A Novel and Effective Brain Tumor Classification Model Using Deep Feature Fusion and Famous Machine Learning Classifiers

Abstract

Brain tumors are difficult to treat and cause substantial fatalities worldwide. Medical professionals visually analyze the images and mark out the tumor regions to identify brain tumors, which is time-consuming and prone to error. Researchers have proposed automated methods in recent years to detect brain tumors early. These approaches, however, encounter difficulties due to their low accuracy and large false-positive values. An efficient tumor identification and classification approach is required to extract robust features and perform accurate disease classification. This paper proposes a novel multiclass brain tumor classification method based on deep feature fusion. The MR images are preprocessed using min-max normalization, and then extensive data augmentation is applied to MR images to overcome the lack of data problem. The deep CNN features obtained from transfer learned architectures such as AlexNet, GoogLeNet, and ResNet18 are fused to build a single feature vector and then loaded into Support Vector Machine (SVM) and K-nearest neighbor (KNN) to predict the final output. The novel feature vector contains more information than the independent vectors, boosting the proposed method’s classification performance. The proposed framework is trained and evaluated on 15,320 Magnetic Resonance Images (MRIs). The study shows that the fused feature vector performs better than the individual vectors. Moreover, the proposed technique performed better than the existing systems and achieved accuracy of 99.7%; hence, it can be used in clinical setup to classify brain tumors from MRIs.

Isolated Convolutional-Neural-Network-Based Deep-Feature Extraction for Brain Tumor Classification Using Shallow Classifier

“…In this work, various isolated trained CNNs (19, 22, and 25 layers) were utilized to extract the deep features. The deep features were extracted using the transfer learning method, as discussed in [ 26 , 35 ]. The authors computed the deep features of the pre-trained model for the brain MRI dataset and concatenated various features for better classification performance.…”

Potential roles of transformers in brain tumor diagnosis and treatment

“…In the past decade, with the rise of CNNs and emerging leading computational resources (e.g., graphics processing unit and tensor processing unit, multiple strategies have been put forth for BT classification by calibrating the CNN models, such as VGG16, AlexNet, ResNets, DenseNets, Inception, and Xception, which had already been successfully applied for various computer‐based visualizations) [57–62] . The above pre‐trained localized convolution‐based CNN models indicated excellent BT classification capability across vast datasets [63–65] . However, despite their tremendous success, they carry inductive biases, such as the local receptive field's translation equivariance.…”

“…[57][58][59][60][61][62] The above pre-trained localized convolution-based CNN models indicated excellent BT classification capability across vast datasets. [63][64][65] However, despite their tremendous success, they carry inductive biases, such as the local receptive field's translation equivariance. Because of these biases, CNN models present difficulties while learning long-range information; furthermore, CNNs generally require data augmentation for better performance owing to their need for local pixel differentiation during learning.…”

MEHW‐SVM multi‐kernel approach for improved brain tumour classification

“…The study places significant emphasis on the critical importance of brain cancer categorization, which has traditionally relied upon the expertise of clinicians [14]. The authors emphasize the need for improved automated tumour categorization systems to assist radiologists in achieving precise diagnostic outcomes.…”