Automated Leukemia Detection using K-means Clustering for Feature Extraction

Leukemia is a kind of blood cancer that may cause significant damage to a person's general health. It is characterized by the production of an excessive number of white blood cells. To address leukemia quickly and effectively, it is important to have a diagnosis that is both correct and quick. Not too long ago, experts started using AI methods to help find cancer much earlier. One of the hardest parts of making a method to find leukemia is separating the nuclei from the rest of the picture. When medical staff use quick and accurate division methods, they can find patients faster and treat them more effectively. So far, hybrid clustering algorithms have been very helpful in the process of picture segmentation in the field of medical image processing. To find leukemias like chronic myeloid leukemia (CML) and chronic lymphocytic leukemia (CLL), this study looks into segmentation methods that use machine learning (ML) and deep learning (DL). The study looks at how many ML and DL algorithms can be used to automatically diagnose different types of leukemia. It is checked to see how well the ML and DL algorithms do at segmentation, pre-processing, feature extraction, selection, and total classification accuracy.