Using the technique of color image processing to enhance the cytomorphological deformation

摘要

Abstract: A great deal of research has been carried out by biologists, pathologists, and biomedical physicists on the studies of the metamorphosis in various types of cells with symptoms of cancerous disease. Color and texture of the cell and their interrelationships are important features for analyzing cells and prove successful to differentiate abnormal from normal ones. However, to categorize the abnormal (or suspicious) cell into cancerous or non-cancerous ones, more information rather than that obtained only from the observations on the microscopic images of the smear are needed, and therefore, further steps, such as biopsy, etc., have to be taken. In this paper, color image processing technique is introduced as a means to enhance the visualization and diagnostic capability of a human expert, and we hope that it would come out to be an effective tool in identifying the non-cancerous cells from the cancerous ones even when they look alike under the microscope for some reason. A real microscopic image is first resolved into several spectral-component images. More and useful features are extracted, respectively, from 0.4 to 0.5 $mu@m, 0.5 to 0.6 $mu@m, and 0.6 to 0.7 $mu@m spectral bands. Combination of these different spectral-band images after separate processings derives a color image, which will sharpen the distinguishing features between cancerous and non-cancerous cells, even when they all look alike originally both morphologically and chromatically under the microscope. In this paper some recent promising results obtained with real color image processing in our laboratory are given. To improve the resolution, 512 $MUL 512 pixel image, other than 256 $MUL 256, we employed for processing. !11