,et al.Processing method of IR image based on mathematical morphology and wavelet transform[J].Optics and Precision Engineering,2007,15(1):138-144.(in Chinese)同武勤,凌永顺,黄超超,等.数学形态学和小波变换的红外图像处理方法[J].光学精密工程,2007,15(1):138-144.
[6]CHEN Xiaoxi,WANG Yanjie,LIU Lian.Deep study on wavelet threshold method for image noise removing[J].Laser&Infrared,2012,42(1):105-110.(in Chinese)陈晓曦,王延杰,刘恋.小波阈值去噪法的深入研究[J].激光与红外,2012,42(1):105-110.
[7]FAN Lulu,AN Chenbin.Research of image fusion algorithm based on LWT[J].Laser&Infrared,2012,42(9):1076-1079.(in Chinese)范璐璐,安成斌.基于提升小波变换的图像融合算法研究[J].激光与红外,2012,42(9):1076-1079.
[8]ZHANG Tianyu.Researchon wavelet image denoising algorithm based on WIENER filter[J].Journal of Jinggangshan University:Natural Science,2011,32(1):92-96.(in Chinese)张天瑜.基于维纳滤波的小波图像去噪算法研究[J].井冈山大学学报:自然科学版,2011,32(1):92-96.
[9]LU Gang,YAN Jingwen,KOU Yequan,et al.Dual-tree complex wavelet image denoising based on parental and neighboring[J].Optics and Precision Engineering,2009,17(4):916-922.(in Chinese)卢刚,闫敬文,寇业泉,等.由双树复数小波变换的父系数及邻域系数实现图像去噪[J].光学精密工程,2009,17(4):916-922.
[10]GONG Weiguo,LIU Xiaoying,LI Weihong,et al..Local adaptive image denoising based on double-density dualtree complex wavelet transform[J].Optics and Precision Engineering,2009,17(5):1171-1179.(in Chinese)龚卫国,刘晓营,李伟红,等.双密度双树复小波变换的局域自适应图像去噪[J].光学精密工程,2009,17(5):1171-1179.
[11]CHEN Xingjie,CHAI Xiaodong.Infrared image segmentation based on a simplified PCNN[J].Journal of Anhui University:Natural Science Edition,2010,34(1):74-77.(in Chinese)陈兴杰,柴晓冬.一种基于简化PCNN的红外图像分割方法[J].安徽大学学报:自然科学版,2010,34(1):74-77.
[12]WANG Yuanyuan,JIAO Jing.Detection of regions interests from breast tumor ultrasound images using improve PCNN[J].Optics and Precision Engineering,2011,19(6):1398-1405.(in Chinese)汪源源,焦静.改进型脉冲耦合神经网络检测乳腺肿瘤超声图像感兴趣区域[J].光学精密工程,2011,19(6):1398-1405.
[13]LI Qi,XIA Zhiwei,DING Shenghui,et al.Image denoising of CW THz images by use of non-local mean[J].Infrared and Laser Engineering.2012,41(2):517-522.(in Chinese)李琦,夏志伟,丁胜晖,等.采用非局部均值的连续太赫兹图像去噪处理[J].红外与激光工程,2012,41(2):517-522.
[14]LI Yan,TANG Xinyi,GE Jun,et al.Real-time multichannels infrared image acquisition system based on FPGA[J].Infrared and Laser Engineering.2012,41(5):1363-1368.(in Chinese)李燕,汤心溢,葛军,等.基于FPGA的多通道红外图像实时采集系统[J].红外与激光工程,2012,41(5):1363-1368.
[2]GUO Yecai,WANG Shaobo.Method of medical ultrasonic image de-noising based on PCNN in the wavelet domain[J].Journal of Anhui University:Natural Science Edition,2010,34(5):54-59.(in Chinese)郭业才,王绍波.基于PCNN的小波域超声医学图像去噪方法[J].安徽大学学报:自然科学版,2010,34(5):54-59.
[3]LI Yunhong,YIN Xin.Image denoising using wavelet packet transform based on correctional Wiener filtering[J].Computer Engineering and Applications,2012,48(21):182-185.(in Chinese)李云红,伊欣.基于修正维纳滤波的小波包变换图像去噪[J].计算机工程与应用,2012,48(21):182-185.
