Table 10.

Performance comparison of the state-of-the-art methods and the proposed approach using various evaluation measurements on brain MRI dataset (Number of utilized images 595 (where, normal = 115, and abnormal = 480)).

Published Methods	Used Methods	True Positive	True Negative	False Positive	False Negative
Orouskhani, et al. [44]	Conditional Deep Triplet Network	375	175	60	8
Inglese, et al. [45]	Decision Support System	360	178	57	7
Mandle, et al. [46]	Kernel-based SVM	350	177	63	9
Abdulmunem, et al. [47]	Deep Belief Network	365	178	67	10
Jang, et al. [48]	Sorting Algorithm	380	174	66	8
Popuri, et al. [49]	Ensemble Learning	350	175	61	7
Latif, et al. [50]	Neural-Network-Based Features with SVM Classifier	355	176	64	11
Nawaz, et al. [51]	Multilayer Perception, J48, Meta Bagging, Random Tree	375	169	59	6
Assam, et al. [52]	Random Forest	380	172	58	7
Islam, et al. [53]	Convolutional Neural Network	370	174	60	9
Dehkordi, et al. [54]	Evolutionary Convolutional Neural Network	360	173	55	8
Krishna, et al. [55]	Local Linear Radial Basis Function Neural Network	355	177	62	9
Takrouni, et al. [56]	Deep Convolutional Network	365	171	68	10
Fayaz, et al. [57]	Convolutional Neural Network	370	178	60	8
Proposed Approach	Logistic Regression	405	185	30	5