RETRACTED ARTICLE: Identification of lesion using an efficient hybrid algorithm for MRI brain image segmentation

Sasikala, E.; Kanmani, P; Gopalakrishnan, Ragavendran; Radha, R.

doi:10.1007/s12652-021-03060-9

Cited by 5 publications

(6 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…https://www.indjst.org/ 4 a comparison of the accuracy achieved by the LeakyReLU and ReLU with previously evaluated results. The testing accuracy of the proposed models are noticeably higher than those achieved by the models listed in the references (17)(18)(19)(20)(21) . (19) Fuzzy logic Two 450 -95.67% -Vankdothu et al (20) RCNN Three 264 PYTHON 95.17% -Gu et al (21) CNN The improved performance is achieved due to the fine-tuning of the model's hyperparameter values, optimizer type, batch and kernel sizes, activation functions, pool size, the number of neurons used in the convolution layers, and the number of training epochs.…”

Section: Resultsmentioning

confidence: 64%

MRI Brain Tumor Prediction using Azure Streamlit Framework and Analysis of CNN Activation Functions

Saxena,

Singh,

Singh

2023

IJST

View full text Add to dashboard Cite

Objective:The present research work is focused on brain tumor classification, prediction and to increase the performance to locate the tumor region. Methods: A two-dimensional Convolutional Neural Network (CNN) model is proposed to classify the Magnetic Resonance Images (MRI) into tumor and nontumor categories. The method is applied on a collected dataset consisting of 2056 MRI images. The model is implemented in Python with hyperparameter tuning and activation functions.Findings: In this paper, ReLU and LeakyReLU activation functions are applied with several optimizers. The analysis of the implemented results has been used to gauge performance accuracy. The computed results achieve 99.51% accuracy for predicting the brain tumor using LeakyReLU with Adam optimizer. Novelty: The proposed model provides quick, and accurate approach to classify patients by setting hyperparameter tuning parameters which helps to the doctor to detect patients suffering with tumor and the entire process reduces the computation time.

show abstract

Section: Resultsmentioning

confidence: 64%

MRI Brain Tumor Prediction using Azure Streamlit Framework and Analysis of CNN Activation Functions

Saxena,

Singh,

Singh

2023

IJST

View full text Add to dashboard Cite

show abstract

“…And the Rician noise is added using Eq. (1). Where is the image after adding Rician noise, is the image before adding the noise, and e1 and e2 are random numbers from a Gaussian distribution [20].…”

Section: Adding Noise To Mrimentioning

confidence: 99%

“…Image segmentation is a crucial challenge in computer vision and image processing alike. For images, segmentation generally means dividing them into mutually exclusive areas to make them easy for analysis and examination [1][2][3]. The trend of medical image segmentation is growing rapidly, and the area of stockholders has become very large.…”

Section: Introductionmentioning

confidence: 99%

Novel Framework of Segmentation 3D MRI of Brain Tumors

El-Henawy¹,

Elbaz²,

Ali³

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Medical image segmentation is a crucial process for computer-aided diagnosis and surgery. Medical image segmentation refers to portioning the images into small, disjointed parts for simplifying the processes of analysis and examination. Rician and speckle noise are different types of noise in magnetic resonance imaging (MRI) that affect the accuracy of the segmentation process negatively. Therefore, image enhancement has a significant role in MRI segmentation. This paper proposes a novel framework that uses 3D MRI images from Kaggle and applies different diverse models to remove Rician and speckle noise using the best possible noise-free image. The proposed techniques consider the values of Peak Signal to Noise Ratio (PSNR) and the level of noise as inputs to the attention-U-Net model for segmentation of the tumor. The framework has been divided into three stages: removing speckle and Rician noise, the segmentation stage, and the feature extraction stage. The framework presents solutions for each problem at a different stage of the segmentation. In the first stage, the framework uses Vibrational Mode Decomposition (VMD) along with Block-matching and 3D filtering (Bm3D) algorithms to remove the Rician. Afterwards, the most significant Rician noise-free images are passed to the three different methods: Deep Residual Network (DeRNet), Dilated Convolution Auto-encoder Denoising Network (Di-Conv-AE-Net), and Denoising Generative Adversarial Network (DGAN-Net) for removing the speckle noise. VMD and Bm3D have achieved PSNR values for levels of noise (0, 0.25, 0.5, 0.75) for reducing the Rician

show abstract

“…These techniques are evaluated and the performance of the different methods are qualitatively analyzed by classifying the tumors from the MR brain images based on the area of segmentation, number of pixels and processing time. Sasikala et al [16] proposed fractional order BAT algorithm with fuzzy c means to detect brain tumor. In the same work, delaunay triangulation and fractional order nature methods are applied to segment the lesion from brain.…”

Section: Related Workmentioning

confidence: 99%

Interpolation Method for Identification of Brain Tumor from Magnetic Resonance Images

Singh¹,

Saxena²

2023

IJEM

View full text Add to dashboard Cite

During the past years, it is observed from the literature that, identification of the brain tumor identification in human being is gaining popularity. Diagnosing any disease without manual interaction with great accuracy makes computer science research more demanding, therefore, the present work is related to identify the tumor clots in the affected patients. For this purpose, a well-known Safdarganj Hospital, New Delhi, India is consulted and 2165 Magnetic Resonance Images (MRI) of a single patient are collected through scanning, and interpolation technique of numerical method used to identify the accurate position of the brain tumor. A system model is developed and implemented by the use of Python programming language and MATLAB for the identification of affected areas in the form of a contour of a patient. The desired accuracy and specificity are evaluated using the computed results and also presented in the form of graphs.

show abstract

RETRACTED ARTICLE: Identification of lesion using an efficient hybrid algorithm for MRI brain image segmentation

Cited by 5 publications

References 29 publications

MRI Brain Tumor Prediction using Azure Streamlit Framework and Analysis of CNN Activation Functions

MRI Brain Tumor Prediction using Azure Streamlit Framework and Analysis of CNN Activation Functions

Novel Framework of Segmentation 3D MRI of Brain Tumors

Interpolation Method for Identification of Brain Tumor from Magnetic Resonance Images

Contact Info

Product

Resources

About