Segmentation of MR Images for Brain Tumor Detection Using Autoencoder Neural Network DOI
Farnaz Hoseini,

Shohreh Shamlou,

Milad Ahmadi-Gharehtoragh

et al.

Research Square (Research Square), Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 26, 2024

Abstract Medical images often require segmenting into different regions in the first analysis stage. Relevant features are selected to differentiate various from each other, and segmented meaningful (anatomically significant) based on these features. The purpose of this study is present a model for identifying local tumor formation MR human brain. proposed system operates an unsupervised manner minimize intervention expert users achieve acceptable speed classification process. method includes several steps preprocessing brain image classify that Perform normalization task. These lead more accurate results high-resolution ultimately improve accuracy sensitivity separation tissue. output stage applied self-encoding neural network zoning. By nature networks, leads reduce dimensionality pixels surrounding healthy environment, which significantly helps remove incorrectly extracted as tumors. Finally, by extracting previous stage's through Otsu thresholding, area type also extracted. was trained tested using BRATS2020 database evaluated performance metrics. Dice Similarity Coefficient (DSC) show 97% entire improved detection compared other methods, well reduction cost diagnostic

Language: Английский

Integrating Deep Learning and Imaging Techniques for High-Precision Brain Tumor Analysis DOI
Dilip Kumar Gokapay, Sachi Nandan Mohanty

Communications in computer and information science, Journal Year: 2025, Volume and Issue: unknown, P. 53 - 67

Published: Jan. 1, 2025

Language: Английский

Citations

0
Brain tumor segmentation using multi-scale attention U-Net with EfficientNetB4 encoder for enhanced MRI analysis DOI Creative Commons

R. Preetha,

Jasmine Pemeena Priyadarsini M,

J. S. Nisha

et al.

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: March 22, 2025

Abstract Accurate brain tumor segmentation is critical for clinical diagnosis and treatment planning. This study proposes an advanced framework that combines Multiscale Attention U-Net with the EfficientNetB4 encoder to enhance performance. Unlike conventional U-Net-based architectures, proposed model leverages EfficientNetB4’s compound scaling optimize feature extraction at multiple resolutions while maintaining low computational overhead. Additionally, Multi-Scale Mechanism (utilizing $$1\times 1, 3\times 3$$ , $$5\times 5$$ kernels) enhances representation by capturing boundaries across different scales, addressing limitations of existing CNN-based methods. Our approach effectively suppresses irrelevant regions localization through attention-enhanced skip connections residual attention blocks. Extensive experiments were conducted on publicly available Figshare dataset, comparing EfficientNet variants determine optimal architecture. demonstrated superior performance, achieving Accuracy 99.79%, MCR 0.21%, Dice Coefficient 0.9339, Intersection over Union (IoU) 0.8795, outperforming other in accuracy efficiency. The training process was analyzed using key metrics, including Coefficient, dice loss, precision, recall, specificity, IoU, showing stable convergence generalization. method evaluated against state-of-the-art approaches, surpassing them all accuracy, mean IoU. demonstrates effectiveness robust efficient tumors, positioning it as a valuable tool research applications.

Language: Английский

Citations

0
The impact of backbone selection in YOLOv8 models on brain tumor localization DOI Creative Commons
Ramin Ranjbarzadeh, Martin Crane, Malika Bendechache

et al.

Iran Journal of Computer Science, Journal Year: 2025, Volume and Issue: unknown

Published: March 28, 2025

Language: Английский

Citations

0
Brain Tumor Segmentation and Detection using Deep Learning Method based on ResNet152 DOI Open Access
Sana Ali,

Jitendra Agrawal

Procedia Computer Science, Journal Year: 2025, Volume and Issue: 258, P. 160 - 169

Published: Jan. 1, 2025

Language: Английский

Citations

0
The Impact of Backbone Selection in Yolov8 Models on Brain Tumor Localization DOI
Ramin Ranjbarzadeh, Martin Crane, Malika Bendechache

et al.

