A Hybrid Deep Learning Model with Data Augmentation to Improve Tumor Classification Using MRI Images DOI Creative Commons
Eman M. G. Younis,

Mahmoud Nabil Mahmoud,

Abdullah M. Albarrak

et al.

Diagnostics, Journal Year: 2024, Volume and Issue: 14(23), P. 2710 - 2710

Published: Nov. 30, 2024

Cancer ranks second among the causes of mortality worldwide, following cardiovascular diseases. Brain cancer, in particular, has lowest survival rate any form cancer. tumors vary their morphology, texture, and location, which determine classification. The accurate diagnosis enables physicians to select optimal treatment strategies potentially prolong patients' lives. Researchers who have implemented deep learning models for diseases recent years largely focused on neural network optimization enhance performance. This involves implementing with best performance incorporating various architectures by configuring hyperparameters.

Language: Английский

Convolutional Neural Networks: A Survey DOI Creative Commons
Moez Krichen

Computers, Journal Year: 2023, Volume and Issue: 12(8), P. 151 - 151

Published: July 28, 2023

Artificial intelligence (AI) has become a cornerstone of modern technology, revolutionizing industries from healthcare to finance. Convolutional neural networks (CNNs) are subset AI that have emerged as powerful tool for various tasks including image recognition, speech natural language processing (NLP), and even in the field genomics, where they been utilized classify DNA sequences. This paper provides comprehensive overview CNNs their applications recognition tasks. It first introduces fundamentals CNNs, layers convolution operation (Conv_Op), Feat_Maps, activation functions (Activ_Func), training methods. then discusses several popular CNN architectures such LeNet, AlexNet, VGG, ResNet, InceptionNet, compares performance. also examines when use advantages limitations, recommendations developers data scientists, preprocessing data, choosing appropriate hyperparameters (Hyper_Param), evaluating model further explores existing platforms libraries TensorFlow, Keras, PyTorch, Caffe, MXNet, features functionalities. Moreover, it estimates cost using potential cost-saving strategies. Finally, reviews recent developments attention mechanisms, capsule networks, transfer learning, adversarial training, quantization compression, enhancing reliability efficiency through formal The is concluded by summarizing key takeaways discussing future directions research development.

Language: Английский

Citations

266
RanMerFormer: Randomized vision transformer with token merging for brain tumor classification DOI Creative Commons
Jian Wang, Siyuan Lu, Shuihua Wang‎

et al.

Neurocomputing, Journal Year: 2024, Volume and Issue: 573, P. 127216 - 127216

Published: Jan. 5, 2024

Brains are the control center of nervous system in human bodies, and brain tumor is one most deadly diseases. Currently, magnetic resonance imaging (MRI) effective way to tumors early detection clinical diagnoses due its superior quality for soft tissues. Manual analysis MRI error-prone which depends on empirical experience fatigue state radiologists a large extent. Computer-aided diagnosis (CAD) systems becoming more impactful because they can provide accurate prediction results based medical images with advanced techniques from computer vision. Therefore, novel CAD method classification named RanMerFormer presented this paper. A pre-trained vision transformer used as backbone model. Then, merging mechanism proposed remove redundant tokens transformer, improves computing efficiency substantially. Finally, randomized vector functional-link serves head RanMerFormer, be trained swiftly. All simulation obtained two public benchmark datasets, reveal that achieve state-of-the-art performance classification. The applied real-world scenarios assist diagnosis.

Language: Английский

Citations

30
A Comprehensive Review of Convolutional Neural Networks for Defect Detection in Industrial Applications DOI Creative Commons
Rahima Khanam, Muhammad Hussain, Richard Hill

et al.

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 94250 - 94295

Published: Jan. 1, 2024

Quality inspection and defect detection remain critical challenges across diverse industrial applications. Driven by advancements in Deep Learning, Convolutional Neural Networks (CNNs) have revolutionized Computer Vision, enabling breakthroughs image analysis tasks like classification object detection. CNNs' feature learning capabilities made through Machine Vision one of their most impactful This article aims to showcase practical applications CNN models for surface various scenarios, from pallet racks display screens. The review explores methodologies suitable hardware platforms deploying CNN-based architectures. growing Industry 4.0 adoption necessitates enhancing quality processes. main results demonstrate efficacy automating detection, achieving high accuracy real-time performance different surfaces. However, limited datasets, computational complexity, domain-specific nuances require further research. Overall, this acknowledges potential as a transformative technology vision applications, with implications ranging control enhancement cost reductions process optimization.

