Early Prediction of Brain Tumor Classification Using Convolution Neural Networks

Arunnehru, J.; Kumar, Ajay; Verma, Jagvir

doi:10.1007/978-981-15-3666-3_2

Cited by 8 publications

(7 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The critical feature was selected using principal component analysis (PCA) and Gray-level co-occurrence matrix (GLCM) to detect the presence of brain tumours and their classification into malignant and benign categories using support vector machine (SVM) [22]. Another feature extraction method utilising CNN is to cluster the mri images using a fuzzy c-means algorithm first [27]. Moreover, the canny edge algorithm is used to detect the tumour region, and CNN was proposed utilizing this two-stage information, with an accuracy of 91.40 percent.…”

Section: Related Workmentioning

confidence: 99%

Classification of brain tumor of magnetic resonance medical images using convolutional neural network approach

Verma¹,

Arora²

2022

ijhs

View full text Add to dashboard Cite

The impact tumours in the brain in medical field cannot be ignored and may lead to a short life in their highest grade. Thus, conduction of proper diagnosis that too in its early stage to improve the quality of life of patients is a necessity. Normally, several image processing techniques including Computed Tomography (CT) and Magnetic Resonance Imaging (MRI) is a type of imaging that uses a (MRI) are be ingutilized to localize and calculate the size and tumor in a brain. But has limited performance for accurate quantitative measurements that too in a small number of sample images. In this project, a simple yet robust classification using Convolutional Neural Networks (CNN) for for brain cancer is proposed. The investigational outcomes with low complication is anticipated and potentially competes the relevant state of arts methods.

show abstract

Section: Related Workmentioning

confidence: 99%

Classification of brain tumor of magnetic resonance medical images using convolutional neural network approach

Verma¹,

Arora²

2022

ijhs

View full text Add to dashboard Cite

show abstract

“…54 A typical CNN architecture for image classification has several hidden layers between the input and output layers. The hidden layers are sequences of (convolution—ReLU —pooling) followed by a fully connected layer, and a softmax classification layer, 55 as shown in Figure 2; a representation of a CNN used to classify RGB (red, green, blue) images of size 28 × 28 pixels.…”

Section: Convolutional Neural Networkmentioning

confidence: 99%

“…A convenient manner to configure the padding is by adding just enough zero padding to keep the size of the output equal the size of the input. For instance, in Matlab, by setting the padding parameter to “same,” 54,55 the size of the padding is calculated by the software at training or prediction time so that the output has the same size as the input when the stride equals 1. If stride is larger than 1, the output size is ⌈ inputSize stride ⌉ , where inputSize is the height or width of the input, stride is the stride in the corresponding dimension, and ⌈ · ⌉ is the ceiling function.…”

Section: Case Studymentioning

confidence: 99%

“…Different epochs and batch sizes were evaluated during the training. Epochs in the range between 20 and 50 are suggested for image processing with CNN, 55,68 whereas batch sizes in the range between 2 and 32 have been reported to produce the best performance for deep neural networks. 69 Accordingly, in this paper, epochs of 30, 40, and 50 along with batch sizes of 8, 16, 32, and 64 were considered, which results in 12 different training configurations.…”

Section: Hyperparametersmentioning

confidence: 99%

“…Each convolutional layer was followed by batch normalization and ReLU layers, considering that such a structure generated successful results in a previous image classification study with CNN. 55 In addition to these initial values, different multiplier (mul) values of 1, 4, and 8 were applied to the number of filters, i.e., combinations of number of filters (8,16,32,32), (32,64,128,128), and (64,128,256,256) were investigated for selection of the best number of filters.…”

Section: Hyperparametersmentioning

confidence: 99%

See 2 more Smart Citations

All-terminal network reliability estimation using convolutional neural networks

Davila-Frias

Yadav

2020

Proceedings of the Institution of Mechanical Engineers, Part O:

View full text Add to dashboard Cite

Estimating the all-terminal network reliability by using artificial neural networks (ANNs) has emerged as a promissory alternative to classical exact NP-hard algorithms. Approaches based on traditional ANNs have usually considered the network reliability upper bound as part of the inputs, which implies additional time-consuming calculations during both training and testing phases. This paper proposes the use of Convolutional Neural Networks (CNNs), without the reliability upper-bound as an input, to address the all-terminal network reliability estimation problem. The present study introduces a multidimensional matrix format to embed the topological and link reliability information of networks. The unique contribution of this article is the method to capture the topology of a network in terms of its adjacency matrix, link reliability, and topological attributes providing a novel use of CNN beyond image classification. Since CNNs have been successful for image classification, appropriate modifications are needed and introduced to use them in the estimation of network reliability. A regression output layer is proposed, preceded by a sigmoid layer to achieve predictions within the range of reliability characteristic, a feature that some previous ANN-based works lack. Several training parameters together with a filter multiplier (CNN architecture parameter) were investigated. The actual values and the ones predicted with the best trained CNN were compared in the light of RMSE (0.04406) and p-value (0.3) showing non-significant difference. This study provides evidence supporting the hypothesis that the network reliability can be estimated by CNNs from its topology and link reliability information, embedded as an image-like multidimensional matrix. Another important result of the proposed approach is the significant reduction in computational time. An average of 1.18 ms/network was achieved by the CNN, whereas backtracking exact algorithm took around 500 s/network.

show abstract

Dense SIFT-Based Facial Expression Recognition Using Machine Learning Techniques

Vaijayanthi

Arunnehru

2022

Proceedings of the 6th International Conference on Advance Computing and Intelligent Engineering

View full text Add to dashboard Cite

Early Prediction of Brain Tumor Classification Using Convolution Neural Networks

Cited by 8 publications

References 16 publications

Classification of brain tumor of magnetic resonance medical images using convolutional neural network approach

Classification of brain tumor of magnetic resonance medical images using convolutional neural network approach

All-terminal network reliability estimation using convolutional neural networks

Dense SIFT-Based Facial Expression Recognition Using Machine Learning Techniques

Contact Info

Product

Resources

About