Published: Jan. 1, 2024

Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI

Language: Английский

Citations

3
Innovative fusion of VGG16, MobileNet, EfficientNet, AlexNet, and ResNet50 for MRI-based brain tumor identification DOI

Marjan Kia,

Soroush Sadeghi,

Homayoun Safarpour

et al.

Iran Journal of Computer Science, Journal Year: 2024, Volume and Issue: unknown

Published: Dec. 9, 2024

Language: Английский

Citations

3
Improved Brain Tumor Segmentation in MR Images with a Modified U-Net DOI Creative Commons
Hiam Alquran,

Mohammed Alslatie,

Ali Rababah

et al.

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(15), P. 6504 - 6504

Published: July 25, 2024

Detecting brain tumors is crucial in medical diagnostics due to the serious health risks these abnormalities present patients. Deep learning approaches can significantly improve localization various issues, particularly tumors. This paper emphasizes use of deep models segment using a large dataset. The study involves comparing modifications U-Net structures, including kernel size, number channels, dropout ratio, and changing activation function from ReLU Leaky ReLU. Optimizing parameters has notably enhanced tumor segmentation MR images, achieving Global Accuracy 99.4% dice similarity coefficient 90.2%. model was trained, validated, tested on many magnetic resonance with training time not exceeding 19 min powerful GPU. approach be extended care hospitals assist radiologists identifying locations suspicious regions, thereby improving diagnosis treatment effectiveness. software could also integrated into equipment protocols.

Language: Английский

Citations

2
Segmentation of MR images for brain tumor detection using autoencoder neural network DOI Creative Commons
Farnaz Hoseini,

Shohreh Shamlou,

Milad Ahmadi-Gharehtoragh

et al.

Discover Artificial Intelligence, Journal Year: 2024, Volume and Issue: 4(1)

Published: Oct. 26, 2024

Language: Английский

Citations

2
Comparative Study on Architecture of Deep Neural Networks for Segmentation of Brain Tumor using Magnetic Resonance Images DOI Creative Commons

R. Preetha,

M. Jasmine Pemeena Priyadarsini,

J. S. Nisha

et al.

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 138549 - 138567

Published: Jan. 1, 2023

The state-of-the-art works for the segmentation of brain tumor using images acquired by Magnetic Resonance Imaging (MRI) with their performances are analyzed in this comparative study. First, architectures convolutional neural networks (CNN) and variants U-shaped Network (U-Net), a kind Deep Neural (DNN) compared differences highlighted. publicly available datasets MRI specifically Brain Tumor Segmentation (BraTS) also discussed. Next, various methods literature parameters such as Dice score Hausdroff distance (95). This study concludes that U-Net based BraTS-2019 dataset outperform well other CNN architectures.

Language: Английский

Citations

5
Enhancing brain tumor detection in MRI images using YOLO-NeuroBoost model DOI Creative Commons

A. Lumin Chen,

Da Lin, Qiqi Gao

et al.

Frontiers in Neurology, Journal Year: 2024, Volume and Issue: 15

Published: Aug. 22, 2024

Brain tumors are diseases characterized by abnormal cell growth within or around brain tissues, including various types such as benign and malignant tumors. However, there is currently a lack of early detection precise localization in MRI images, posing challenges to diagnosis treatment. In this context, achieving accurate target images becomes particularly important it can improve the timeliness effectiveness To address challenge, we propose novel approach–the YOLO-NeuroBoost model. This model combines improved YOLOv8 algorithm with several innovative techniques, dynamic convolution KernelWarehouse, attention mechanism CBAM (Convolutional Block Attention Module), Inner-GIoU loss function. Our experimental results demonstrate that our method achieves mAP scores 99.48 97.71 on Br35H dataset open-source Roboflow dataset, respectively, indicating high accuracy efficiency detecting images. research holds significant importance for improving treatment provides new possibilities development medical image analysis field.

Language: Английский

Citations

1