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

---

The Personal Health Applications of Machine Learning Techniques in the Internet of Behaviors

Sustainability, Journal Year: 2023, Volume and Issue: 15(16), P. 12406 - 12406

Published: Aug. 15, 2023

With the swift pace of development artificial intelligence (AI) in diverse spheres, medical and healthcare fields are utilizing machine learning (ML) methodologies numerous inventive ways. ML techniques have outstripped formerly state-of-the-art practices, yielding faster more precise outcomes. Healthcare practitioners increasingly drawn to this technology their initiatives relating Internet Behavior (IoB). This area research scrutinizes rationales, approaches, timing human adoption, encompassing domains Things (IoT), behavioral science, edge analytics. The significance applications based on IoB stems from its ability analyze interpret copious amounts complex data instantly, providing innovative perspectives that can enhance outcomes boost efficiency IoB-based procedures thus aid diagnoses, treatment protocols, clinical decision making. As a result inadequacy thorough inquiry into employment ML-based approaches context using for applications, we conducted study subject matter, introducing novel taxonomy underscores need employ each method distinctively. objective mind, classified cutting-edge solutions challenges five categories, which convolutional neural networks (CNNs), recurrent (RNNs), deep (DNNs), multilayer perceptions (MLPs), hybrid methods. In order delve deeper, systematic literature review (SLR) examined critical factors, such as primary concept, benefits, drawbacks, simulation environment, datasets. Subsequently, highlighted pioneering studies issues. Moreover, several related implementation medicine been tackled, thereby gradually fostering further endeavors health studies. Our findings indicated Tensorflow was most commonly utilized setting, accounting 24% proposed by researchers. Additionally, accuracy deemed be crucial parameter majority papers.

Language: Английский

---

Automated diagnosis of cardiovascular diseases from cardiac magnetic resonance imaging using deep learning models: A review

Computers in Biology and Medicine, Journal Year: 2023, Volume and Issue: 160, P. 106998 - 106998

Published: May 6, 2023

Language: Английский

---

A review of deep learning in dentistry

Neurocomputing, Journal Year: 2023, Volume and Issue: 554, P. 126629 - 126629

Published: July 27, 2023

Oral diseases have a significant impact on human health, often going unnoticed in their early stages. Deep learning, promising field artificial intelligence, has shown remarkable success various domains, especially dentistry. This paper aims to provide an overview of recent research deep learning applications dentistry, with focus dental imaging. algorithms perform well difficult tasks such as image segmentation and recognition, enabling accurate identification oral conditions abnormalities. Integration other health data offers holistic understanding the relationship between systemic health. However, there are still many challenges that need be addressed.

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 EfficientNetv2 with global and efficient channel attention mechanisms for accurate MRI-Based brain tumor classification

Cluster Computing, Journal Year: 2024, Volume and Issue: 27(8), P. 11187 - 11212

Published: May 20, 2024

Abstract The early and accurate diagnosis of brain tumors is critical for effective treatment planning, with Magnetic Resonance Imaging (MRI) serving as a key tool in the non-invasive examination such conditions. Despite advancements Computer-Aided Diagnosis (CADx) systems powered by deep learning, challenge accurately classifying from MRI scans persists due to high variability tumor appearances subtlety early-stage manifestations. This work introduces novel adaptation EfficientNetv2 architecture, enhanced Global Attention Mechanism (GAM) Efficient Channel (ECA), aimed at overcoming these hurdles. enhancement not only amplifies model’s ability focus on salient features within complex images but also significantly improves classification accuracy tumors. Our approach distinguishes itself meticulously integrating attention mechanisms that systematically enhance feature extraction, thereby achieving superior performance detecting broad spectrum Demonstrated through extensive experiments large public dataset, our model achieves an exceptional high-test 99.76%, setting new benchmark MRI-based classification. Moreover, incorporation Grad-CAM visualization techniques sheds light decision-making process, offering transparent interpretable insights are invaluable clinical assessment. By addressing limitations inherent previous models, this study advances field medical imaging analysis highlights pivotal role enhancing interpretability learning models diagnosis. research sets stage advanced CADx systems, patient care outcomes.

