Visual Deep Learning Model Improvement, Comparison, and Integration: Prediction of Pneumonia Based on Chest X-Ray Images DOI Creative Commons
Ziang Niu

Highlights in Science Engineering and Technology, Journal Year: 2024, Volume and Issue: 123, P. 625 - 630

Published: Dec. 24, 2024

Using machine learning to process lung medical images can greatly improve hospital efficiency and save costs. With the increase in number of patients, demand for pneumonia pathologic recognition systems is increasing. Therefore, organic combination two great significance reduce pressure on health systems. This paper presents a deep-learning method identify predict pneumonia. Convolutional Neural Networks, ResNet, DenseNet as well improved integrated models, known normal were used training sets determine whether present. The results showed that original CNN ResNet network had best effect, F1-score reached 0.88. this these neural networks. Finally, model 0.89, which was able more accurately. provides new idea selecting, integrating, applying field.

Language: Английский

Medical Imaging-based Artificial Intelligence in Pneumonia: A Narrative Review DOI
Yanping Yang, Wenyu Xing, Yiwen Liu

et al.

Neurocomputing, Journal Year: 2025, Volume and Issue: unknown, P. 129731 - 129731

Published: Feb. 1, 2025

Language: Английский

Citations

1
EO-CNN: Equilibrium Optimization-Based hyperparameter tuning for enhanced pneumonia and COVID-19 detection using AlexNet and DarkNet19 DOI
Soner Kızıloluk, Eser Sert, Mohamed Hammad

et al.

Journal of Applied Biomedicine, Journal Year: 2024, Volume and Issue: 44(3), P. 635 - 650

Published: July 1, 2024

Language: Английский

Citations

5
Optimizing Pneumonia Identification in Chest X-Rays Using Deep Learning Pre-Trained Architecture for Image Reconstruction in Medical Imaging DOI Open Access
Rajshri C. Mahajan

International Journal of Advanced Research in Science Communication and Technology, Journal Year: 2025, Volume and Issue: unknown, P. 52 - 63

Published: April 2, 2025

The rapid accumulation of fluid in the lungs is hallmark fatal illness known as pneumonia. Therefore, it crucial to get a diagnosis and medication soon possible order stop condition from getting worse. In diagnose pneumonia, chest X-rays (CXR) are typically used. This study assesses efficacy ResNet50 other pre-trained DL models classifying X-ray images evidence proposed model achieves an accuracy 93.06%, precision 88.97%, recall 96.78%, F1-score 92.71%, surpassing MobileNet, EfficientNetB0, Xception across all performance metrics. has been further tested shown be reliable effective differentiating between normal pneumonia patients utilizing ROC curve analysis, accuracy-loss trends, confusion matrix. highlights superiority automated detection, offering promising tool for early clinical decision support. results highlight how deep learning-based methods have ability improve radiological evaluations, which turn can decrease diagnostic mistakes increase patient outcomes. research contributes developing AI-driven medical imaging solutions, facilitating more accurate scalable detection real-world healthcare settings

Language: Английский

Citations

0
Enhanced Pneumonia Detection Using Ensembled Deep Neural Networks DOI

Senthil Kumar S,

P. Martín,

S. Karthick

et al.

Journal of Machine and Computing, Journal Year: 2025, Volume and Issue: unknown, P. 1152 - 1159

Published: April 5, 2025

In order to effectively treat pneumonia, which is still a major worldwide health problem, rapid and precise diagnosis essential. This paper introduces an ensemble strategy improve pneumonia identification using chest X-ray images (CXM), utilising developments in deep learning. We propose Ensemble Deep Neural Networks (EDNN), comprising cascaded ShuffleNet Support Vector Machines (SVM), harness diverse features classification performance. The method combines the strengths of multiple models, mitigating individual weaknesses enhancing overall diagnostic accuracy. Implementation carried out Python, proposed approach achieves impressive accuracy 97.89% on benchmark datasets. Through extensive experimentation validation datasets, our demonstrates superior performance compared models existing state-of-the-art methods. Additionally, we provide insights into interpretability predictions, transparency trustworthiness automated detection systems. framework holds promise for robust reliable clinical settings, facilitating timely interventions improving patient outcomes.

Language: Английский

Citations

0
Role of Artificial Intelligence and Personalized Medicine in Enhancing HIV Management and Treatment Outcomes DOI Creative Commons

Ashok Kumar Sah,

Rabab Hassan Elshaikh, Manar G. Shalabi

et al.

