Blood Cancer Detection Using Improved Machine Learning Algorithm
N. P. Dharani, G. Sujatha, Rajneesh Rani
Abstract
The occurrence of blood cancer has been on rise over the last decade, and treatment of this disease begins as soon as possible following a correct diagnosis. There are a variety of tests and medical experts involved in the diagnostic process, which is time-consuming and expensive. In order to make an accurate prediction of its outcome, an automatic diagnosis system is necessary. This paper suggests a method for blood cancer detection using Improved Machine Learning Algorithm like Ensemble Method with the combination of Effective Fuzzy C Means (EFCM) and Iterative Morphological Process (IMP). The use of EFCM and IMP techniques helps to segment and analyse the blood image data, allowing for the identification of specific characteristics associated with blood cancers. This segmentation process enables the algorithm to focus on the relevant regions of interest, facilitating more accurate and targeted detection of cancerous cells. Moreover, a pre-processing and enhancement methods have been used to the image of blood. By utilizing Machine Learning to process images of blood cancers, accurate diagnosis is achieved, diagnosis times is reduced, and diagnostic testing is provided faster, cheaper, and with greater safety.