CDCG-UNet: Chaotic Optimization Assisted Brain Tumor Segmentation Based on Dilated Channel Gate Attention U-Net Model

Neuroinformatics, Journal Year: 2025, Volume and Issue: 23(2)

Published: Jan. 22, 2025

Language: Английский

---

VSA-GCNN: Attention Guided Graph Neural Networks for Brain Tumor Segmentation and Classification

Big Data and Cognitive Computing, Journal Year: 2025, Volume and Issue: 9(2), P. 29 - 29

Published: Jan. 31, 2025

For the past few decades, brain tumors have had a substantial influence on human life, and pose severe health risks if not treated diagnosed in early stages. Brain tumor problems are highly diverse vary extensively terms of size, type, location. This diversity makes it challenging to progress an accurate reliable diagnostic tool. In order effectively segment classify region, still several developments required make diagnosis. Thus, purpose this research is accurately Magnetic Resonance Images (MRI) enhance Primarily, images collected from BraTS 2019, 2020, 2021 datasets, which pre-processed using min–max normalization eliminate noise. Then, given into segmentation stage, where Variational Spatial Attention with Graph Convolutional Neural Network (VSA-GCNN) applied handle variations shape, segmented outputs processed feature extraction, AlexNet model used reduce dimensionality. Finally, classification Bidirectional Gated Recurrent Unit (Bi-GRU) employed regions as gliomas meningiomas. From results, evident that proposed VSA-GCNN-BiGRU shows superior results 2019 dataset accuracy (99.98%), sensitivity (99.92%), specificity (99.91%) when compared existing models. By considering 2020 dataset, Dice similarity coefficient (0.4), (97.7%), (98.2%), (97.4%). While evaluating achieved 97.6%, 98.6%, 99.4%, 99.8%. overall observation, supports classification, provides clinical significance MRI

Language: Английский

---

A transfer learning based model for brain tumor detection using magnetic resonance imaging

AIP conference proceedings, Journal Year: 2025, Volume and Issue: 3224, P. 020059 - 020059

Published: Jan. 1, 2025

Language: Английский

---

Brain Tumor Segmentation and Classification using MRI: Modified Segnet Model and Hybrid Deep Learning Architecture with Improved Texture Features

Computational Biology and Chemistry, Journal Year: 2025, Volume and Issue: 117, P. 108381 - 108381

Published: Feb. 18, 2025

Language: Английский

---

An Evaluation of Pre-trained CNN Architectures for Brain Tumor Segmentation and Detection

Lecture notes in networks and systems, Journal Year: 2025, Volume and Issue: unknown, P. 507 - 524

Published: Jan. 1, 2025

Language: Английский

---

PixMed-Enhancer: An Efficient Approach for Medical Image Augmentation

Bioengineering, Journal Year: 2025, Volume and Issue: 12(3), P. 235 - 235

Published: Feb. 26, 2025

AI-powered medical imaging faces persistent challenges, such as limited datasets, class imbalances, and high computational costs. To overcome these barriers, we introduce PixMed-Enhancer, a novel conditional GAN that integrates the ghost module into its encoder—a pioneering approach achieves efficient feature extraction while significantly reducing complexity without compromising performance. Our method features hybrid loss function, uniquely combining binary cross-entropy (BCE) Structural Similarity Index Measure (SSIM), to ensure pixel-level precision enhancing perceptual realism. Additionally, use of input masks offers unparalleled control over generation tumor features, marking breakthrough in fine-grained dataset augmentation for segmentation diagnostic tasks. Rigorous testing on diverse datasets establishes PixMed-Enhancer state-of-the-art solution, excelling realism, structural fidelity, efficiency. robust foundation real-world clinical applications AI-driven imaging.

Language: Английский

---

MSegNet: A Multi-View Coupled Cross-Modal Attention Model for Enhanced MRI Brain Tumor Segmentation

International Journal of Computational Intelligence Systems, Journal Year: 2025, Volume and Issue: 18(1)

Published: March 20, 2025

Language: Английский

---

Brain tumor detection with bi-directional cascade Gaussian kernel feature-generative adversarial networks

Biomedical Signal Processing and Control, Journal Year: 2025, Volume and Issue: 107, P. 107838 - 107838

Published: March 26, 2025

Language: Английский

---

Comparison of deep learning methods in brain tumor diagnosis: High-performance classification with MRI data

Communications Faculty of Sciences University of Ankara Series A2-A3 Physical Sciences and Engineering, Journal Year: 2025, Volume and Issue: 67(1), P. 59 - 73

Published: Feb. 23, 2025

Brain tumors are serious health problems that must be diagnosed accurately and in a timely manner order to provide effective treatment. Magnetic resonance imaging (MRI) is widely used the detection of brain tumors. The accuracy MRI results depends on expertise physician usually requires confirmation with biopsy. In recent years, revolutionary developments image processing deep learning technologies have provided significant improvements diagnosis classification using MRI. this study, it aimed classify effectively for four different classes (glioma, meningioma, pituitary, no tumor) previously created data. Four transfer learning-based methods classification; ResNet-18, EfficientNet-B0, DenseNet-121, ConvNeXt-Tiny, compared Fastai library. Accurate critical importance treatment patients, aim study achieve high speed. Our proposed library-based EfficientNet-B0 model has achieved both fast highly successful 99% rate 73 minutes training performance. addition, DenseNet-121 rates, ResNet-18 ConvNeXt-Tiny models 98% rates. insights into possible uses frameworks field medical imaging. these studies literature.

Language: Английский

---

A Comprehensive Framework for Brain MRI Analysis: Classification, Segmentation, and Survival Prediction

Smart innovation, systems and technologies, Journal Year: 2025, Volume and Issue: unknown, P. 593 - 607

Published: Jan. 1, 2025

Language: Английский

---