Enhanced Pneumonia Detection from Chest X-rays Using Machine Learning and Deep Neural Architectures - Research paper overview

Aug 3, 2026

Upload by Skyler

Pneumonia remains a major global health threat, especially for vulnerable groups such as infants and the elderly, and chest X-ray interpretation is difficult due to subtle symptom presentation and variability in image assessment. This study applies modern machine learning to chest X-ray images using a Kaggle dataset with 5,000+ annotated samples, evaluating deep convolutional neural networks and ensemble strategies. Results show Fuzzy opponent histogram filter with Logistic model trees achieving 96.97% accuracy, while Lenet with LMT reaches 95.85%, supporting faster, more reliable clinical decision-making.

LanguageEnglish

CategoryHealthcare

FormatPDF

Pages10

Reading Time25 min

AccessFree to download

Introduction

Clinical relevance of pneumonia and diagnostic challenges

Role of chest X-ray and limitations of manual interpretation

Motivation for AI and deep learning in medical imaging

Method and Models (from abstract)

Enhanced Pneumonia Detection from Chest X-rays Using Machine Learning and Deep Neural Architectures Kamal Upreti 1†, Anju Singh2 , Divakar Singh3 , Preety Shoran 1 , Uma Shankar4 , Meenakshi Yadav5 and Rituraj Jain6 1Department of Computer Science, CHRIST (Deemed to be University), Delhi NCR Campus, Ghaziabad, India 2Department of Computer Science and Engineering, Lakshmi Narain College of Technology, Kalchuri Nagar, Raisen Road, Bhopal, Madhya Pradesh, India 3Department of Computer Science and Engineering, university Institute of Technology, Barkatullah University, Bhopal, Madhya Pradesh, India 4Department of Management, Faculty of Management and Social Sciences, Qaiwan International University, Sulaimanyah, Kurdistan, Iraq 5Department of Information Technology, Galgotias College of Engineering and Technology, Greater Noida, India 6Department of Information Technology, Marwadi University, Rajkot, Gujarat, India Abstract—Pneumonia is a major worldwide health concern, particularly for vulnerable groups such as babies and the elderly. Despite advances in medical imaging, diagnosing pneumonia using a chest X-ray remains difficult, due to the subtle presentation of symptoms and the variety in picture interpretation. This study utilizes modern machine learning can improve the accuracy and speed of diagnosing pneumonia using chest X-ray images. Utilizing a comprehensive dataset from the Kaggle online repository, consisting of over 5,000 annotated images, we evaluate the efficacy of various machine learning models including deep convolutional neural networks (CNN) and ensemble learning techniques. Our findings indicate that models like the Fuzzy opponent histogram filter combined with Logistic model trees (LMT) achieved the highest accuracy at 96.97%, while the deep learning-based Lenet (CNN) with LMT closely followed at 95.85%. The study aims to improve diagnostic precision, reduce interpretation discrepancies, and facilitate faster clinical decision-making by identifying the most effective machine learning approaches for real-world applications in healthcare settings. Index Terms—Artificial intelligence, Chest X-rays, Fuzzy opponent histogram filter, Machine learning, Pneumonia. ARO-The Scientific Journal ofKoya University Vol. XIII, No. 1 (2025), Article ID: ARO.12174 . 10 pages DOI: 10. 14500/aro.12174 Received: 05 April 2025; Accepted: 18 May 2025 Regular research paper; Published: 10 June 2025 †Corresponding author’s e-mail: kamal.upreti@christuniversity.in Copyright © 2025 Kamal Upreti, Anju Singh, Divakar Singh, Preety Shoran, Uma Shankar, Meenakshi Yadav and Rituraj Jain. This isan open-access article distributed under the Creative Commons Attribution License (CC BY-NC-SA 4.0) . I. Introduction Pneumonia is a major health concern across the world, accounting for the majority of illnesses and deaths, particularly among young children and the elderly. Chest X-ray imaging is commonly used for diagnosis; however, it can be difficult to interpret, especially if the symptoms are mild. Recent breakthroughs demonstrated that the application of machine learning algorithms considerably enhances the capacity of chest X-ray imaging to identify pneumonia; hence, it accelerates the diagnostic process and leads to dramatically better patient outcomes (Singh, et al., 2024) . Another kind of pneumonia is acinetobacter baumannii, which is notable for its resistance to strong antibiotics such as carbapenems and colistin. This resistance complicates therapy, highlighting the need for more effective therapeutic procedures. Although utilizing a mixture of antibiotics has been somewhat successful, the outcomes vary and are not always constant (Shein, et al., 2024) . Pneumonia is a serious respiratory disease that can take many different forms, including bacterial pneumonia, virus-induced pneumonia, mycoplasma-caused pneumonia, and others that maybe parasitic or fungal in origin. This illness can also

FAQs

Why is pneumonia diagnosis from chest X-rays challenging?

Pneumonia symptoms can be subtle, and interpretation varies across clinicians, making consistent diagnosis difficult from X-ray images.

Which dataset and model types are used for pneumonia detection?

The study uses a Kaggle dataset with 5,000+ annotated chest X-ray images and evaluates deep convolutional neural networks and ensemble learning techniques.

What performances did the best models achieve?

Fuzzy opponent histogram filter combined with Logistic model trees achieved the highest accuracy of 96.97%, while Lenet (CNN) with LMT closely followed at 95.85%.

Aug 3, 2026

Upload by Skyler