scholarly journals Convolutional Neural Network with Hyperparameter Tuning for Brain Tumor Classification

2021 ◽  
Author(s):  
Agus Eko Minarno ◽  
Mochammad Hazmi Cokro Mandiri ◽  
Yuda Munarko ◽  
Hariyady Hariyady
Keyword(s):  
Neural Network ◽  
Brain Tumor ◽  
Convolutional Neural Network ◽  
Pituitary Tumors ◽  
Model Testing ◽  
Tumor Classification ◽  
Appropriate Treatment ◽  
Tumor Types ◽  
The Brain ◽  
Best Parameters

Brain tumor has been acknowledged as the most dangerous disease through all its circles. Early identification of tumor disease is considered pivotal to identify the spread of brain tumors in administering the appropriate treatment. This study proposes a Convolutional Neural Network method to detect brain tumor on MRI images. The 3264 datasets were undertaken in this study with detailed images of Glioma tumor (926 images), Meningioma tumors (937 images), pituitary tumors (901 images), and other with no-tumors (500 images). The application of CNN method combined with Hyperparameter Tuning is proposed to achieve optimal results in classifying the brain tumor types. Hyperparameter Tuning acts as a navigator to achieve the best parameters in the proposed CNN model. In this study, the model testing was conducted with three different scenarios. The result of brain tumor classification depicts an accuracy of 96% in the third model testing scenario.

Convolutional Neural Network Based Brain Tumor Classification Using Robust Background Saliency Detection

2021 ◽  
Vol 11 (10) ◽  
pp. 2610-2617
Author(s):  
K. Uthra Devi ◽  
R. Gomathi
Keyword(s):  
Neural Network ◽  
Brain Tumor ◽  
Convolutional Neural Network ◽  
Saliency Detection ◽  
Automated Analysis ◽  
Regions Of Interest ◽  
Tumor Classification ◽  
Tumor Section ◽  
Canny Edge ◽  
The Brain

To perceive the tumors found in brain and their treatment, experts manually note and identify different Regions of Interest (ROI). To overcome the faults and divergences during this state, automated analysis is performed. A unique technique is used to classify the tumor section of the brain from an MRI is proposed using saliency-focused image depiction and optimization in classification based on CNN. Primarily, the MRI images are pre-processed using the Canny Edge Finding algorithm and then those images are represented as saliency driven based on Robust Background Saliency Detection (RBD). Followed by the abstraction of features then classifying the image is performed using CNN along with ADAM optimization. The implementation is accomplished, and the results are analyzed, showing that it outperforms previous techniques.

Brain Tumor Classification Using Convolutional Neural Network

2018 ◽  
pp. 183-189 ◽  
Author(s):  
Nyoman Abiwinanda ◽  
Muhammad Hanif ◽  
S. Tafwida Hesaputra ◽  
Astri Handayani ◽  
Tati Rajab Mengko
Keyword(s):  
Neural Network ◽  
Brain Tumor ◽  
Convolutional Neural Network ◽  
Tumor Classification

scholarly journals Classification of Brain Tumor using Convolutional Neural Networks

2020 ◽  
Vol 9 (3) ◽  
pp. 2841-2845
Keyword(s):  
Neural Network ◽  
Brain Tumor ◽  
Convolutional Neural Network ◽  
Medical Science ◽  
Activation Functions ◽  
Case Scenario ◽  
Aggressive Disease ◽  
Fully Connected ◽  
The Brain

In medical science, brain tumor is the most common and aggressive disease and is known to be risk factors that have been confirmed by research. A brain tumor is the anomalous development of cell inside the brain. One conventional strategy to separate brain tumors is by reviewing the MRI pictures of the patient's mind. In this paper, we have designed a Convolutional Neural Network (CNN) to perceive whether the image contains tumor or not. We have designed 5 different CNN and examined each design on the basis of convolution layers, max-pooling, and flattening layers and activation functions. In each design we have made some changes on layers i.e. using different pooling layers in design 2 and 4, using different activation functions in design 2 and 3, and adding more Fully Connected layers in design 5. We examine their results and compare it with other designs. After comparing their results we find a best design out of 5 based on their accuracy. Utilizing our Convolutional neural network, we could accomplish a training accuracy and validation accuracy of design 3 at 100 epochs is 99.99% and 92.34%, best case scenario.

scholarly journals Emergence of Convolutional Neural Network in Future Medicine: Why and How. A Review on Brain Tumor Segmentation

