[Retracted] Deep Learning Model for the Automatic Classification of White Blood Cells

Table 1

Comparison of existing state-of-art models.

Citation/year of publishing	Reference	Approach	Objective
[1]/2021	CMaP	CNN	To implement a system to diagnosis acute leukaemia using WBC images
[2]/2021	ICPSC	VGG16, KNN, CNN	To implement transfer learning algorithm for the diagnosing and classifying WBC images
[3]/2021	Artificial cells, nanomedicine, and biotechnology	CNN, VGG16, VGG19, Inception-V3, ResNet-50	To implement algorithm for TWO-DCNN for WBC classification
[4]/2021	The international conference on intelligent engineering and management	CNN, VGG16, VGG19, ResNet50, ResNet101 and inception V3	To automatically classify sickle cell disease by using data augmentation techniques to yield better accuracy
[7]/2020	Biotechnology & biotechnological equipment	CNN and faster R-CNN	To implement deep learning method that identifies lymphoma cells from blood cells dataset using pre-trained networks
[8]/2020	IRBM	CNN, RNN and canonical correlation analysis (CCA).	To implement CCA method to observe the effect of overlapping nuclei
[9]/2020	Soft computing	CNN, ELM and MRMR algorithm.	To pre-train AlexNet, VGG16, GoogleNet, and ResNet as feature extractors and predict and classify blood cells
[10]/2019	CMaP	CNN, VGG16	To implement a system for the classification of eight blood cells groups with high accuracy by using a transfer learning approach with convolutional neural networks
[11]/2019	The soft computing and signal processing	CNN, LeNet, VGG16, xception	To implement deep learning system by using CNN for classification of WBC
[12]/2019	JBaH	CNN, MGCNN	To implement a gabor wavelet and deep CNN named as MGCNN on medical hyper spectral imaging for blood cell classification