Detection of Subtype Blood Cells using Deep Learning
Gupta, D. G.
; Khanna, A.
; Wang, B.
; Qian, J.
;
Rodrigues, J. R.
; Tiwari, P.
; Li, Q.
; Albuquerque, V.
Cognitive Systems Research Vol. 52, Nº -, pp. 1036 - 1044, December, 2018.
ISSN (print): 1389-0417
ISSN (online):
Scimago Journal Ranking: 0,29 (in 2018)
Digital Object Identifier: 10.1016/j.cogsys.2018.08.022
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.
