International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | A Review on Deep Learning and Image Processing Techniques for Pneumonia Detection using Chest X-Ray Images |
|---|---|
| ABSTRACT | Pneumonia remains one of the most significant contributors to global morbidity and mortality, particularly in low-resource regions where access to advanced diagnostic equipment is limited. Chest radiography is the primary modality for pneumonia diagnosis due to its low cost and wide availability; however, human interpretation of chest X-rays is highly susceptible to errors, variability, and workload pressures. In the last decade, artificial intelligence (AI) has evolved dramatically, introducing automated methods for disease detection using conventional image-processing techniques, machine learning algorithms, and deep learning architectures. This review provides a comprehensive, high-level examination of the methods, challenges, and advancements in pneumonia detection from chest radiographs. It integrates the classical approaches based on handcrafted features and segmentation with state-of-the-art deep learning models such as DenseNet121, CheXNet, ResNet, VGG, Hybrid CNNs, and the recently proposed EfficientNetV2L. We conduct an in-depth analysis of various datasets, preprocessing methods, augmentation strategies, evaluation metrics, and performance benchmarks. The review synthesizes more than 40 influential studies, emphasizing clinical relevance, model interpretability, mathematical principles, and computational considerations. The work further identifies persistent challenges—dataset imbalance, domain shift, lack of standardization, explainability gaps—and proposes future research directions, including federated learning, GAN-based augmentation, multimodal learning, and explainable AI (XAI). This paper offers a rigorous academic understanding suitable for readers, researchers, and practitioners involved in computational medical imaging and diagnostic AI systems. |
| AUTHOR | AISHWARYA KESHI, PREETI DESHMUKH |
| VOLUME | 176 |
| DOI | DOI: 10.15680/IJIRCCE.2025.1311089 |
| pdf/89_A Review on Deep Learning and Image Processing Techniques for Pneumonia Detection.pdf | |
| KEYWORDS |
