Exploring explainable AI features in the vocal biomarkers of lung disease

Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 179, P. 108844 - 108844

Published: July 8, 2024

This review delves into the burgeoning field of explainable artificial intelligence (XAI) in detection and analysis lung diseases through vocal biomarkers. Lung diseases, often elusive their early stages, pose a significant public health challenge. Recent advancements AI have ushered innovative methods for detection, yet black-box nature many models limits clinical applicability. XAI emerges as pivotal tool, enhancing transparency interpretability AI-driven diagnostics. synthesizes current research on application analyzing biomarkers highlighting how these techniques elucidate connections between specific features pathology. We critically examine methodologies employed, types studied, performance various models. The potential to aid monitor disease progression, personalize treatment strategies pulmonary medicine is emphasized. Furthermore, this identifies challenges, including data heterogeneity model generalizability, proposes future directions research. By offering comprehensive context aims bridge gap advanced computational approaches practice, paving way more transparent, reliable, effective diagnostic tools.

Language: Английский

---

Features and Eigenspectral Densities Analyses for Machine Learning and Classification of Severities in Chronic Obstructive Pulmonary Diseases

Intelligence-Based Medicine, Journal Year: 2025, Volume and Issue: unknown, P. 100217 - 100217

Published: Feb. 1, 2025

Language: Английский

---

Genetic Algorithm-Guided Diverse Sample Selection with Diffusion-Based Generative Memory for Continual Learning of Acoustics

Published: Jan. 1, 2025

Language: Английский

---

Lung sound disease detection using attention over pre-trained efficientnet architecture

Multimedia Tools and Applications, Journal Year: 2024, Volume and Issue: unknown

Published: Aug. 31, 2024

Language: Английский

---

Deep Learning Models for Classification of Lung Diseases

European Journal of Theoretical and Applied Sciences, Journal Year: 2024, Volume and Issue: 2(2), P. 858 - 868

Published: March 1, 2024

This thesis focuses on the importance of early detection in lung cancer through use medical imaging techniques and deep learning models. The current practice examining nodules larger than 7 mm can delay allow cancerous to grow undetected. project aims detect as small 3 improve chances identification. constrained volume datasets transfer addresses scarcity data, neural networks are employed for classification segmentation tasks. Despite limited dataset, results demonstrate effectiveness proposed Class activation maps enhance accuracy provide insights into most critical areas diagnosis. research contributes understanding disease diagnosis highlights potential imaging.

Language: Английский

---

A Review on Identifying Lung Disease Sounds using different ML and DL Models

International Journal of Scientific Research in Computer Science Engineering and Information Technology, Journal Year: 2024, Volume and Issue: 10(3), P. 399 - 411

Published: May 30, 2024

This comprehensive review explores the efficacy of various machine learning (ML) and deep (DL) models in identifying lung disease sounds, addressing complex diagnostic challenges posed by diverse acoustic patterns associated with diseases. ML algorithms like Support Vector Machines (SVM), Random Forests, k-Nearest Neighbors (k-NN) offer robust classification frameworks, while DL architectures such as Convolutional Neural Networks (CNN) excel extracting intricate audio patterns. By analyzing performance metrics these models, including accuracy, sensitivity, specificity, area under curve (AUC), aims to assess their comparative strengths limitations accurately sounds. The insights gained from this can significantly contribute development more precise effective tools interventions tailored diseases, thus improving patient outcomes healthcare efficiency realm respiratory disorders.

Language: Английский

---

Early stage lung cancer detection from speech sounds in natural environments

Biomedical Signal Processing and Control, Journal Year: 2024, Volume and Issue: 96, P. 106628 - 106628

Published: July 8, 2024

Language: Английский

---

Developing a 3D Segmentation Technique by a Region-Growing Algorithm of CT Scan Lung Images

Revue d intelligence artificielle, Journal Year: 2024, Volume and Issue: 38(4), P. 1327 - 1333

Published: Aug. 23, 2024

Conventional methodologies for lung image segmentation (LIS) encounter challenges posed by anatomical intricacies and intensity fluctuations in computed tomography (CT) scans.This study introduces a precise effective approach to segmenting areas utilising region-growing algorithm.Initial steps involve data pre-processing, encompassing regulation, noise reduction, identification of regions.The core employs algorithm; namely, active contours (ACs); with explicit criteria based on homogeneity, values, spatial connectivity.This iterative algorithm expands connected regions from seed points (SPs) within the identified region, ensuring conformity defined criteria.Refinement occurs through merging neighbouring exhibiting similar attributes.Evaluation dataset 196 chronic obstructive pulmonary disease (COPD) patients varying degrees abnormalities demonstrates accurate three-dimensional (3D) segmentation, yielding an average dice similarity coefficient (DSC) 0.946 ± 0.023.This performance significantly surpasses that thresholding methods (DSC: 0.826 0.033), indicating notably enhanced overlap between segmented ground truth data.This contributes robust efficient technique realm LIS, facilitating 3D LIS CT scans.

Language: Английский

---

Improving lung cancer diagnoses: a machine learning approach for detection and prediction in CT-Scan image analysis

Service Oriented Computing and Applications, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 22, 2024

Language: Английский

---

Detection of tuberculosis using cough audio analysis: a deep learning approach with capsule networks

Discover Artificial Intelligence, Journal Year: 2024, Volume and Issue: 4(1)

Published: Nov. 4, 2024

Tuberculosis (TB) is a widespread infectious disease that requires early detection for effective treatment and control. This study aims to improve TB using cough audio analysis, comparing the performance of capsule networks other deep learning models. We used recordings from 1105 individuals with new or worsening at least two weeks, totaling 9772 recordings. These were processed into spectral images, HOG features extracted. Various models, including Capsule Networks + FCNN, CNN, VGG16, ResNet50 trained evaluated. FCNN achieved best an accuracy 0.97, sensitivity 0.98, specificity 0.96, F1 score precision outperforming attribute due model's ability learn complex images. concludes are more than typical CNN-based models in diagnosing audio. suggests advanced frameworks could significantly enhance screening accuracy, especially resource-limited areas.

Language: Английский

---