Detection of subtype blood cells using deep learning. (December 2018)

• Record Type: Journal Article
• Authors: Tiwari, Prayag; Qian, Jia; Li, Qiuchi; Wang, Benyou; Gupta, Deepak; Khanna, Ashish; Rodrigues, Joel J.P.C.; de Albuquerque, Victor Hugo C.
• Is Part Of: Cognitive systems research. Volume 52(2018)
• Page Start: 1036
• Page End: 1044
• Publication Date: 2018-12
• Subjects: Blood cells -- Classification -- CNN; Cognition -- Periodicals; Cognitive engineering (System design) -- Periodicals; Artificial intelligence -- Periodicals; 153.05
• DOI: 10.1016/j.cogsys.2018.08.022
• Languages: English
• ISSNs: 1389-0417

Abstract

Abstract: Deep Learning has already shown power in many application fields, and is accepted by more and more people as a better approach than the traditional machine learning models. In particular, the implementation of deep learning algorithms, especially Convolutional Neural Networks (CNN), brings huge benefits to the medical field, where a huge number of images are to be processed and analyzed. This paper aims to develop a deep learning model to address the blood cell classification problem, which is one of the most challenging problems in blood diagnosis. A CNN-based framework is built to automatically classify the blood cell images into subtypes of the cells. Experiments are conducted on a dataset of 13k images of blood cells with their subtypes, and the results show that our proposed model provide better results in terms of evaluation parameters.