CNN-Based Deep Learning Technique for the Brain Tumor Identification and Classification in MRI Images

Mandle, Anil Kumar; Sahu, Satya Prakash; Gupta, Govind P.

doi:10.4018/ijssci.304438

Cited by 27 publications

(16 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Finally, effective and precise classification was performed using KSVM-SSD. The suggested KSVM-SSD model was superior, with accuracy values of 99.2%, 99.36%, and 99.15%.Mandle et al [18] introduced an abnormal growth of either benign or malignant brain cells was referred to as a brain tumor. Tumors are recognized using magnetic resonance imaging.…”

Section: Related Workmentioning

confidence: 98%

Optimizing Brain Tumor Recognition with Ensemble support Vector-based Local Coati Algorithm and CNN Feature Extraction

Sumithra,

et al. 2024

Preprint

View full text Add to dashboard Cite

Nowadays, brain tumor (BT) recognition has become a common phenomenon in the healthcare industry. In the medical system,BT identification and classification can take a significant part in the diagnostics and considerations of the patients. BT is characterized as an abnormal mass of tissue in which the cells proliferate unexpectedly with no control over cell proliferation. In recent years, improvements in machine learning (ML), particularly deep learning (DL) procedures, have shown significant potential for mechanizing and improving these undertakings by utilizing medical imaging information. Also, we examine the difficulties and probabilities in this field, including information shortage, model interpretability, and moral contemplations. To overcome these challenges Ensemble support Vector-based Local Coati (ESV-LC) Algorithm is employed to identify and classify the brain tumor disease in the patients. For optimal classification, the features need to be extracted and this can be achieved by employing the Convolutional Neural network (CNN). To accurately classify BT, Ensemble Support Vector Machine (ESVM) is involved, which enhances classification performance, and hyperparameter tuning is performed through Local Search Coati Optimization. The Brain Tumor Image Dataset and Figshare Brain Tumor dataset are utilized for BT classification and identification. The performance metrics like Accuracy, Precision, Sensitivity, Specificity, and F1-score are to be evaluated, where the accuracy achieves the value of 98.3%, sensitivity of 97.6%, precision of 97.7%, specificity of 98.1%, and F1-score of 96.7% respectively.

show abstract

Section: Related Workmentioning

confidence: 98%

Optimizing Brain Tumor Recognition with Ensemble support Vector-based Local Coati Algorithm and CNN Feature Extraction

Sumithra,

et al. 2024

Preprint

View full text Add to dashboard Cite

show abstract

“…VGG16, VGG19, ResNet50, InceptionV3, and DenseNet201 achieved validation accuracy of 97.08%, VOLUME 11, 2023 96.43%, 89.29%, 92.86%, and 94.81%, respectively. This study [24] uses the VGG19 model for brain tumor categorization. The deep neural network is applied for the extraction of features.…”

Section: Literature Reviewmentioning

confidence: 99%

“…In this study [23], Bayesian Optimization-based technique is used for CNN hyperparameter optimization using the Figshare brain tumor dataset with an accuracy of 98.70%. In this study [24], a VGG19 model is used for brain tumor detection using Figshare dataset with an accuracy of 99.83%. In this study [25], a brain tumor detection approach, trained on the Figshare dataset is proposed, with an accuracy of 95.82%.…”

Section: As Represented Inmentioning

confidence: 99%

A CNN-Model to Classify Low-Grade and High-Grade Glioma From MRI Images

et al. 2023

View full text Add to dashboard Cite

Glioma is the most occurring brain tumor in the world. Its grade (level of severity) identification, crucial in its treatment planning, is most demanding in a clinical environment. Computeraided methods have been experimented with to identify the grade of glioma, out of which deep learning-based methods, due to their auto features engineering, have a good impact in terms of their achieved outcomes. In this study, convolutional neural networks (CNNs) have been explored and utilized for the classification of glioma grading, for example, low grade (grade I-II) and high grade (grade III-IV). A CNN-based model, which is light-weighted in terms of layers, size, and learnable parameters, has been proposed. Experimental tests were carried out on benchmarked publicly available datasets, for example, Brats-2017, Brats-2018, & Brats-2019. A locally developed dataset from Bahawal Victoria Hospital, Bahawalpur, Pakistan, has also been employed for experimentation and research to cross-validate the outcomes. Additionally, experiments have been carried out to compare the effectiveness of the proposed model, and results have been compared with the results of state-of-the-art pertained CNN models, i.e., resnet18, squeezenet, and alexnet. The proposed model achieved maximum standard evaluation measures on the benchmarked dataset, i.e., accuracy, specificity, and sensitivity at 97.85%, 98.88%, and 99.88%, respectively. Similarly, these measures were 98.89%, 99.28%, and 99.77% on a locally developed dataset, which is the best compared to the recent stateof-the-art related studies.INDEX TERMS Low and high-grade glioma grading, convolutional neural networks, MRI images.

show abstract

“…Deep Learning (DL) (Aggarwal et al, 2022;Mengi et al, 2023) provides critical infrastructure operators with valuable insights and predictive capabilities that can help them make more informed decisions, improve system resilience, and enhance public safety. By analyzing data from sensors and other sources, DL models can identify patterns and anomalies that may indicate equipment failure or maintenance needs so that it could be repaired before failures occur, reducing downtime (Mandle et al, 2022). Deep learning in critical infrastructure requires large amounts of training data for accurate and reliable modeling of the task.…”

Section: Introductionmentioning

confidence: 99%

A Novel Deep Federated Learning-Based Model to Enhance Privacy in Critical Infrastructure Systems

Sharma,

Singh,

Chhabra

et al. 2023

International Journal of Software Science and Computational Intelligence

View full text Add to dashboard Cite

Deep learning (DL) can provide critical infrastructure operators with valuable insights and predictive capabilities to help them make more informed decisions, improving system's robustness. However, training DL models requires large amounts of data, which can be costly to store in a centralized manner. Storing large amounts of sensitive critical infrastructure data in the cloud can pose significant security risks. Federated learning (FL) allows several clients to share learning data and train ML models. Unlike centralized models, FL does not require the sharing of client data. A novel framework is presented to train a VGG16 based CNN global model without sharing the data and only updating the local models among clients using federated averaging. For experimentation, MNIST dataset is used. The framework achieves high accuracy and keep data private using FL in critical infrastructures. The benefits and challenges of FL along with security vulnerabilities and attacks have been discussed along with the defenses that can be used to mitigate these attacks.

show abstract

CNN-Based Deep Learning Technique for the Brain Tumor Identification and Classification in MRI Images

Cited by 27 publications

References 38 publications

Optimizing Brain Tumor Recognition with Ensemble support Vector-based Local Coati Algorithm and CNN Feature Extraction

Optimizing Brain Tumor Recognition with Ensemble support Vector-based Local Coati Algorithm and CNN Feature Extraction

A CNN-Model to Classify Low-Grade and High-Grade Glioma From MRI Images

A Novel Deep Federated Learning-Based Model to Enhance Privacy in Critical Infrastructure Systems

Contact Info

Product

Resources

About