基于多尺度Retinex的医学图像增强方法研究

目的增强医学图像中的暗区信息和图像对比度,压缩医学图像的动态范围。方法提出并改进了基于多尺度Retinex方法的医学图像增强处理方法,在3种标准偏差下,求得高斯环境函数;然后使用3种不同的误差函数对医学图像进行卷积操作,将3种标准偏差尺度下得到的结果进行加权平均;最后将输出灰度值进行修正,得到可用于显示的结果。结果改进的MSR算法既可实现低对比度的医学图像增强,又能实现图像的动态范围压缩,能够显著提高暗区医学图像的信息。结论改进MSR算法能够显著提高暗区图像的信息量,其增强后的信息熵是原图像的2倍多,该方法克服了常规医学增强方法的不足,能够满足医生临床诊断的要求。

Enhancement of medical images based multi-scale Retinex

Objective To enhance the information of hidden area of medical images and image contrast,and compress the dynamic range.Methods An improved enhancement algorithm of medical images based on multi-scale Retinex was presented.The three different Gaussian filter coefficients under three different deviations were calculated,and the convolution operation was implemented between the image distribution and Gaussian filters.Weighted average of multi-scale was gained and mapped to gray range of display device.Results With this improved method,image contrast enhancement,sharpening and dynamic range compression were achieved at the same time.The information of hidden area of images was obviously enhanced.Conclusion Improved MSR can observably improve entropy of medical images,and also overcome the lack of enhancement of traditional methods and satisfy the clinic demand.