Multi-modal deep learning methods for classification of chest diseases using different medical imaging and cough sounds

PLoS ONE, Journal Year: 2024, Volume and Issue: 19(3), P. e0296352 - e0296352

Published: March 12, 2024

Chest disease refers to a wide range of conditions affecting the lungs, such as COVID-19, lung cancer (LC), consolidation (COL), and many more. When diagnosing chest disorders medical professionals may be thrown off by overlapping symptoms (such fever, cough, sore throat, etc.). Additionally, researchers make use X-rays (CXR), cough sounds, computed tomography (CT) scans diagnose disorders. The present study aims classify nine different disorders, including LC, COL, atelectasis (ATE), tuberculosis (TB), pneumothorax (PNEUTH), edema (EDE), pneumonia (PNEU). Thus, we suggested four novel convolutional neural network (CNN) models that train distinct image-level representations for classifications extracting features from images. Furthermore, proposed CNN employed several new approaches max-pooling layer, batch normalization layers (BANL), dropout, rank-based average pooling (RBAP), multiple-way data generation (MWDG). scalogram method is utilized transform sounds coughing into visual representation. Before beginning model has been developed, SMOTE approach used calibrate CXR CT well sound images (CSI) CXR, scan, CSI training evaluating come 24 publicly available benchmark illness datasets. classification performance compared with seven baseline models, namely Vgg-19, ResNet-101, ResNet-50, DenseNet-121, EfficientNetB0, DenseNet-201, Inception-V3, in addition state-of-the-art (SOTA) classifiers. effectiveness further demonstrated results ablation experiments. was successful achieving an accuracy 99.01%, making it superior both SOTA As result, capable offering significant support radiologists other professionals.

Language: Английский

---

Internet of Things with Deep Learning Techniques for Pandemic Detection: A Comprehensive Review of Current Trends and Open Issues

Electronics, Journal Year: 2024, Volume and Issue: 13(13), P. 2630 - 2630

Published: July 4, 2024

Technological advancements for diverse aspects of life have been made possible by the swift development and application Internet Things (IoT) based technologies. IoT technologies are primarily intended to streamline various processes, guarantee system (technology or process) efficiency, ultimately enhance quality life. An effective method pandemic detection is combination deep learning (DL) techniques with IoT. proved beneficial in many healthcare domains, especially during last worldwide health crisis: COVID-19 pandemic. Using studies published between 2019 2024, this review seeks examine ways that IoT-DL models contribute detection. We obtained titles, keywords, abstracts chosen papers using Scopus Web Science (WoS) databases. This study offers a comprehensive literature unresolved problems applying DL 19 were eligible be read from start finish out 2878 initially accessed. To provide practitioners, policymakers, researchers useful information, we range previous goals, approaches used, contributions those studies. Furthermore, considering numerous as they help preparedness control, structured overview current scientific trends open issues field. provides thorough state-of-the-art routing currently use, well their limits potential future developments, making it an invaluable resource practitioners tool multidisciplinary research.

Language: Английский

---

Brain-GCN-Net: Graph-Convolutional Neural Network for brain tumor identification

Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 180, P. 108971 - 108971

Published: Aug. 5, 2024

Language: Английский

---

SUPER-COUGH: A Super Learner-based ensemble machine learning method for detecting disease on cough acoustic signals

Biomedical Signal Processing and Control, Journal Year: 2024, Volume and Issue: 93, P. 106165 - 106165

Published: Feb. 28, 2024

Language: Английский

---

Artificial Intelligence in Healthcare: Balancing Innovation, Ethics, and Human Rights Protection

Journal of Digital Technologies and Law, Journal Year: 2025, Volume and Issue: 3(1), P. 143 - 180

