Learning Architecture for Brain Tumor Classification Based on Deep Convolutional Neural Network: Classic and ResNet50
<b>Background:</b> Accurate classification of brain tumors in medical images is vital for effective diagnosis and treatment planning, which improves the patient’s survival rate. In this paper, we investigate the application of Convolutional Neural Networks (CNN) as a powerful tool for en...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-03-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/15/5/624 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850228196381818880 |
|---|---|
| author | Rabei Raad Ali Noorayisahbe Mohd Yaacob Marwan Harb Alqaryouti Ala Eddin Sadeq Mohamed Doheir Musab Iqtait Eko Hari Rachmawanto Christy Atika Sari Siti Salwani Yaacob |
| author_facet | Rabei Raad Ali Noorayisahbe Mohd Yaacob Marwan Harb Alqaryouti Ala Eddin Sadeq Mohamed Doheir Musab Iqtait Eko Hari Rachmawanto Christy Atika Sari Siti Salwani Yaacob |
| author_sort | Rabei Raad Ali |
| collection | DOAJ |
| description | <b>Background:</b> Accurate classification of brain tumors in medical images is vital for effective diagnosis and treatment planning, which improves the patient’s survival rate. In this paper, we investigate the application of Convolutional Neural Networks (CNN) as a powerful tool for enhancing diagnostic accuracy using a Magnetic Resonance Imaging (MRI) dataset. <b>Method:</b> This study investigates the application of CNNs for brain tumor classification using a dataset of Magnetic Resonance Imaging (MRI) with a resolution of 200 × 200 × 1. The dataset is pre-processed and categorized into three types of tumors: Glioma, Meningioma, and Pituitary. The CNN models, including the Classic layer architecture and the ResNet50 architecture, are trained and evaluated using an 80:20 training-testing split. <b>Results:</b> The results reveal that both architectures accurately classify brain tumors. Classic layer architecture achieves an accuracy of 94.55%, while the ResNet50 architecture surpasses it with an accuracy of 99.88%. Compared to previous studies and 99.34%, our approach offers higher precision and reliability, demonstrating the effectiveness of ResNet50 in capturing complex features. <b>Conclusions:</b> The study concludes that CNNs, particularly the ResNet50 architecture, exhibit effectiveness in classifying brain tumors and hold significant potential in aiding medical professionals in accurate diagnosis and treatment planning. These advancements aim to further enhance the performance and practicality of CNN-based brain tumor classification systems, ultimately benefiting healthcare professionals and patients. For future research, exploring transfer learning techniques could be beneficial. By leveraging pre-trained models on large-scale datasets, researchers can utilize knowledge from other domains to improve brain tumor classification tasks, particularly in scenarios with limited annotated data. |
| format | Article |
| id | doaj-art-13d19ebb1b164cdeb5627f09de167380 |
| institution | OA Journals |
| issn | 2075-4418 |
| language | English |
| publishDate | 2025-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj-art-13d19ebb1b164cdeb5627f09de1673802025-08-20T02:04:36ZengMDPI AGDiagnostics2075-44182025-03-0115562410.3390/diagnostics15050624Learning Architecture for Brain Tumor Classification Based on Deep Convolutional Neural Network: Classic and ResNet50Rabei Raad Ali0Noorayisahbe Mohd Yaacob1Marwan Harb Alqaryouti2Ala Eddin Sadeq3Mohamed Doheir4Musab Iqtait5Eko Hari Rachmawanto6Christy Atika Sari7Siti Salwani Yaacob8Technical Engineering College for Computer and AI, Northern Technical University, Mosul 41000, IraqCenter for Software Technology and Management (SOFTAM), Faculty of Information Science and Technology, University Kebangsaan Malaysia (UKM), Selangor 43600, MalaysiaDepartment of English Language-Literature and Translation, Zarqa University, Zarqa 13110, JordanDepartment of English Language-Literature and Translation, Zarqa University, Zarqa 13110, JordanDepartment of Technology Management, Universiti Teknikal Malaysia Melaka, Malacca 76100, MalaysiaDepartment of Data Science and Artificial Intelligence, Zarqa University, Zarqa 13110, JordanFaculty of Computer Science, Universitas Dian Nuswantoro, Semarang 50131, IndonesiaFaculty of Computer Science, Universitas Dian Nuswantoro, Semarang 50131, IndonesiaDepartment of Computer Science, Faculty of Computing, Universiti Malaysia Pahang Al-Sultan Abdullah, Pahang 26600, Malaysia<b>Background:</b> Accurate