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

Abstract

In today’s world, a brain tumor is one of the most serious diseases. If it is detected at an advanced stage, it might lead to a very limited survival rate. Therefore, brain tumor classification is crucial for appropriate therapeutic planning to improve patient life quality. This research investigates a deep-feature-trained brain tumor detection and differentiation model using classical/linear machine learning classifiers (MLCs). In this study, transfer learning is used to obtain deep brain magnetic resonance imaging (MRI) scan features from a constructed convolutional neural network (CNN). First, multiple layers (19, 22, and 25) of isolated CNNs are constructed and trained to evaluate the performance. The developed CNN models are then utilized for training the multiple MLCs by extracting deep features via transfer learning. The available brain MRI datasets are employed to validate the proposed approach. The deep features of pre-trained models are also extracted to evaluate and compare their performance with the proposed approach. The proposed CNN deep-feature-trained support vector machine model yielded higher accuracy than other commonly used pre-trained deep-feature MLC training models. The presented approach detects and distinguishes brain tumors with 98% accuracy. It also has a good classification rate (97.2%) for an unknown dataset not used to train the model. Following extensive testing and analysis, the suggested technique might be helpful in assisting doctors in diagnosing brain tumors.

Dendrimer: An update on recent developments and future opportunities for the brain tumors diagnosis and treatment

“…Magnetic resonance imaging (MRI) technique was the first one utilised to detect and diagnose brain tumour lesions ( Khan et al, 2020 ; Almalki et al, 2022 ; Wu et al, 2022 ; Yazdan et al, 2022 ). Meanwhile, gadolinium (Gd)-chelated diagnostic agents are extensively utilized as contrast agents for tumor imaging ( Rodríguez-Galván et al, 2020 ).…”

“…Therefore, molecular imaging techniques would be useful for forecasting therapy response, prudently segmenting patients, measuring biodistribution, and determining the drug release profile (Bernsen et al, 2013;Li et al, 2021). Magnetic resonance imaging (MRI) technique was the first one utilised to detect and diagnose brain tumour lesions (Khan et al, 2020;Almalki et al, 2022;Wu et al, 2022;Yazdan et al, 2022). Meanwhile, gadolinium (Gd)-chelated diagnostic agents are extensively utilized as contrast agents for tumor imaging (Rodríguez-Galván et al, 2020).…”

Blockchain-Based Deep CNN for Brain Tumor Prediction Using MRI Scans

“…Overall, 96.47% accuracy, 98.24% specificity, and 96.32% sensitivity were attained by the suggested model. The researchers in [ 34 ] utilized transfer learning to extract the characteristics from a convolutional neural network that has been built for deep brain magnetic resonance imaging scans. To assess the performance, multiple layers of separate CNNs are created.…”

WBM-DLNets: Wrapper-Based Metaheuristic Deep Learning Networks Feature Optimization for Enhancing Brain Tumor Detection

“…In healthcare imaging, machine learning has been utilized for disease diagnosis in breast [ 9 , 10 ], brain [ 11 , 12 , 13 ], and lung [ 14 , 15 ] tumors. Recently, research on brain tumor segmentation, with numerous segmentation methods using different datasets, has increased considerably.…”

“…Recently, research on brain tumor segmentation, with numerous segmentation methods using different datasets, has increased considerably. Currently, three types of segmentation models have been developed [ 16 ]: supervised machine learning [ 17 ], clustering-based segmentation [ 18 , 19 ], and deep learning [ 13 ].…”