Optimizing the topology of convolutional neural network (CNN) and artificial neural network (ANN) for brain tumor diagnosis (BTD) through MRIs DOI Creative Commons
Jianhong Ye, Zhiyong Zhao,

Ehsan Ghafourian

et al.

Heliyon, Journal Year: 2024, Volume and Issue: 10(16), P. e35083 - e35083

Published: July 23, 2024

The use of MRI analysis for BTD and tumor type detection has considerable importance within the domain machine vision. Numerous methodologies have been proposed to address this issue, significant progress achieved in via deep learning (DL) approaches. While majority offered approaches using artificial neural networks (ANNs) (DNNs) demonstrate satisfactory performance Bayesian Tree Descent (BTD), none these research studies can ensure optimality employed model structure. Put simply, there is room improvement efficiency models BTD. This introduces a novel approach optimizing configuration Convolutional Neural Networks (CNNs) Artificial issue. suggested employs (CNN) purpose segmenting brain MRIs. model's configurable hyper-parameters are tuned genetic algorithm (GA). Multi-Linear Principal Component Analysis (MPCA) used decrease dimensionality segmented features pictures after they segmented. Ultimately, segmentation procedure executed an Network (ANN). In network (ANN), (GA) sets ideal number neurons hidden layer appropriate weight vector. effectiveness was assessed by utilizing BRATS2014 BTD20 databases. results indicate that method classify samples from two databases with average accuracy 98.6 % 99.1 %, respectively, which represents at least 1.1 over preceding methods.

Language: Английский

Modified U-Net with attention gate for enhanced automated brain tumor segmentation DOI
Shoffan Saifullah, Rafał Dreżewski, Anton Yudhana

et al.

Neural Computing and Applications, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 2, 2025

Language: Английский

Citations

1
Modernizing Neuro-Oncology: The Impact of Imaging, Liquid Biopsies, and AI on Diagnosis and Treatment DOI Open Access

John Rafanan,

Nabih Ghani, Sarah Kazemeini

et al.

International Journal of Molecular Sciences, Journal Year: 2025, Volume and Issue: 26(3), P. 917 - 917

Published: Jan. 22, 2025

Advances in neuro-oncology have transformed the diagnosis and management of brain tumors, which are among most challenging malignancies due to their high mortality rates complex neurological effects. Despite advancements surgery chemoradiotherapy, prognosis for glioblastoma multiforme (GBM) metastases remains poor, underscoring need innovative diagnostic strategies. This review highlights recent imaging techniques, liquid biopsies, artificial intelligence (AI) applications addressing current challenges. Advanced including diffusion tensor (DTI) magnetic resonance spectroscopy (MRS), improve differentiation tumor progression from treatment-related changes. Additionally, novel positron emission tomography (PET) radiotracers, such as 18F-fluoropivalate, 18F-fluoroethyltyrosine, 18F-fluluciclovine, facilitate metabolic profiling high-grade gliomas. Liquid biopsy, a minimally invasive technique, enables real-time monitoring biomarkers circulating DNA (ctDNA), extracellular vesicles (EVs), cells (CTCs), tumor-educated platelets (TEPs), enhancing precision. AI-driven algorithms, convolutional neural networks, integrate tools accuracy, reduce interobserver variability, accelerate clinical decision-making. These innovations advance personalized neuro-oncological care, offering new opportunities outcomes patients with central nervous system tumors. We advocate future research integrating these into workflows, accessibility challenges, standardizing methodologies ensure broad applicability neuro-oncology.

Language: Английский

Citations

1
FlexiCombFE: A flexible, combination-based feature engineering framework for brain tumor detection DOI Creative Commons
Ilknur Tuncer, Abdul Hafeez‐Baig,

Prabal Datta Barua

et al.

Biomedical Signal Processing and Control, Journal Year: 2025, Volume and Issue: 104, P. 107538 - 107538

Published: Jan. 26, 2025

Language: Английский

Citations

1
Impact of preprocessing techniques on MRI-based brain tumor detection DOI
Tanima Ghosh,

N. Jayanthi

Multimedia Tools and Applications, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 1, 2025

Language: Английский

Citations

1
Advanced Deep Learning and Machine Learning Techniques for MRI Brain Tumor Analysis: A Review DOI Creative Commons

Rim Missaoui,

Wided Hechkel, Wajdi Saadaoui

et al.