2018 ◽  
Vol 24 (1) ◽  
pp. 43-53
Author(s):  
Behrouz Alizadeh Savareh ◽  
Hassan Emami ◽  
Mohamadreza Hajiabadi ◽  
Mahyar Ghafoori ◽  
Seyed Majid Azimi
Keyword(s):  
Neural Network ◽  
Image Processing ◽  
Brain Tumor ◽  
Convolutional Neural Network ◽  
Magnetic Resonance Images ◽  
Tumor Segmentation ◽  
Brain Tumor Segmentation ◽  
Manual Analysis ◽  
The Brain ◽  
Evaluation Parameters

Abstract Manual analysis of brain tumors magnetic resonance images is usually accompanied by some problem. Several techniques have been proposed for the brain tumor segmentation. This study will be focused on searching popular databases for related studies, theoretical and practical aspects of Convolutional Neural Network surveyed in brain tumor segmentation. Based on our findings, details about related studies including the datasets used, evaluation parameters, preferred architectures and complementary steps analyzed. Deep learning as a revolutionary idea in image processing, achieved brilliant results in brain tumor segmentation too. This can be continuing until the next revolutionary idea emerging.

scholarly journals Effective Brain Tumor Classification on MRI Using Deep Belief-convolutional Neural Network with Pixel Change Detection based on Pixel Mapping Technique

Webology ◽  
2021 ◽  
Vol 18 (Special Issue 05) ◽  
pp. 1096-1117
Author(s):  
K.V. Shiny ◽  
N. Sugitha
Keyword(s):  
Neural Network ◽  
Brain Tumor ◽  
Change Detection ◽  
Convolutional Neural Network ◽  
Malignant Tumor ◽  
Benign Tumor ◽  
Human Life ◽  
Tumor Classification ◽  
Mapping Technique ◽  
Mr Images

Brain tumor is a kind of cancer, in which tissues in the brain grows rapidly and unevenly in the brains and causes huge threats on human life. Brain tumor is recognized as one of the common dreadful cancers among adults and it also affects the children too. This kind of cancer is categorized into two types, such as benign tumor and malignant tumor. However, benign tumor is curable, whereas recovering of patients whoever affected by malignant tumor has less chance to survive. Nowadays, MR images are usually employed to detect the kinds of brain tumor. Early classification and identification of tumor is significant to treat the tumor and saves the human life from early death. However, the classification of brain tumor and percentage in change detection using pre-operative and post-operative MR images is a very challenging task. In order to overcome such issues, this research proposes a new effective technique for brain tumor classification and determination of pixel change detection using proposed Deep Belief Network (DBN) + Deep Convolutional Neural Network (DCNN). The process involves four phases, such as pre-processing, segmentation, feature extraction, and classification. The combination of DBN + CNN is employed for decision making based on error function. The DBN + CNN are trained utilizing the developed BirCat algorithm. Moreover, the proposed approach achieved a maximum accuracy of 0.957, sensitivity of 0.967, and specificity of 0.918.

scholarly journals A Two-Dimensional Convolutional Neural Network for Brain Tumor Detection From MRI

2020 ◽  
Vol 26 (4) ◽  
pp. 398-413
Author(s):  
Ayoub Najaf-Zadeh ◽  
Keyword(s):  
Neural Network ◽  
Brain Tumor ◽  
Brain Tumors ◽  
Convolutional Neural Network ◽  
Pituitary Tumors ◽  
Activation Function ◽  
Two Dimensional ◽  
Risk Of Death ◽  
Magnetic Resonance Imaging Mri ◽  
Two Stages

Aims: Cancerous brain tumors are among the most dangerous diseases that lower the quality of life of people for many years. Their detection in the early stages paves the way for the proper treatment. The present study aimed to present a two-dimensional Convolutional Neural Network (CNN) for detecting brain tumors under Magnetic Resonance Imaging (MRI) using the deep learning method. Methods & Materials: The proposed method has two stages of feature extraction and classification. A 12-layer CNN was used to extract the features of the MRI images and then the softmax activation function was used to classify these features. The proposed method was applied to a standard database consisting of three brain tumor types of meningioma, glioma, and pituitary. Findings: The proposed method had better performance compared to previously presented methods. Its accuracy was reported as 98.68%. Conclusion: Meningioma, glioma, and pituitary tumors are the most common types of brain tumors. Early detection of these tumors can decrease the risk of death. Because of its fully connected structure, the use of proposed deep CNN can help physicians to correctly detect brain tumors with MRI images.

Sign in / Sign up

Export Citation Format

Share Document