Hematologic Cancer Detection Using White Blood Cancerous Cells Empowered with Transfer Learning and Image Processing

Table 1

Limitations of previous studies (it explains the results of previous studies and shows the previous studies research gap).

Publications	Methods	Datasets	Accuracy (%)	Limitations
Pansombut et al. [35]	CNN	Image (public)	80	(i) Low-ratio dataset
				(ii) Data image processing layer
Madhukar et al. [34]	SVM	Image (public)	93.5	(i) Low-ratio dataset
				(ii) Minor image classes
				(iii) Data image processing layer
Supardi et al. [33]	KNN	Image (public)	86	(i) Low-ratio dataset
				(ii) Data image processing layer
Patel and Mishra [32]	SVM	Image (public)	93.57	(i) Data image processing layer
Laosai and Chamnongthai [31]	SVM	Image (public)	92	(i) Low-ratio dataset
				(ii) Data image processing layer
Faivdullah et al. [30]	SVM	Feature (public)	79.38	(i) Required handcrafted features
Setiawan et al. [29]	SVM, K-means	Image (public)	87	(i) Low-diverse dataset
				(ii) Low-ratio dataset
				(iii) Data image processing layer
Kumar et al. [28]	KNN, Naïve Bayes, CNN	Image (public)	92.8	(i) Low-ratio dataset
				(ii) Less number of classes
Loey et al. [27]	CNN, AlexNet	Image (public)	94.3	(i) Low-ratio dataset
				(ii) Data image processing
				(iii) Less number of classes