DeepChestGNN: A Comprehensive Framework for Enhanced Lung Disease Identification through Advanced Graphical Deep Features

Sensors, Год журнала: 2024, Номер 24(9), С. 2830 - 2830

Опубликована: Апрель 29, 2024

Lung diseases are the third-leading cause of mortality in world. Due to compromised lung function, respiratory difficulties, and physiological complications, disease brought on by toxic substances, pollution, infections, or smoking results millions deaths every year. Chest X-ray images pose a challenge for classification due their visual similarity, leading confusion among radiologists. To imitate those issues, we created an automated system with large data hub that contains 17 datasets chest total 71,096, aim classify ten different classes. For combining various resources, our contain noise annotations, class imbalances, redundancy, etc. We conducted several image pre-processing techniques eliminate artifacts from images, such as resizing, de-annotation, CLAHE, filtering. The elastic deformation augmentation technique also generates balanced dataset. Then, developed DeepChestGNN, novel medical model utilizing deep convolutional neural network (DCNN) extract 100 significant features indicative diseases. This model, incorporating Batch Normalization, MaxPooling, Dropout layers, achieved remarkable 99.74% accuracy extensive trials. By graph networks (GNNs) feedforward architecture is very flexible when it comes working accurate classification. study highlights impact advanced research clinical application potential diagnosing diseases, providing optimal framework precise efficient identification

Язык: Английский

---

An anatomically enhanced and clinically validated framework for lung abnormality classification using deep features and KL divergence

MethodsX, Год журнала: 2025, Номер 14, С. 103348 - 103348

Опубликована: Май 14, 2025

Язык: Английский

---

Multi-Layer Stacked Residual Coordinate Termite Alate Network for Multi-Class Lung Diseases Detection from Chest X-Ray Images

Applied Soft Computing, Год журнала: 2025, Номер unknown, С. 113393 - 113393

Опубликована: Май 1, 2025

Язык: Английский

---

AI-Driven Thoracic X-ray Diagnostics: Transformative Transfer Learning for Clinical Validation in Pulmonary Radiography

Journal of Personalized Medicine, Год журнала: 2024, Номер 14(8), С. 856 - 856

Опубликована: Авг. 12, 2024

Our research evaluates advanced artificial (AI) methodologies to enhance diagnostic accuracy in pulmonary radiography. Utilizing DenseNet121 and ResNet50, we analyzed 108,948 chest X-ray images from 32,717 patients achieved an area under the curve (AUC) of 94% identifying conditions pneumothorax oedema. The model's performance surpassed that expert radiologists, though further improvements are necessary for diagnosing complex such as emphysema, effusion, hernia. Clinical validation integrating Latent Dirichlet Allocation (LDA) Named Entity Recognition (NER) demonstrated potential natural language processing (NLP) clinical workflows. NER system a precision 92% recall 88%. Sentiment analysis using DistilBERT provided nuanced understanding notes, which is essential refining decisions. XGBoost SHapley Additive exPlanations (SHAP) enhanced feature extraction model interpretability. Local Interpretable Model-agnostic Explanations (LIME) occlusion sensitivity enriched transparency, enabling healthcare providers trust AI predictions. These techniques reduced times by 60% annotation errors 75%, setting new benchmark efficiency thoracic diagnostics. explored transformative medical imaging, advancing traditional diagnostics accelerating evaluations settings.

Язык: Английский

---

Enhancing multi-class lung disease classification in chest x-ray images: A hybrid manta-ray foraging volcano eruption algorithm boosted multilayer perceptron neural network approach

Network Computation in Neural Systems, Год журнала: 2024, Номер unknown, С. 1 - 32

Опубликована: Май 16, 2024

One of the most used diagnostic imaging techniques for identifying a variety lung and bone-related conditions is chest X-ray. Recent developments in deep learning have demonstrated several successful cases illness diagnosis from X-rays. However, issues stability class imbalance still need to be resolved. Hence this manuscript, multi-class disease classification x-ray images using hybrid manta-ray foraging volcano eruption algorithm boosted multilayer perceptron neural network approach proposed (MPNN-Hyb-MRF-VEA). Initially, input X-ray are taken Covid-Chest dataset. Anisotropic diffusion Kuwahara filtering (ADKF) enhance quality these lower noise. To capture significant discriminative features, Term frequency-inverse document frequency (TF-IDF) based feature extraction method utilized case. The Multilayer Perceptron Neural Network (MPNN) serves as model disorders COVID-19, pneumonia, tuberculosis (TB), normal. A Hybrid Manta-Ray Foraging Volcano Eruption Algorithm (Hyb-MRF-VEA) introduced further optimize fine-tune MPNN's parameters. Python platform accurately evaluate methodology. performance provides 23.21%, 12.09%, 5.66% higher accuracy compared with existing methods like NFM, SVM, CNN respectively.

