Brain Tumor Classification Using a Hybrid Ensemble of Xception and Parallel Deep CNN Models

Informatics in Medicine Unlocked, Journal Year: 2025, Volume and Issue: unknown, P. 101629 - 101629

Published: Feb. 1, 2025

Language: Английский

---

Optimizing Brain Tumor Detection in MRI Scans Through InceptionResNetV2 and Deep Stacked Autoencoders with SwiGLU Activation and Sparsity Regularization

MethodsX, Journal Year: 2025, Volume and Issue: 14, P. 103255 - 103255

Published: March 7, 2025

This study presents an automated framework for brain tumor classification aimed at accurately distinguishing types in MRI images. The proposed model integrates InceptionResNetV2 feature extraction with Deep Stacked Autoencoders (DSAEs) classification, enhanced by sparsity regularization and the SwiGLU activation function. InceptionResNetV2, pre-trained on ImageNet, was fine-tuned to extract multi-scale features, while DSAE structure compressed these features highlight critical attributes essential classification. approach achieved high performance, reaching overall accuracy of 99.53 %, precision 98.27 recall 99.21 specificity 98.73 F1-score 98.74 %. These results demonstrate model's efficacy categorizing glioma, meningioma, pituitary tumors, non-tumor cases, minimal misclassifications. Despite its success, limitations include dependency weights significant computational resources. Future studies should address enhancing interpretability, exploring domain-specific transfer learning, validating diverse datasets strengthen utility real-world settings. Overall, integrated DSAEs, regularization, offers a promising solution reliable efficient diagnosis clinical environments.•Leveraging capture from data.•Utilizing emphasize precise classification.•Incorporating function complex, non-linear patterns within data.

Language: Английский

---

A synaptic deep tumor sense predictor system for brain tumor detection and classification

Alexandria Engineering Journal, Journal Year: 2025, Volume and Issue: 123, P. 29 - 45

Published: March 23, 2025

Language: Английский

---

EC-HDLNet: Extended coati-based hybrid deep dilated convolutional learning network for brain tumor classification

Biomedical Signal Processing and Control, Journal Year: 2025, Volume and Issue: 107, P. 107865 - 107865

Published: March 26, 2025

Language: Английский

---

Deep Learning Innovations for Predictive Healthcare Systems

Lecture notes in networks and systems, Journal Year: 2025, Volume and Issue: unknown, P. 199 - 206

Published: Jan. 1, 2025

Language: Английский

---

ECFO-DCNN: Egocentric Critter Fish Optimization Enabled Deep Convolutional Neural Network for Brain Tumor Classification

Deleted Journal, Journal Year: 2025, Volume and Issue: unknown

Published: April 1, 2025

Language: Английский

---

A novel similarity navigated graph neural networks and crayfish optimization algorithm for accurate brain tumor detection

Research on Biomedical Engineering, Journal Year: 2025, Volume and Issue: 41(2)

Published: April 5, 2025

Language: Английский

---

Improving Brain Disease Classification Accuracy Using Ensemble Learning

Lecture notes in computer science, Journal Year: 2025, Volume and Issue: unknown, P. 197 - 208

Published: Jan. 1, 2025

Language: Английский

---

Advanced Deep Learning and Machine Learning Techniques for MRI Brain Tumor Analysis: A Review

Sensors, Journal Year: 2025, Volume and Issue: 25(9), P. 2746 - 2746

Published: April 26, 2025

A brain tumor is the result of abnormal growth cells in central nervous system (CNS), widely considered as a complex and diverse clinical entity that difficult to diagnose cure. In this study, we focus on current advances medical imaging, particularly magnetic resonance imaging (MRI), how machine learning (ML) deep (DL) algorithms might be combined with assessments improve diagnosis. Due its superior contrast resolution safety compared other methods, MRI highlighted preferred modality for tumors. The challenges related analysis different processes including detection, segmentation, classification, survival prediction are addressed along ML/DL approaches significantly these steps. We systematically analyzed 107 studies (2018–2024) employing ML, DL, hybrid models across publicly available datasets such BraTS, TCIA, Figshare. light recent developments analysis, many have been proposed accurately obtain ontological characteristics tumors, enhancing diagnostic precision personalized therapeutic strategies.

Language: Английский

---

Metric-Based Meta-Learning Approach for Few-Shot Classification of Brain Tumors Using Magnetic Resonance Images

Electronics, Journal Year: 2025, Volume and Issue: 14(9), P. 1863 - 1863

Published: May 2, 2025

Brain tumor prediction from magnetic resonance images is an important problem, but it difficult due to the complexity of brain structure and variability in appearance. There have been various ML DL-based approaches, limitations current models are a lack adaptability new tasks need for extensive training on large datasets. To address these issues, novel meta-learning approach has proposed, enabling rapid adaptation with limited data. This paper presents method that integrates vision transformer metric-based model, few-shot learning enhance classification performance. The proposed begins preprocessing MRI images, followed by feature extraction using transformer. A Siamese network enhances model’s learning, quick unseen data improving robustness. Furthermore, applying strategy performance when there comparison other developed reveals consistently performs better. It also compared previously approaches same datasets evaluation metrics including accuracy, precision, specificity, recall, F1-score. results demonstrate efficacy our methodology classification, which significant implications enhancing diagnostic accuracy patient outcomes.

Language: Английский

---