Language: Английский

---

A systematic review of deep learning data augmentation in medical imaging: Recent advances and future research directions

Healthcare Analytics, Journal Year: 2024, Volume and Issue: 5, P. 100340 - 100340

Published: May 8, 2024

Data augmentation involves artificially expanding a dataset by applying various transformations to the existing data. Recent developments in deep learning have advanced data augmentation, enabling more complex transformations. Especially vital medical domain, learning-based improves model robustness generating realistic variations images, enhancing diagnostic and predictive task performance. Therefore, assist researchers experts their pursuits, there is need for an extensive informative study that covers latest advancements growing domain of imaging. There gap literature regarding recent augmentation. This explores diverse applications imaging analyzes research these areas address this gap. The also popular datasets evaluation metrics improve understanding. Subsequently, provides short discussion conventional techniques along with detailed on algorithms further results experimental details from state-of-the-art understand progress Finally, discusses challenges proposes future directions concerns. systematic review offers thorough overview imaging, covering application domains, models, analysis, challenges, directions. It valuable resource multidisciplinary studies making decisions based analytics.

Language: Английский

---

TransResUNet: Revolutionizing Glioma Brain Tumor Segmentation Through Transformer-Enhanced Residual UNet

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 72105 - 72116

Published: Jan. 1, 2024

Accurate segmentation of brain tumors from MRI sequences is essential across diverse clinical scenarios, facilitating precise delineation anatomical structures and disease-affected areas. This study presents an innovative deep-learning method for segmenting glioma tumors, utilizing a hybrid architecture that combines ResNet U-Net with Transformer blocks. The proposed model adeptly encompasses both the local global contextual details present in scans. includes encoder based on extracting hierarchical features, followed by residual blocks to enhance feature representation while maintaining spatial information. Additionally, central transformer block, incorporating Multi-Head Attention mechanisms, enables modeling long-range dependencies comprehension, progressively refining interactions. To handle structural scale variations within images, skip connections are utilized during decoding phase. Transposed convolutional layers decoder upsample maps, retaining information earlier layers. A rigorous assessment model's functionality was carried out BraTS2019 dataset, employing comprehensive set evaluation metrics including accuracy, IOU score, specificity, sensitivity, dice precision. focused individual tumor classes, namely whole, core, enhancing regions. During validation, suggested demonstrated remarkable scores 0.91, 0.89, 0.84 whole tumor, core respectively, yielding impressive overall accuracy rate 98%.

Language: Английский

---

Continual Learning in Medicine: A Systematic Literature Review

Neural Processing Letters, Journal Year: 2025, Volume and Issue: 57(1)

Published: Jan. 7, 2025

Abstract Continual Learning (CL) is a novel AI paradigm in which tasks and data are made available over time; thus, the trained model computed on basis of stream data. CL-based approaches able to learn new skills knowledge without forgetting previous ones, with no guaranteed access previously encountered data, mitigating so-called “catastrophic forgetting” phenomenon. Interestingly, by making systems improve time need for large amounts or computational resources, CL can help at reducing impact computationally-expensive energy-intensive activities; hence, play key role path towards more green AIs, enabling efficient sustainable uses resources. In this work, we describe different methods proposed literature solve tasks; survey applications, highlighting strengths weaknesses, particular focus biomedical context. Furthermore, discuss how make robust suitable wider range applications.

Language: Английский

---

Transfer learning for accurate fetal organ classification from ultrasound images: a potential tool for maternal healthcare providers

Scientific Reports, Journal Year: 2023, Volume and Issue: 13(1)

Published: Oct. 20, 2023

Ultrasound imaging is commonly used to aid in fetal development. It has the advantage of being real-time, low-cost, non-invasive, and easy use. However, organ detection a challenging task for obstetricians, it depends on several factors, such as position fetus, habitus mother, technique. In addition, image interpretation must be performed by trained healthcare professional who can take into account all relevant clinical factors. Artificial intelligence playing an increasingly important role medical help solve many challenges associated with classification. this paper, we propose deep-learning model automating classification from ultrasound images. We tested dataset images, including two datasets different regions, recorded them machines ensure effective organs. training process labeled annotations organs brain, abdomen, femur, thorax, well maternal cervical part. The was detect these images using deep convolutional neural network architecture. Following process, model, DenseNet169, assessed separate test dataset. results were promising, accuracy 99.84%, which impressive result. F1 score 99.84% AUC 98.95%. Our study showed that proposed outperformed traditional methods relied manual experienced clinicians. also other learning-based architectures strategies. This may contribute development more accessible health services around world improve status mothers their newborns worldwide.

Language: Английский

---