[4]LI Yunhong,YIN Xin.Wave adaptive denoising method based on PCNN[J].Optics and Precision Engineering,2012,20(9):2060-2067.(in Chinese)李云红,伊欣.基于脉冲耦合神经网络模型的小波自适应斑点噪声滤除算法[J].光学精密工程,2012,20(9):2060-2067.
[5]TONG Wuqin,LING Yongshun,HUANG Chaochao,et al.Processing method of IR image based on mathematical morphology and wavelet transform[J].Optics and Precision Engineering,2007,15(1):138-144.(in Chinese)同武勤,凌永顺,黄超超,等.数学形态学和小波变换的红外图像处理方法[J].光学精密工程,2007,15(1):138-144.
[6]CHEN Xiaoxi,WANG Yanjie,LIU Lian.Deep study on wavelet threshold method for image noise removing[J].Laser&Infrared,2012,42(1):105-110.(in Chinese)陈晓曦,王延杰,刘恋.小波阈值去噪法的深入研究[J].激光与红外,2012,42(1):105-110.
[7]FAN Lulu,AN Chenbin.Research of image fusion algorithm based on LWT[J].Laser&Infrared,2012,42(9):1076-1079.(in Chinese)范璐璐,安成斌.基于提升小波变换的图像融合算法研究[J].激光与红外,2012,42(9):1076-1079.
[8]ZHANG Tianyu.Researchon wavelet image denoising algorithm based on WIENER filter[J].Journal of Jinggangshan University:Natural Science,2011,32(1):92-96.(in Chinese)张天瑜.基于维纳滤波的小波图像去噪算法研究[J].井冈山大学学报:自然科学版,2011,32(1):92-96.
[9]LU Gang,YAN Jingwen,KOU Yequan,et al.Dual-tree complex wavelet image denoising based on parental and neighboring[J].Optics and Precision Engineering,2009,17(4):916-922.(in Chinese)卢刚,闫敬文,寇业泉,等.由双树复数小波变换的父系数及邻域系数实现图像去噪[J].光学精密工程,2009,17(4):916-922.
[10]GONG Weiguo,LIU Xiaoying,LI Weihong,et al..Local adaptive image denoising based on double-density dualtree complex wavelet transform[J].Optics and Precision Engineering,2009,17(5):1171-1179.(in Chinese)龚卫国,刘晓营,李伟红,等.双密度双树复小波变换的局域自适应图像去噪[J].光学精密工程,2009,17(5):1171-1179.
[11]CHEN Xingjie,CHAI Xiaodong.Infrared image segmentation based on a simplified PCNN[J].Journal of Anhui University:Natural Science Edition,2010,34(1):74-77.(in Chinese)陈兴杰,柴晓冬.一种基于简化PCNN的红外图像分割方法[J].安徽大学学报:自然科学版,2010,34(1):74-77.
[12]WANG Yuanyuan,JIAO Jing.Detection of regions interests from breast tumor ultrasound images using improve PCNN[J].Optics and Precision Engineering,2011,19(6):1398-1405.(in Chinese)汪源源,焦静.改进型脉冲耦合神经网络检测乳腺肿瘤超声图像感兴趣区域[J].光学精密工程,2011,19(6):1398-1405.
[13]LI Qi,XIA Zhiwei,DING Shenghui,et al.Image denoising of CW THz images by use of non-local mean[J].Infrared and Laser Engineering.2012,41(2):517-522.(in Chinese)李琦,夏志伟,丁胜晖,等.采用非局部均值的连续太赫兹图像去噪处理[J].红外与激光工程,2012,41(2):517-522.
[14]LI Yan,TANG Xinyi,GE Jun,et al.Real-time multichannels infrared image acquisition system based on FPGA[J].Infrared and Laser Engineering.2012,41(5):1363-1368.(in Chinese)李燕,汤心溢,葛军,等.基于FPGA的多通道红外图像实时采集系统[J].红外与激光工程,2012,41(5):1363-1368.