Published: March 27, 2025

Objective : to identify key ethical, legal and social challenges related the use of artificial intelligence in healthcare; develop recommendations for creating adaptive mechanisms that can ensure a balance between innovation, ethical regulation protection fundamental human rights. Methods multidimensional methodological approach was implemented, integrating classical analysis methods with modern tools comparative jurisprudence. The study covers both digital technologies medical field in-depth implications using healthcare. Such an integrated provides comprehensive understanding issues well-grounded conclusions about development prospects this area. Results has revealed number serious problems These include data bias, nontransparent complex algorithms, privacy violation risks. undermine public confidence exacerbate inequalities access health services. authors conclude integration into healthcare should take account rights, such as non-discrimination, comply standards. Scientific novelty work proposes effective reduce risks maximize potential under crises. Special attention is paid regulatory measures, impact assessment provided by Artificial Intelligence Act. measures play role identifying minimizing associated high-risk systems, ensuring compliance standards Practical significance were developed, support democratic norms respond promptly emerging proposed allow achieving crisis management This helps build systems their sustained positive on

Language: Английский

---

Ultrasound-based AI for COVID-19 detection: a comprehensive review of public and private lung ultrasound datasets and studies

Multimedia Tools and Applications, Journal Year: 2025, Volume and Issue: unknown

Published: April 5, 2025

Language: Английский

---

A tree-based explainable AI model for early detection of Covid-19 using physiological data

BMC Medical Informatics and Decision Making, Journal Year: 2024, Volume and Issue: 24(1)

Published: June 24, 2024

Abstract With the outbreak of COVID-19 in 2020, countries worldwide faced significant concerns and challenges. Various studies have emerged utilizing Artificial Intelligence (AI) Data Science techniques for disease detection. Although cases declined, there are still deaths around world. Therefore, early detection before onset symptoms has become crucial reducing its extensive impact. Fortunately, wearable devices such as smartwatches proven to be valuable sources physiological data, including Heart Rate (HR) sleep quality, enabling inflammatory diseases. In this study, we utilize an already-existing dataset that includes individual step counts heart rate data predict probability infection symptoms. We train three main model architectures: Gradient Boosting classifier (GB), CatBoost trees, TabNet analyze compare their respective performances. also add interpretability layer our best-performing model, which clarifies prediction results allows a detailed assessment effectiveness. Moreover, created private by gathering from Fitbit guarantee reliability avoid bias. The identical set models was then applied using same pre-trained models, were documented. Using tree-based method, outperformed previous with accuracy 85% on publicly available dataset. Furthermore, produced 81% when You will find source code link: https://github.com/OpenUAE-LAB/Covid-19-detection-using-Wearable-data.git .

Language: Английский

---

Multi-source deep feature fusion for medical image analysis

Multidimensional Systems and Signal Processing, Journal Year: 2024, Volume and Issue: 36(1)

Published: Dec. 10, 2024

Language: Английский

---

Multi-Level Training and Testing of CNN Models in Diagnosing Multi-Center COVID-19 and Pneumonia X-ray Images

Applied Sciences, Journal Year: 2023, Volume and Issue: 13(18), P. 10270 - 10270

Published: Sept. 13, 2023

This study aimed to address three questions in AI-assisted COVID-19 diagnostic systems: (1) How does a CNN model trained on one dataset perform test datasets from disparate medical centers? (2) What accuracy gains can be achieved by enriching the training with new images? (3) learned features elucidate classification results, and how do they vary among different models? To achieve these aims, four models—AlexNet, ResNet-50, MobileNet, VGG-19—were five rounds incrementally adding images baseline set comprising 11,538 chest X-ray images. In each round, models were tested decreasing levels of image similarity. Notably, all showed performance drops when containing outlier or sourced other clinics. Round 1, 95.2~99.2% was for Level 1 testing (i.e., same clinic but apart only), 94.7~98.3% 2 an external similar). However, drastically decreased 3 rotation deformation), mean sensitivity plummeting 99% 36%. For 4 another clinic), 97% 86%, 67%. Rounds 3, 25% 50% improved average Level-3 15% 23% 56% 71% 83%). 5, increased Level-4 81% 92% 95%, respectively. Among models, ResNet-50 demonstrated most robust across five-round training/testing phases, while VGG-19 persistently underperformed. Heatmaps intermediate activation visual correlations pneumonia manifestations insufficient explicitly explain classification. heatmaps at shed light progression models’ learning behavior.

Language: Английский

---

Transparent and trustworthy interpretation of COVID-19 features in chest X-rays using explainable AI

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

Published: July 17, 2024

Language: Английский

---