Deep learning: systematic review, models, challenges, and research directions

Neural Computing and Applications, Journal Year: 2023, Volume and Issue: 35(31), P. 23103 - 23124

Published: Sept. 7, 2023

Abstract The current development in deep learning is witnessing an exponential transition into automation applications. This can provide a promising framework for higher performance and lower complexity. ongoing undergoes several rapid changes, resulting the processing of data by studies, while it may lead to time-consuming costly models. Thus, address these challenges, studies have been conducted investigate techniques; however, they mostly focused on specific approaches, such as supervised learning. In addition, did not comprehensively other techniques, unsupervised reinforcement techniques. Moreover, majority neglect discuss some main methodologies learning, transfer federated online Therefore, motivated limitations existing this study summarizes techniques supervised, unsupervised, reinforcement, hybrid learning-based addition each category, brief description categories their models provided. Some critical topics namely, transfer, federated, models, are explored discussed detail. Finally, challenges future directions outlined wider outlooks researchers.

Language: Английский

---

A comparison review of transfer learning and self-supervised learning: Definitions, applications, advantages and limitations

Expert Systems with Applications, Journal Year: 2023, Volume and Issue: 242, P. 122807 - 122807

Published: Dec. 2, 2023

Deep learning has emerged as a powerful tool in various domains, revolutionising machine research. However, one persistent challenge is the scarcity of labelled training data, which hampers performance and generalisation deep models. To address this limitation, researchers have developed innovative methods to overcome data enhance model capabilities. Two prevalent techniques that gained significant attention are transfer self-supervised learning. Transfer leverages knowledge learned from pre-training on large-scale dataset, such ImageNet, applies it target task with limited data. This approach allows models benefit representations effectively new tasks, resulting improved generalisation. On other hand, focuses using pretext tasks do not require manual annotation, allowing them learn valuable large amounts unlabelled These can then be fine-tuned for downstream mitigating need extensive In recent years, found applications fields, including medical image processing, video recognition, natural language processing. approaches demonstrated remarkable achievements, enabling breakthroughs areas disease diagnosis, object understanding. while these offer numerous advantages, they also limitations. For example, may face domain mismatch issues between requires careful design ensure meaningful representations. review paper explores fields within past three years. It delves into advantages limitations each approach, assesses employing techniques, identifies potential directions future By providing comprehensive current methods, article offers guidance selecting best technique specific issue.

Language: Английский

---

Brain Tumor Detection and Classification Using Intelligence Techniques: An Overview

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 12870 - 12886

Published: Jan. 1, 2023

A tumor is carried on by rapid and uncontrolled cell growth in the brain. If it not treated initial phases, could prove fatal. Despite numerous significant efforts encouraging outcomes, accurate segmentation classification continue to be a challenge. Detection of brain tumors significantly complicated distinctions position, structure, proportions. The main disinterest this study stays offer investigators, comprehensive literature Magnetic Resonance (MR) imaging's ability identify tumors. Using computational intelligence statistical image processing techniques, research paper proposed several ways detect cancer This also shows an assessment matrix for specific system using particular systems dataset types. explains morphology tumors, accessible data sets, augmentation methods, component extraction, categorization among Deep Learning (DL), Transfer (TL), Machine (ML) models. Finally, our compiles all relevant material identification understanding including their benefits, drawbacks, advancements, upcoming trends.

Language: Английский

---

Vision Transformers, Ensemble Model, and Transfer Learning Leveraging Explainable AI for Brain Tumor Detection and Classification

IEEE Journal of Biomedical and Health Informatics, Journal Year: 2023, Volume and Issue: 28(3), P. 1261 - 1272

Published: April 12, 2023

The abnormal growth of malignant or nonmalignant tissues in the brain causes long-term damage to brain. Magnetic resonance imaging (MRI) is one most common methods detecting tumors. To determine whether a patient has tumor, MRI filters are physically examined by experts after they received. It possible for images different specialists produce inconsistent results since professionals formulate evaluations differently. Furthermore, merely identifying tumor not enough. begin treatment as soon possible, it equally important type has. In this paper, we consider multiclass classification tumors significant work been done on binary classification. order detect faster, more unbiased, and reliably, investigated performance several deep learning (DL) architectures including Visual Geometry Group 16 (VGG16), InceptionV3, VGG19, ResNet50, InceptionResNetV2, Xception. Following this, propose transfer learning(TL) based model called IVX16 three best-performing TL models. We use dataset consisting total 3264 images. Through extensive experiments, achieve peak accuracy $95.11\%$ , notation="LaTeX">$93.88\%$ notation="LaTeX">$94.19\%$ notation="LaTeX">$93.58\%$ notation="LaTeX">$94.5\%$ notation="LaTeX">$96.94\%$ VGG16, Xception, IVX16, respectively. Explainable AI evaluate validity each DL implement recently introduced Vison Transformer (ViT) models compare their obtained output with ensemble model.

