A hybrid deep CNN model for brain tumor image multi-classification
Abstract The current approach to diagnosing and classifying brain tumors relies on the histological evaluation of biopsy samples, which is invasive, time-consuming, and susceptible to manual errors. These limitations underscore the pressing need for a fully automated, deep-learning-based multi-class...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2024-01-01
|
| Series: | BMC Medical Imaging |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12880-024-01195-7 |
| _version_ | 1797349630121345024 |
|---|---|
| author | Saravanan Srinivasan Divya Francis Sandeep Kumar Mathivanan Hariharan Rajadurai Basu Dev Shivahare Mohd Asif Shah |
| author_facet | Saravanan Srinivasan Divya Francis Sandeep Kumar Mathivanan Hariharan Rajadurai Basu Dev Shivahare Mohd Asif Shah |
| author_sort | Saravanan Srinivasan |
| collection | DOAJ |
| description | Abstract The current approach to diagnosing and classifying brain tumors relies on the histological evaluation of biopsy samples, which is invasive, time-consuming, and susceptible to manual errors. These limitations underscore the pressing need for a fully automated, deep-learning-based multi-classification system for brain malignancies. This article aims to leverage a deep convolutional neural network (CNN) to enhance early detection and presents three distinct CNN models designed for different types of classification tasks. The first CNN model achieves an impressive detection accuracy of 99.53% for brain tumors. The second CNN model, with an accuracy of 93.81%, proficiently categorizes brain tumors into five distinct types: normal, glioma, meningioma, pituitary, and metastatic. Furthermore, the third CNN model demonstrates an accuracy of 98.56% in accurately classifying brain tumors into their different grades. To ensure optimal performance, a grid search optimization approach is employed to automatically fine-tune all the relevant hyperparameters of the CNN models. The utilization of large, publicly accessible clinical datasets results in robust and reliable classification outcomes. This article conducts a comprehensive comparison of the proposed models against classical models, such as AlexNet, DenseNet121, ResNet-101, VGG-19, and GoogleNet, reaffirming the superiority of the deep CNN-based approach in advancing the field of brain tumor classification and early detection. |
| first_indexed | 2024-03-08T12:33:04Z |
| format | Article |
| id | doaj.art-249620c0fc9c4ff1b6904e0a58be6ab0 |
| institution | Directory Open Access Journal |
| issn | 1471-2342 |
| language | English |
| last_indexed | 2024-03-08T12:33:04Z |
| publishDate | 2024-01-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Medical Imaging |
| spelling | doaj.art-249620c0fc9c4ff1b6904e0a58be6ab02024-01-21T12:39:46ZengBMCBMC Medical Imaging1471-23422024-01-0124112110.1186/s12880-024-01195-7A hybrid deep CNN model for brain tumor image multi-classificationSaravanan Srinivasan0Divya Francis1Sandeep Kumar Mathivanan2Hariharan Rajadurai3Basu Dev Shivahare4Mohd Asif Shah5Department of Computer Science and Engineering, Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and TechnologyDepartment of Electronics and Communication Engineering, PSNA College of Engineering and TechnologySchool of Computing Science and Engineering, Galgotias UniversitySchool of Computing Science and Engineering, VIT Bhopal University, Bhopal–Indore Highway KothrikalanSchool of Computing Science and Engineering, Galgotias UniversityDepartment of Economics, Kabridahar UniversityAbstract The current approach to diagnosing and classifying brain tumors relies on the histological evaluation of biopsy samples, which is invasive, time-consuming, and susceptible to manual errors. These limitations underscore the pressing need for a fully automated, deep-learning-based multi-classification system for brain malignancies. This article aims to leverage a deep convolutional neural network (CNN) to enhance early detection and presents three distinct CNN models designed for different types of classification tasks. The first CNN model achieves an impressive detection accuracy of 99.53% for brain tumors. The second CNN model, with an accuracy of 93.81%, proficiently categorizes brain tumors into five distinct types: normal, glioma, meningioma, pituitary, and metastatic. Furthermore, the third CNN model demonstrates an accuracy of 98.56% in accurately classifying brain tumors into their different grades. To ensure optimal performance, a grid search optimization approach is employed to automatically fine-tune all the relevant hyperparameters of the CNN models. The utilization of large, publicly accessible clinical datasets results in robust and reliable classification outcomes. This article conducts a comprehensive comparison of the proposed models against classical models, such as AlexNet, DenseNet121, ResNet-101, VGG-19, and GoogleNet, reaffirming the superiority of the deep CNN-based approach in advancing the field of brain tumor classification and early detection.https://doi.org/10.1186/s12880-024-01195-7Brain tumor gradingHybrid deep learningHybrid convolutional neural networkGrid searchHyperparameters |
| spellingShingle | Saravanan Srinivasan Divya Francis Sandeep Kumar Mathivanan Hariharan Rajadurai Basu Dev Shivahare Mohd Asif Shah A hybrid deep CNN model for brain tumor image multi-classification BMC Medical Imaging Brain tumor grading Hybrid deep learning Hybrid convolutional neural network Grid search Hyperparameters |
| title | A hybrid deep CNN model for brain tumor image multi-classification |
| title_full | A hybrid deep CNN model for brain tumor image multi-classification |
| title_fullStr | A hybrid deep CNN model for brain tumor image multi-classification |
| title_full_unstemmed | A hybrid deep CNN model for brain tumor image multi-classification |
| title_short | A hybrid deep CNN model for brain tumor image multi-classification |
| title_sort | hybrid deep cnn model for brain tumor image multi classification |
| topic | Brain tumor grading Hybrid deep learning Hybrid convolutional neural network Grid search Hyperparameters |
| url | https://doi.org/10.1186/s12880-024-01195-7 |
| work_keys_str_mv | AT saravanansrinivasan ahybriddeepcnnmodelforbraintumorimagemulticlassification AT divyafrancis ahybriddeepcnnmodelforbraintumorimagemulticlassification AT sandeepkumarmathivanan ahybriddeepcnnmodelforbraintumorimagemulticlassification AT hariharanrajadurai ahybriddeepcnnmodelforbraintumorimagemulticlassification AT basudevshivahare ahybriddeepcnnmodelforbraintumorimagemulticlassification AT mohdasifshah ahybriddeepcnnmodelforbraintumorimagemulticlassification AT saravanansrinivasan hybriddeepcnnmodelforbraintumorimagemulticlassification AT divyafrancis hybriddeepcnnmodelforbraintumorimagemulticlassification AT sandeepkumarmathivanan hybriddeepcnnmodelforbraintumorimagemulticlassification AT hariharanrajadurai hybriddeepcnnmodelforbraintumorimagemulticlassification AT basudevshivahare hybriddeepcnnmodelforbraintumorimagemulticlassification AT mohdasifshah hybriddeepcnnmodelforbraintumorimagemulticlassification |