A thresholding approach for detection of sputum cell for lung cancer early diagnosis

In this paper, we address the problem of detection and extraction of sputum cells that help in lung cancer early diagnosis. Our approach is based on thresholding classifier looking at the distribution of sputum pixels and non sputum pixels in RGB space for extracting the sputum cell from the raw sputum image. In this method the problem is viewed as a segmentation problem focusing on extraction of such sputum cells from the images whereby we want to partition the image into sputum cell regions including the nuclei, cytoplasm and the background that includes all the rest. These cells will be analyzed to check whether they are cancerous or not. In this study, we used a database of 100 sputum color images to test the thresholding classifier by comparing it with the ground truth data of extracted sputum cells and it has shown a better extraction result than previous work. Moreover, we computed a histogram for different color spaces (RGB, YCbCr, HSV, L*a*b* and XYZ) to find the best color space with low false detection rate. We used some performance criteria such as precision, specificity and accuracy to evaluate the improved thresholding classifier.