Image processing method and device for mammary peripheral tissue equalization

Abstract

The embodiment of the invention discloses an image processing method and device for mammary peripheral tissue equalization. The method comprises the following steps: extracting a mask image of effective human tissue from a mammary original image; carrying out grey level transformation on the original image so as to obtain an image to be processed; decomposing the image to be processed so as to obtain a low-frequency image and a plurality of high-frequency images; calculating according to the percentage composition of the mask image, the image to be processed and a gland so as to obtain a grey mapping curve; carrying out grey mapping on the low-frequency image through the grey mapping curve so as to obtain a mapped low-frequency image; carrying out gain processing on all high-frequency images so as to obtain gained high-frequency images; carrying out reconstruction processing on the mapped low-frequency image and the gained high-frequency images, and thus obtaining an equalized image. The method can carry out adaptive adjustment according to individual differences, thereby ensuring the equalization effect, reducing noises and artifacts, and improving the processing efficiency.

Description

technical field [0001] The invention relates to the field of medical image processing, in particular to an image processing method and device for balancing breast peripheral tissues. Background technique [0002] The distribution characteristics of breast tissue cause a wide range of grayscale differences between the central area and the edge area. If a fixed brightness contrast is used, only a part of the tissue can be observed. If the dynamic range compression method is used, the small compression range will easily cause insufficient equalization effect, and the compression range is too large. It will also cause the problem of excessive noise and artifacts, and in severe cases, it may also change the original gray distribution characteristics of the glandular tissue area. [0003] In the prior art, the large-scale convolution kernel method is usually used to equalize the peripheral tissue of the breast. This method specifically uses a fixed compression factor to process th...

AI Technical Summary

Problems solved by technology

[0002] The distribution characteristics of breast tissue cause a wide range of grayscale differences between the central area and the edge area. If a fixed brightness contrast is used, only a part of the tissue can be observed. If the dynamic range compression method is used, the small compression range will easily cause insufficient equalization effect, and the compression range is too large. It will also cause problems of excessive noise and artifacts, and in severe cases, it may also change the original gray distribution characteristics of the glandular tissue area

[0003] In the prior art, the large-scale convolution kernel method is usually used to equalize the peripheral tissue of the breast. This method specifically uses a fixed compression factor to process the image as a whole. Since the tissue information on the side of the breast wall close to the breast wall is quite different from the density of the peripheral tissue, A fixed compression factor is used. If the compression factor is too large, the original gray features of the gland area may change. If the compression factor is too small, the equalization effect is not enough, and the peripheral tissues cannot be seen clearly. Therefore, a fixed compression factor cannot guarantee that all images in the image In addition, the large-size convolution kernel method often uses a convolution kernel size of 100-300, resulting in a very large amount of calculation for the equalization process and low processing efficiency.

Images