Language: Английский

Citations

26
Optimized deep learning architecture for brain tumor classification using improved Hunger Games Search Algorithm DOI

Marwa M. Emam,

Nagwan Abdel Samee, Mona Jamjoom

et al.

Computers in Biology and Medicine, Journal Year: 2023, Volume and Issue: 160, P. 106966 - 106966

Published: April 24, 2023

Language: Английский

Citations

42
Attention transformer mechanism and fusion-based deep learning architecture for MRI brain tumor classification system DOI

Sadafossadat Tabatabaei,

Khosro Rezaee,

Min Zhu

et al.

Biomedical Signal Processing and Control, Journal Year: 2023, Volume and Issue: 86, P. 105119 - 105119

Published: June 18, 2023

Language: Английский

Citations

30
Efficient prediction method of triple failure pressure for corroded pipelines under complex loads based on a backpropagation neural network DOI

Tieyao Zhang,

Jian Shuai,

Yi Shuai

et al.

Reliability Engineering & System Safety, Journal Year: 2022, Volume and Issue: 231, P. 108990 - 108990

Published: Nov. 22, 2022

Language: Английский

Citations

33
MEEDNets: Medical Image Classification via Ensemble Bio-inspired Evolutionary DenseNets DOI Creative Commons
Hengde Zhu, Wei Wang, Irek Ulidowski

et al.

Knowledge-Based Systems, Journal Year: 2023, Volume and Issue: 280, P. 111035 - 111035

Published: Sept. 28, 2023

Inspired by the biological evolution, this paper proposes an evolutionary synthesis mechanism to automatically evolve DenseNet towards high sparsity and efficiency for medical image classification. Unlike traditional automatic design methods, generates a sparser offspring in each generation based on its previous trained ancestor. Concretely, we use synaptic model mimic evolution asexual reproduction. Each generation's knowledge is passed down descendant, environmental constraint limits size of descendant DenseNet, moving process sparsity. Additionally, address limitation ensemble learning that requires multiple base networks make decisions, propose evolution-based mechanism. It utilises scheme generate highly sparse networks, which can be used as perform inference. This specially useful extreme case when there only single network. Finally, MEEDNets (Medical Image Classification via Ensemble Bio-inspired Evolutionary DenseNets) consists DenseNet-121s synthesised process. Experimental results show our bio-inspired DenseNets are able drop less important structures compensate increasingly architecture. In addition, proposed outperforms state-of-the-art methods two publicly accessible datasets. All source code study available at https://github.com/hengdezhu/MEEDNets.

Language: Английский

Citations

19
YoDenBi-NET: YOLO + DenseNet + Bi-LSTM-based hybrid deep learning model for brain tumor classification DOI
Abdülkadir Karacı, Kemal Akyol

Neural Computing and Applications, Journal Year: 2023, Volume and Issue: 35(17), P. 12583 - 12598

Published: March 4, 2023

Language: Английский

Citations

14
Deep Feature Extraction with Cubic-SVM for Classification of Brain Tumor DOI Open Access
Mohammed Bourennane,

Hilal Naimi,

Mohamed Elbar

et al.

STUDIES IN ENGINEERING AND EXACT SCIENCES, Journal Year: 2024, Volume and Issue: 5(1), P. 19 - 35

Published: Jan. 12, 2024

Brain tumors (BT) are fatal and debilitating conditions that shorten the typical lifespan of patients. Patients with BTs who receive inadequate treatment an incorrect diagnosis have a lower chance survival. Magnetic resonance imaging (MRI) is often employed to assess tumor. However, because massive quantity data provided by MRI, early BT detection complex time-consuming procedure in biomedical imaging. As consequence, automated efficient strategy required. The brain or malignancies has been done using variety conventional machine learning (ML) approaches. manually collected properties, however, provide main problem these models. constraints previously stated addressed fusion deep model for binary classification presented this study. recommended method combines two different CNN (Efficientnetb0, VGG-19) models automatically extract features make use feature’s Cubic SVM classifier model. Additionally, approach displayed outstanding performance various measures, including Accuracy (99.78%), Precision Recall F1-Score on same Kaggle (Br35H) dataset. proposed performs better than current approaches classifying from MRI images.

Language: Английский

Citations

6
Condition monitoring of wind turbine based on a novel spatio-temporal feature aggregation network integrated with adaptive threshold interval DOI
Lixiao Cao, Jie Zhang,

Qian Zheng

et al.

Advanced Engineering Informatics, Journal Year: 2024, Volume and Issue: 62, P. 102676 - 102676

Published: June 28, 2024

Language: Английский

Citations

5