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

Citations

1
A Convolutional Block Base Architecture for Multiclass Brain Tumor Detection Using Magnetic Resonance Imaging DOI Open Access
Muneeb A. Khan, Heemin Park

Electronics, Journal Year: 2024, Volume and Issue: 13(2), P. 364 - 364

Published: Jan. 15, 2024

In the domain of radiological diagnostics, accurately detecting and classifying brain tumors from magnetic resonance imaging (MRI) scans presents significant challenges, primarily due to complex diverse manifestations in these scans. this paper, a convolutional-block-based architecture has been proposed for detection multiclass using MRI Leveraging strengths CNNs, our framework demonstrates robustness efficiency distinguishing between different tumor types. Extensive evaluations on three datasets underscore model’s exceptional diagnostic accuracy, with an average accuracy rate 97.52%, precision 97.63%, recall 97.18%, specificity 98.32%, F1-score 97.36%. These results outperform contemporary methods, including state-of-the-art (SOTA) models such as VGG16, VGG19, MobileNet, EfficientNet, ResNet50, Xception, DenseNet121. Furthermore, its adaptability across modalities underlines potential broad clinical application, offering advancement field diagnostics detection.

Language: Английский

Citations

8
Abnormal Brain Tumors Classification Using ResNet50 and Its Comprehensive Evaluation DOI Creative Commons
Ayesha Younis, Qiang Li, Zargaam Afzal

et al.

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 78843 - 78853

Published: Jan. 1, 2024

Brain tumors present significant health risks due to abnormal cell growth, potentially leading organ dysfunction and mortality in adults. Magnetic resonance imaging (MRI) is crucial for tumor classification, but limited expertise this area necessitates advanced methods accurate diagnosis. Deep Learning has emerged as a pivotal tool, yet gaps remain achieving optimal accuracy. This study addresses these by proposing an enhanced model classifying meningioma, glioma, pituitary gland tumors, thereby improving precision brain detection. Trained on dataset of 5712 images, the achieves exceptional accuracy (99%) both training validation datasets, with focus precision. Leveraging techniques such data augmentation, transfer learning ResNet50, regularization ensures stability generalizability. Evaluation 1311-image test set reveals outstanding class-specific accuracies (glioma: 98.33%, meningioma: 94.44%, no tumor: 100.00%, pituitary: 100.00%). Comprehensive metrics including (0.983559), recall (0.983219), F1 score (0.983140), AUC (ROC) (0.999038) underscore model's efficacy. demonstrates potential deep early diagnosis, surpassing conventional laying robust foundation future research neural network-based classification algorithms tumors.

Language: Английский

Citations

8
Improved Brain Tumor Segmentation Using Modified U-Net based on Particle Swarm Optimization Image Enhancement DOI
Shoffan Saifullah, Rafał Dreżewski

Proceedings of the Genetic and Evolutionary Computation Conference Companion, Journal Year: 2024, Volume and Issue: unknown, P. 611 - 614

Published: July 14, 2024

Language: Английский

Citations

8
Brain tumor detection and classification in MRI using hybrid ViT and GRU model with explainable AI in Southern Bangladesh DOI Creative Commons

Md. Mahfuz Ahmed,

Md. Maruf Hossain, Md. Rakibul Islam

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Oct. 1, 2024

Language: Английский

Citations

8
Metastatic Lymph Node Detection on Ultrasound Images Using YOLOv7 in Patients with Head and Neck Squamous Cell Carcinoma DOI Open Access

Sato Eida,

Motoki Fukuda, Ikuo Katayama

et al.

Cancers, Journal Year: 2024, Volume and Issue: 16(2), P. 274 - 274

Published: Jan. 8, 2024

Ultrasonography is the preferred modality for detailed evaluation of enlarged lymph nodes (LNs) identified on computed tomography and/or magnetic resonance imaging, owing to its high spatial resolution. However, diagnostic performance ultrasonography depends examiner's expertise. To support ultrasonographic diagnosis, we developed YOLOv7-based deep learning models metastatic LN detection and compared their with that highly experienced radiologists less residents. We enrolled 462 B- D-mode ultrasound images 261 279 non-metastatic histopathologically confirmed LNs from 126 patients head neck squamous cell carcinoma. The were optimized using training validation was evaluated testing images, respectively. model's comparable superior residents' reading whereas B-mode higher than residents but lower images. Thus, can assist in diagnoses. model could raise same level as radiologists.

Language: Английский

Citations

7