Abstract

Deep learning has demonstrated significant efficacy across various domains and is increasingly being embraced as a superior alternative to conventional machine learning models by a growing number of individuals. The utilization of deep learning methods, namely convolutional neural networks (CNN), offers significant advantages to the medical domain, which necessitates the processing and analysis of a substantial volume of images. The objective of this study is to construct a deep learning model that can effectively tackle the blood cell classification predicament, which is widely recognized as a highly formidable issue in the field of blood diagnosis. A convolutional neural network (CNN) architecture has been developed to autonomously categorize blood cell pictures into distinct cell subtypes. A series of experiments were conducted on a dataset of 13,000 distinct images depicting various categories of blood cells. The results demonstrate that the proposed model exhibits superior performance with respect to the evaluation metrics.

Description