Classification of Brain Tumors Using Convolutional Neural Network over Various SVM Methods

Sajja, Venkata Rama Krishna; Kalluri, Hemantha Kumar

doi:10.18280/isi.250412

Cited by 15 publications

(5 citation statements)

References 14 publications

(16 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…At each position, the kernel weights are multiplied by the corresponding image values and added, plus a bias term. Each time this will cause the results to be summed up in a single pixel [29,30].…”

Section: Convolution Layermentioning

confidence: 99%

See 1 more Smart Citation

Finger Veins Verification by Exploiting the Deep Learning Technique

Al-Obaidy¹,

Mahmood²,

Alkababji³

2022

ISI

View full text Add to dashboard Cite

Finger vein verification has recently gained the attention of many researchers as one of the most interesting biometrics. This paper proposes a deep learning model called the Deep Fingers Vein Learning (DFVL). to improve recognition accuracy by training a Convolutional Neural Network. The final model consists of the following layers: three convolutional & ReLU, pooling, fully connected, soft-max and classification. All this after the hand image goes through the basic stages of determining the region of interest by operations within the preprocessing. The effect of changing parameter values was examined, analyzed, and discussed. The best accuracy results recorded by tuning the network parameter is 81.7%. This percentage was increased to 89% after using the five-finger fusion (Correct match of three or more fingers).

show abstract

Section: Convolution Layermentioning

confidence: 99%

“…In doing so, it retains positive values only. The overfitting problems are reduced, by the ability of the convolutional layer to output non-linear feature maps using ReLU [29,30].…”

Section: Relu Layermentioning

confidence: 99%

Finger Veins Verification by Exploiting the Deep Learning Technique

Al-Obaidy¹,

Mahmood²,

Alkababji³

2022

ISI

View full text Add to dashboard Cite

show abstract

“…[23] achieved by one of the three proposed CNNs, is based on ResNet50 architecture; although with obvious overfitting problems, as Saxena et al state. Another successful attempt of classifying images with and without brain tumors is displayed by Sajja and Kalluri [24], where the usage of a CNN on a BRATS dataset containing 577 images, gives an accuracy of 96.15%, tested on 182 images.…”

Section: Related Workmentioning

confidence: 99%

Brain Tumor Detection Based on Features Extracted and Classified Using a Low-Complexity Neural Network

Papageorgiou¹

2021

View full text Add to dashboard Cite

Brain tumor detection or brain tumor classification is one of the most challenging problems in modern medicine, where patients suffering from benign or malignant brain tumors are usually characterized by low life expectancy making the necessity of a punctual and accurate diagnosis mandatory. However, even today, this kind of diagnosis is based on manual classification of magnetic resonance imaging (MRI), culminating in inaccurate conclusions especially when they derive from inexperienced doctors. Hence, trusted, automatic classification schemes are essential for the reduction of humans’ death rate due to this major chronic disease. In this article, we propose an automatic classification tool, using a computationally economic convolutional neural network (CNN), for the purposes of a binary problem concerning MRI images depicting the existence or the absence of brain tumors. The proposed model is based on a dataset containing real MRI images of both classes with nearly perfect validation-testing accuracy and low computational complexity, resulting a very fast and reliable training-validation process. During our analysis we compare the diagnostic capacity of three alternative loss functions, validating the appropriateness of cross entropy function, while underlining the capability of an alternative loss function named Jensen-Shannon divergence since our model accomplished nearly excellent testing accuracy, as with cross-entropy. The multiple validation tests applied, enhancing the robustness of the produced results, render this low-complexity CNN structure as an ideal and trustworthy medical aid for the classification of small datasets.

show abstract

“…The activation function ReLU, which stands for the rectified linear unit, is a linear function that gives the output of the input right away if it is a positive value and it returns the zero value if the input is negative. It is a simple function but it has become the go-to activation feature for many kinds of neural network architectures, especially for CNN architecture [11].…”

Section: Design Of Prediction Model Cnn Basedmentioning

confidence: 99%

“…It is a great tool that shapes the way of diagnosis that classifies images into different categories. Medical image classification can be subdivided into two levels: the first is extracting successful features from the image, and the second is applying those extracted features to the image [1]. The features are further used to build models identifying the image dataset in the second stage [2].…”

Section: Introductionmentioning

confidence: 99%

Designing of Deep Learning based program for automatic detection of brain tumour using MRI data

Poddar

2021

IJTMKP

View full text Add to dashboard Cite

The essential organ of the human body is the brain, consisting of millions and millions of cells. But when these cells form abnormal groups due to their uncontrolled division, it is called a tumor. Brain tumors are further classified into two categories, benign (low-grade tumor) and malignant (high-grade tumor). Brain tumors are the most common life-threatening disease, which leads to immediate death in its highest grade or a very short lifespan. Thus, proper accurate detection and planning are crucial in improving the quality of life of people. In this work, MRI scanned images are used to determine whether the brain has a tumor or not. However, manually differentiating these images may lead to some errors and inaccurate results. Hence these trusted digital automatic classification schemes are nowadays an essential part of diagnosis and detection. Here, CNN architecture is implemented to build a simple model that is efficient in detecting of tumor and non-tumor images. The images are initially preprocessed and normalized, and then a Convolution model with dense layers is built to train and test the dataset. The training dataset accuracy and validation accuracy achieved are 89% and 77%, respectively, and the overall accuracy achieved by the model is 88% in a simple architecture. This advancement in deep learning algorithms has made tumor detection much more efficient, accurate and is a boon to the healthcare industry.

show abstract

Classification of Brain Tumors Using Convolutional Neural Network over Various SVM Methods

Cited by 15 publications

References 14 publications

Finger Veins Verification by Exploiting the Deep Learning Technique

Finger Veins Verification by Exploiting the Deep Learning Technique

Brain Tumor Detection Based on Features Extracted and Classified Using a Low-Complexity Neural Network

Designing of Deep Learning based program for automatic detection of brain tumour using MRI data

Contact Info

Product

Resources

About