Contrast Limited Adaptive Histogram Equalization Approach Contrast Enhancement in Liver Tumor

Medical images consist of many unwanted and irrelevant parts in the original format of scanned images. To eliminate the infuriating segments in medical images, a few preprocessing techniques require better visualization of the images before finding the disease in particular organs. Images from the real world with low contrast, noise, and variability are crucial for a number of reasons. This article defines a method for categorizing and identifying liver tumors based on machine learning and image processing. One of the most crucial processes in image processing is smoothing out the image. It is simpler to extract characteristics and classify them after this step. Therefore, a suitable filtering strategy must be used while analyzing biological images. If one wishes to get exceptional outcomes, preprocessing must select the best liver tumor image contrast algorithm. Segmentation methods might be used in order to remove undesired components from liver imaging preprocessing. In this study, liver tumor prediction was based on a preprocessing technique to analyze, grayscale, and enhance the image. To reduce image noise, the histogram equalization - Contrast Limited Adaptive Histogram Equalization (CLAHE) approach is used at the preprocessing step of the image synthesis process. The CLAHE technique in liver tumor disease prediction enriches the production of results that are efficient in performance and is also discussed in the augmentation technique because it extracts the images from the original dataset image for available training sets. LiTS17 (liver tumor segmentation challenge 2017) dataset was used in the proposed liver tumor.