Language: Английский

---

Brain tumor segmentation in MRI with multi-modality spatial information enhancement and boundary shape correction

Pattern Recognition, Journal Year: 2024, Volume and Issue: 153, P. 110553 - 110553

Published: May 6, 2024

Language: Английский

---

Improved Multiclass Brain Tumor Detection using Convolutional Neural Networks and Magnetic Resonance Imaging

International Journal of Advanced Computer Science and Applications, Journal Year: 2023, Volume and Issue: 14(3)

Published: Jan. 1, 2023

Recently, Deep learning algorithms, particularly Convolutional Neural Networks (CNNs), have been applied extensively for image recognition and classification tasks, with successful results in the field of medicine, such as medical analysis. Radiologists a hard time categorizing this lethal illness since brain tumors include variety tumor cells. Lately, methods based on computer-aided diagnostics claimed to employ magnetic resonance imaging help diagnosis cancers (MRI). (CNNs) are often used analysis, including detection cancers. This effort was motivated by difficulty that physicians appropriately detecting tumors, when they early stages bleeding. proposed model categorized into four distinct classes: (Normal, Glioma, Meningioma, Pituitary). The CNN networks reach 95% recall, 95.44% accuracy 95.36% F1-score.

Language: Английский

---

A novel Swin transformer approach utilizing residual multi-layer perceptron for diagnosing brain tumors in MRI images

International Journal of Machine Learning and Cybernetics, Journal Year: 2024, Volume and Issue: 15(9), P. 3579 - 3597

Published: March 5, 2024

Abstract Serious consequences due to brain tumors necessitate a timely and accurate diagnosis. However, obstacles such as suboptimal imaging quality, issues with data integrity, varying tumor types stages, potential errors in interpretation hinder the achievement of precise prompt diagnoses. The rapid identification plays pivotal role ensuring patient safety. Deep learning-based systems hold promise aiding radiologists make diagnoses swiftly accurately. In this study, we present an advanced deep learning approach based on Swin Transformer. proposed method introduces novel Hybrid Shifted Windows Multi-Head Self-Attention module (HSW-MSA) along rescaled model. This enhancement aims improve classification accuracy, reduce memory usage, simplify training complexity. Residual-based MLP (ResMLP) replaces traditional Transformer, thereby improving speed, parameter efficiency. We evaluate Proposed-Swin model publicly available MRI dataset four classes, using only test data. Model performance is enhanced through application transfer augmentation techniques for efficient robust training. achieves remarkable accuracy 99.92%, surpassing previous research models. underscores effectiveness Transformer HSW-MSA ResMLP improvements innovative diagnostic offering support diagnosis, ultimately outcomes reducing risks.

Language: Английский

---

Enhancing Brain Tumor Segmentation Accuracy through Scalable Federated Learning with Advanced Data Privacy and Security Measures

Mathematics, Journal Year: 2023, Volume and Issue: 11(19), P. 4189 - 4189

Published: Oct. 7, 2023

Brain tumor segmentation in medical imaging is a critical task for diagnosis and treatment while preserving patient data privacy security. Traditional centralized approaches often encounter obstacles sharing due to regulations security concerns, hindering the development of advanced AI-based applications. To overcome these challenges, this study proposes utilization federated learning. The proposed framework enables collaborative learning by training model on distributed from multiple institutions without raw data. Leveraging U-Net-based architecture, renowned its exceptional performance semantic tasks, emphasizes scalability approach large-scale deployment experimental results showcase remarkable effectiveness learning, significantly improving specificity 0.96 dice coefficient 0.89 with increase clients 50 100. Furthermore, outperforms existing convolutional neural network (CNN)- recurrent (RNN)-based methods, achieving higher accuracy, enhanced performance, increased efficiency. findings research contribute advancing field image upholding

Language: Английский

---

A Comprehensive Survey of Convolutions in Deep Learning: Applications, Challenges, and Future Trends

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 41180 - 41218

Published: Jan. 1, 2024

In today's digital age, Convolutional Neural Networks (CNNs), a subset of Deep Learning (DL), are widely used for various computer vision tasks such as image classification, object detection, and segmentation. There numerous types CNNs designed to meet specific needs requirements, including 1D, 2D, 3D CNNs, well dilated, grouped, attention, depthwise convolutions, NAS, among others. Each type CNN has its unique structure characteristics, making it suitable tasks. It's crucial gain thorough understanding perform comparative analysis these different understand their strengths weaknesses. Furthermore, studying the performance, limitations, practical applications each can aid in development new improved architectures future. We also dive into platforms frameworks that researchers utilize research or from perspectives. Additionally, we explore main fields like 6D vision, generative models, meta-learning. This survey paper provides comprehensive examination comparison architectures, highlighting architectural differences emphasizing respective advantages, disadvantages, applications, challenges, future trends.

Language: Английский

---

Brain tumor detection with integrating traditional and computational intelligence approaches across diverse imaging modalities - Challenges and future directions

Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 175, P. 108412 - 108412

Published: April 16, 2024

Language: Английский

---