Life, Journal Year: 2025, Volume and Issue: 15(5), P. 745 - 745

Published: May 6, 2025

The integration of artificial intelligence and personalized medicine is transforming HIV management by enhancing diagnostics, treatment optimization, disease monitoring. Advances in machine learning, deep neural networks, multi-omics data analysis enable precise prognostication, tailored antiretroviral therapy, early detection drug resistance. AI-driven models analyze vast genomic, proteomic, clinical datasets to refine strategies, predict progression, pre-empt therapy failures. Additionally, AI-powered diagnostic tools, including learning imaging natural language processing, improve screening accuracy, particularly resource-limited settings. Despite these innovations, challenges such as privacy, algorithmic bias, the need for validation remain. Successful AI into care requires robust regulatory frameworks, interdisciplinary collaboration, equitable technology access. This review explores both potential limitations management, emphasizing ethical implementation expanded research maximize its impact. approaches hold great promise a more personalized, efficient, effective future care.

Language: Английский

Citations

0
Pneumonia Detection in Chest X-Ray Images with Deep Learning DOI

Solène Hébert,

Zhang Yan

Lecture notes in computer science, Journal Year: 2025, Volume and Issue: unknown, P. 257 - 271

Published: Jan. 1, 2025

Language: Английский

Citations

0
Performance Review of Meta LLaMa 3.1 in Thoracic Imaging and Diagnostics DOI Creative Commons

Golnaz Lotfian,

Keyur Parekh,

Pokhraj Prakashchandra Suthar

et al.

iRadiology, Journal Year: 2025, Volume and Issue: unknown

Published: May 11, 2025

ABSTRACT Background The integration of artificial intelligence (AI) in radiology has opened new possibilities for diagnostic accuracy, with large language models (LLMs) showing potential supporting clinical decision‐making. While proprietary like ChatGPT have gained attention, open‐source alternatives such as Meta LLaMa 3.1 remain underexplored. This study aims to evaluate the accuracy thoracic imaging and discuss broader implications versus AI healthcare. Methods (8B parameter version) was tested on 126 multiple‐choice questions selected from Thoracic Imaging: A Core Review by Hobbs et al. These required no image interpretation. model’s answers were validated two board‐certified radiologists. Accuracy assessed overall across subgroups, including intensive care, pathology, anatomy. Additionally, a narrative review introduces three widely used platforms imaging: DeepLesion, ChexNet, 3D Slicer. Results achieved an 61.1%. It performed well care (90.0%) terms signs (83.3%) but showed variability lower normal anatomy basic (40.0%). Subgroup analysis revealed strengths infectious pneumonia pleural disease, notable weaknesses lung cancer vascular pathology. Conclusion demonstrates promise NLP tool diagnostics, though its performance highlights need refinement domain‐specific training. Open‐source offer transparency accessibility, while deliver consistency. Both hold value, depending context resource availability.

Language: Английский

Citations

0
An Enhanced Deep Learning Framework for Pneumonia Detection in Chest X-rays DOI
Abdullah Mohammed Rashid,

Jannatul Asma,

Krittika Barua

et al.

SN Computer Science, Journal Year: 2025, Volume and Issue: 6(5)

Published: May 15, 2025

Language: Английский

Citations

0
A novel enhancement method of X-ray image based on multi-scale adaptive fusion DOI

Guancheng Lu,

Juan Huang, Jinlai Zhang

et al.

Journal of Radiation Research and Applied Sciences, Journal Year: 2025, Volume and Issue: 18(3), P. 101579 - 101579

Published: May 20, 2025

Language: Английский

Citations

0
Patch-Level Feature Selection for Thoracic Disease Classification by Chest X-ray Images Using Information Bottleneck DOI Creative Commons
Mạnh Hùng Nguyễn

Bioengineering, Journal Year: 2024, Volume and Issue: 11(4), P. 316 - 316

Published: March 26, 2024

Chest X-ray (CXR) examination serves as a widely employed clinical test in medical diagnostics. Many studied have tried to apply artificial intelligence (AI) programs analyze CXR images. Despite numerous positive outcomes, assessing the applicability of AI models for comprehensive diagnostic support remains formidable challenge. We observed that, even when exhibit high accuracy on one dataset, their performance may deteriorate tested another. To address this issue, we propose incorporating variational information bottleneck (VIB) at patch level enhance generalizability models. The VIB introduces probabilistic model aimed approximating posterior distribution latent variables given input data, thereby enhancing model’s generalization capabilities unseen data. Unlike conventional approaches that flatten features and use re-parameterization trick sample new feature, our method applies 2D feature maps. This design allows only important pixels respond, will select patches an image. Moreover, proposed patch-level seamlessly integrates with various convolutional neural networks, offering versatile solution improve performance. Experimental results illustrate enhanced standard experiment settings. In addition, shows robust improvement training testing different datasets.

Language: Английский

Citations

3