Brain Tumor Identification Based on VGG-16 Architecture and CLAHE Method

Abstract

Magnetic Resonance Imaging (MRI) in diagnosing brain cancers is widespread. Because of the variety of angles and clarity of anatomy, it is commonly employed. If a brain tumor is malignant or secondary, it is a high risk, leading to death. These tumors have an increased predisposition for spreading from one place to another. In detecting brain abnormality form such as a tumor, from a magnetic resonance scan, expertise and human involvement are required. Previous, the image segmentation of brain tumors is widely developed in this field. Suppose we could somehow use an automatic brain tumor detection technology to identify the presence of a tumor in the brain without requiring human intervention. In that case, it will give us a leg up in the treatment process. This research proposed two stages to identify the brain tumor in MRI; the first stage was the image enhancement process using Clip Limit Adaptive Histogram Equalization (CLAHE) to segment the brain MRI. The second one was classifying the brain tumor on MRI using Visual Geometry Group-16 Layer (VGG-16). The CLAHE was used in some instances, there were CLAHE applied in FLAIR image on green color, and CLAHE applied in Red, Green, Blue (RGB) color space. The experimental result showed the highest performance with accuracy, precision, recall, respectively 90.37%, 90.22%, 87.61%. The CLAHE method in RGB Channel and the VGG-16 model have reliably on predicted oligodendroglioma classes in RGB enhancement with precision 91.08% and recall 95.97%.

Multimodal hybrid convolutional neural network based brain tumor grade classification

“…The proposed model, which contains various layers, aims to classify MRI brain tumor The proposed model achieved higher accuracy of 97.02% and outperformed the various previous works Xinyu Lei [ 12 ] Hybrid dilated CNN Proposed a dilated CNN model, which is built by replacing the convolution kernels of traditional CNN by dilated convolution kernels, and then, the dilated CNN model is tested on the Mnist handwritten digital recognition data set The dilated CNN model reduces the training time by 12:99% and improves the training accuracy by 2:86% averagely, compared with the dilated CNN model Himanshu Padole [ 13 ] Graph CNN, graph wavelet transforms A novel two-stage graph coarsening method rooted in graph signal processing and its application in the GCNN architecture The proposed model achieved higher accuracy of 99.30% and outperformed the various previous works Sichao Fu [ 14 ] Graph-based semi-supervised learning, manifold assumption based SSL algorithms The spectral graph Hessian convolutions is a combination of the Hessian matrix and the spectral graph convolutions HesGCN can learn more efficient data features by fusing the original feature information with its structure information based on Hessian Isselmou Abd El Kader [ 15 ] differential deep-CNN differential deep convolutional neural network model to classify different types of brain tumor, including abnormal and normal MR images The experimental results showed that the proposed model achieved an accuracy of 99.25% Chirodip Lodh Choudhury [ 16 ] Extracting features through a CNN Deep neural network and incorporates a CNN based model to classify the MRI as “detected” or “not detected” The model captures a mean accuracy score of 96.08% with f-score of 97.3 Anushka Singh [ 17 ] Deep CNN The proposed deep learning method which is used to classify Brain tumor types. Our method is based on VGG16 architecture with CNN as the classifier An accuracy of above 93% along with high precision, recall and F-score was achieved Saran Raj Sowrirajan [ 18 ] VGG16 and Neural Autoregressive Distribution Estimation ...…”

“…The results indicated that the developed hybrid VGG16-NADE model outperforms other models in terms of accuracy, specificity, sensitivity, and the F1 score. The suggested hybrid VGG16-NADE model achieved a prediction accuracy of 96.01%, precision of 95.72%, recall of 95.64%, F-measure of 95.68%, a receiver operating characteristic (ROC) of 0.91, an error rate of 0.075, and a Matthews correlation coefficient (MCC) of 0.3564 [ 18 ].…”

Optimization of the Preprocessing Method for Edge Detection on Overlapping Cells at PAP Smear Images

“…Edge detection that gives good results requires procedures that focus on image quality settings [30]. The procedure performed before edge detection is to overcome the uneven [31], [32] contrast in the Pap smear image during acquisition.…”

Image Prediction of Exact Science and Social Science Learning Content with Convolutional Neural Network

“…Image recognition and processing are very well done with Convolutional Neural Networks [5]. Training and Testing are carried out after all datasets have been collected so that the process of validating drawings can be carried out [6].…”