classification of brain tumors in medical images is vital for effective diagnosis and treatment planning, which improves the patient’s survival rate. In this paper, we investigate the application of Convolutional Neural Networks (CNN) as a powerful tool for enhancing diagnostic accuracy using a Magnetic Resonance Imaging (MRI) dataset. <b>Method:</b> This study investigates the application of CNNs for brain tumor classification using a dataset of Magnetic Resonance Imaging (MRI) with a resolution of 200 × 200 × 1. The dataset is pre-processed and categorized into three types of tumors: Glioma, Meningioma, and Pituitary. The CNN models, including the Classic layer architecture and the ResNet50 architecture, are trained and evaluated using an 80:20 training-testing split. <b>Results:</b> The results reveal that both architectures accurately classify brain tumors. Classic layer architecture achieves an accuracy of 94.55%, while the ResNet50 architecture surpasses it with an accuracy of 99.88%. Compared to previous studies and 99.34%, our approach offers higher precision and reliability, demonstrating the effectiveness of ResNet50 in capturing complex features. <b>Conclusions:</b> The study concludes that CNNs, particularly the ResNet50 architecture, exhibit effectiveness in classifying brain tumors and hold significant potential in aiding medical professionals in accurate diagnosis and treatment planning. These advancements aim to further enhance the performance and practicality of CNN-based brain tumor classification systems, ultimately benefiting healthcare professionals and patients. For future research, exploring transfer learning techniques could be beneficial. By leveraging pre-trained models on large-scale datasets, researchers can utilize knowledge from other domains to improve brain tumor classification tasks, particularly in scenarios with limited annotated data.https://www.mdpi.com/2075-4418/15/5/624deep learningConvolutional Neural NetworksResNet-50image classificationmagnetic resonance imaging |
| spellingShingle | Rabei Raad Ali Noorayisahbe Mohd Yaacob Marwan Harb Alqaryouti Ala Eddin Sadeq Mohamed Doheir Musab Iqtait Eko Hari Rachmawanto Christy Atika Sari Siti Salwani Yaacob Learning Architecture for Brain Tumor Classification Based on Deep Convolutional Neural Network: Classic and ResNet50 Diagnostics deep learning Convolutional Neural Networks ResNet-50 image classification magnetic resonance imaging |
| title | Learning Architecture for Brain Tumor Classification Based on Deep Convolutional Neural Network: Classic and ResNet50 |
| title_full | Learning Architecture for Brain Tumor Classification Based on Deep Convolutional Neural Network: Classic and ResNet50 |
| title_fullStr | Learning Architecture for Brain Tumor Classification Based on Deep Convolutional Neural Network: Classic and ResNet50 |
| title_full_unstemmed | Learning Architecture for Brain Tumor Classification Based on Deep Convolutional Neural Network: Classic and ResNet50 |
| title_short | Learning Architecture for Brain Tumor Classification Based on Deep Convolutional Neural Network: Classic and ResNet50 |
| title_sort | learning architecture for brain tumor classification based on deep convolutional neural network classic and resnet50 |
| topic | deep learning Convolutional Neural Networks ResNet-50 image classification magnetic resonance imaging |
| url | https://www.mdpi.com/2075-4418/15/5/624 |
| work_keys_str_mv | AT rabeiraadali learningarchitectureforbraintumorclassificationbasedondeepconvolutionalneuralnetworkclassicandresnet50 AT noorayisahbemohdyaacob learningarchitectureforbraintumorclassificationbasedondeepconvolutionalneuralnetworkclassicandresnet50 AT marwanharbalqaryouti learningarchitectureforbraintumorclassificationbasedondeepconvolutionalneuralnetworkclassicandresnet50 AT alaeddinsadeq learningarchitectureforbraintumorclassificationbasedondeepconvolutionalneuralnetworkclassicandresnet50 AT mohameddoheir learningarchitectureforbraintumorclassificationbasedondeepconvolutionalneuralnetworkclassicandresnet50 AT musabiqtait learningarchitectureforbraintumorclassificationbasedondeepconvolutionalneuralnetworkclassicandresnet50 AT ekoharirachmawanto learningarchitectureforbraintumorclassificationbasedondeepconvolutionalneuralnetworkclassicandresnet50 AT christyatikasari learningarchitectureforbraintumorclassificationbasedondeepconvolutionalneuralnetworkclassicandresnet50 AT sitisalwaniyaacob learningarchitectureforbraintumorclassificationbasedondeepconvolutionalneuralnetworkclassicandresnet50 |