Язык: Английский

---

Optimizing Lung Condition Categorization through a Deep Learning Approach to Chest X-ray Image Analysis

BioMedInformatics, Год журнала: 2024, Номер 4(3), С. 2002 - 2021

Опубликована: Сен. 10, 2024

Background: Evaluating chest X-rays is a complex and high-demand task due to the intrinsic challenges associated with diagnosing wide range of pulmonary conditions. Therefore, advanced methodologies are required categorize multiple conditions from X-ray images accurately. Methods: This study introduces an optimized deep learning approach designed for multi-label categorization images, covering broad spectrum conditions, including lung opacity, normative states, COVID-19, bacterial pneumonia, viral tuberculosis. An model based on modified VGG16 architecture SE blocks was developed applied large dataset images. The evaluated against state-of-the-art techniques using metrics such as accuracy, F1-score, precision, recall, area under curve (AUC). Results: VGG16-SE demonstrated superior performance across all metrics. achieved accuracy 98.49%, F1-score 98.23%, precision 98.41%, recall 98.07% AUC 98.86%. Conclusion: provides effective categorizing X-rays. model’s high various suggests its potential integration into clinical workflows, enhancing speed disease diagnosis.

Язык: Английский

---

TransSMPL: Efficient Human Pose Estimation with Pruned and Quantized Transformer Networks

Electronics, Год журнала: 2024, Номер 13(24), С. 4980 - 4980

Опубликована: Дек. 18, 2024

Existing Transformers for 3D human pose and shape estimation models often struggle with computational complexity, particularly when handling high-resolution feature maps. These challenges limit their ability to efficiently utilize fine-grained features, leading suboptimal performance in accurate body reconstruction. In this work, we propose TransSMPL, a novel Transformer framework built upon the SMPL model, specifically designed address of complexity inefficient utilization maps estimation. By replacing HRNet MobileNetV3 lightweight extraction, applying pruning quantization techniques, incorporating an early exit mechanism, TransSMPL significantly reduces both cost memory usage. introduces two key innovations: (1) multi-scale attention reduced from four scales two, allowing more efficient global local integration, (2) confidence-based strategy, which enables model halt further computations high-confidence predictions are achieved, enhancing efficiency. Extensive dynamic also applied reduce size while maintaining competitive performance. Quantitative qualitative experiments on Human3.6M dataset demonstrate efficacy TransSMPL. Our achieves MPJPE (Mean Per Joint Position Error) 48.5 mm, reducing by over 16% compared existing methods similar level accuracy.

Язык: Английский

---

DIFDD: Deep intelligence framework for disease detection using patients electrocardiogram signals and X-ray images

Multimedia Tools and Applications, Год журнала: 2024, Номер 83(35), С. 82369 - 82398

Опубликована: Март 13, 2024

Язык: Английский

---

Enhancing Pulmonary Diagnosis in Chest X-rays through Generative AI Techniques

J — Multidisciplinary Scientific Journal, Год журнала: 2024, Номер 7(3), С. 302 - 318

Опубликована: Авг. 13, 2024

Chest X-ray imaging is an essential tool in the diagnostic procedure for pulmonary conditions, providing healthcare professionals with capability to immediately and accurately determine lung anomalies. This modality fundamental assessing confirming presence of various issues, allowing timely effective medical intervention. In response widespread prevalence infections globally, there a growing imperative adopt automated systems that leverage deep learning (DL) algorithms. These are particularly adept at handling large radiological datasets high precision. study introduces advanced identification model utilizes VGG16 architecture, specifically adapted identifying anomalies such as opacity, COVID-19 pneumonia, normal appearance lungs, viral pneumonia. Furthermore, we address issue generalizability, which prime significance our work. We employed data augmentation technique through CycleGAN, which, experimental outcomes, has proven enhancing robustness model. The combined performance VGG CycleGAN demonstrates remarkable outcomes several evaluation metrics, including recall, F1-score, accuracy, precision, area under curve (AUC). results showcased achieving 98.58%. contributes advancing generative artificial intelligence (AI) analysis establishes solid foundation ongoing developments computer vision technologies within sector.

Язык: Английский

---