Enhancing Pneumonia Diagnosis with Convolutional Neural Networks: A Comprehensive Evaluation
- Title
- Enhancing Pneumonia Diagnosis with Convolutional Neural Networks: A Comprehensive Evaluation
- Creator
- Tanni, Nikita; Elappila, Manu; George, Tessa; Premjith, Nithin
- Description
- Pneumonia, a significant health concern globally, presents unique challenges in diagnosis and treatment due to its diverse ethology and impact on respiratory function. The potential of augmentation techniques and Convolutional Neural Networks, for automated pneumonia detection is explored in this study. Employing a transfer learning approach with VGG16, DenseNet, and our proposed model achieves outstanding accuracy (95%) and robust performance metrics. The research explores augmentation techniques to enhance the precision and accuracy of the model, emphasizing the importance of data augmentation in improving classification accuracy. A comparative analysis with related models highlights advancements in automated pneumonia detection, showcasing the efficacy of our proposed model. The models ability to correctly identify pneumonia from chest X-ray pictures is demonstrated by the results, suggesting that medical image analysis could benefit from practical implementation of this model. Future directions include expanding the dataset, exploring alternative architectures, and integrating explanation techniques to enhance model interpretability. This research contributes to the advancement of artificial intelligence in healthcare, offering a promising approach for accurate and efficient pneumonia diagnosis, thus addressing critical challenges in respiratory medicine. The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.
- Source
- Lecture Notes in Networks and Systems;Volume;5589 LNNS;pp.597-609
- Date
- 01-01-2025
- Publisher
- Springer Science and Business Media Deutschland GmbH
- Subject
- Accuracy; Advance healthcare; Automated classification; Convolutional Neural Networks (CNNs); DenseNet; Machine learning; VGG16
- Coverage
- Tanni N., CHRIST University, Bengaluru, India; Elappila M., CHRIST University, Bengaluru, India; George T., CHRIST University, Bengaluru, India; Premjith N., CHRIST University, Bengaluru, India
- Rights
- Restricted Access; Hardcopy may be available in the library
- Relation
- ISSN: 23673370; ISBN: 978-981961686-2;
- Format
- online
- Language
- English
- Type
- Conference paper
Collection
Citation
Tanni, Nikita; Elappila, Manu; George, Tessa; Premjith, Nithin, “Enhancing Pneumonia Diagnosis with Convolutional Neural Networks: A Comprehensive Evaluation,” CHRIST (Deemed To Be University) Institutional Repository, accessed June 18, 2026, https://archives.christuniversity.in/items/show/25469.