| _version_ | 1866901915066957824 |
|---|---|
| author | Jincy Lukose ,Anita Ann Joseph,Meenakshy BR,Nevin Siby,Rosaine P Lal |
| author_facet | Jincy Lukose ,Anita Ann Joseph,Meenakshy BR,Nevin Siby,Rosaine P Lal |
| contents | <p><strong><em><span lang="EN-US">Abstract</span></em></strong><strong><span lang="EN-US">—Pneumonia<span> </span>is<span> </span>a<span> </span>life-threatening<span> </span>respiratory<span> </span>infection that<span> </span>requires<span> </span>rapid<span> </span>and<span> </span>accurate<span> </span>diagnosis<span> </span>for<span> </span>effective<span> </span>treatment. In this study, we develop a deep learning-based pneumonia detection and classification model using chest X-ray images, distinguishing between normal, bacterial pneumonia, and viral pneumonia cases. The dataset, sourced from publicly available medical image repositories, is preprocessed and augmented to improve generalization. A Convolutional Neural Network (CNN) model is trained using optimized hyperparameters, with tech- niques such as batch normalization, dropout regularization, and early<span> </span>stopping<span> </span>to<span> </span>enhance<span> </span>accuracy<span> </span>and<span> </span>prevent<span> </span>overfitting. The model is evaluated on a separate test set, achieving a promising accuracy in detecting pneumonia subtypes. Further, performance metrics such as precision, recall, F1-score, and confusion matrices are analyzed. This research demonstrates the potential<span> </span>of<span> </span>deep<span> </span>learning<span> </span>in<span> </span>medical<span> </span>image<span> </span>analysis,<span> </span>offering a<span> </span>scalable<span> </span>and<span> </span>automated<span> </span>approach<span> </span>to<span> </span>assist<span> </span>radiologists<span> </span>in early pneumonia diagnosis. Future work includes leveraging transfer<span> </span>learning<span> </span>with<span> </span>ResNet50<span> </span>and<span> </span>ensemble<span> </span>models<span> </span>for<span> </span>further accuracy improvements.</span></strong></p> <p><strong><span lang="EN-US">Keywords:<span> </span>Pneumonia<span> </span>Detection,<span> </span>Deep<span> </span>Learning,<span> </span>Chest<span> </span>X-ray, CNN, Medical Image Classification, Machine Learning</span></strong></p> |
| format | Recurso digital |
| id | zenodo_https___doi_org_10_5281_zenodo_15532832 |
| institution | Zenodo |
| language | |
| publishDate | 2025 |
| publisher | Zenodo |
| record_format | zenodo |
| spellingShingle | ENHANCED PNEUMONIA DETECTION IN CHEST X-RAYS USING ATTENTION AND FNMS Jincy Lukose ,Anita Ann Joseph,Meenakshy BR,Nevin Siby,Rosaine P Lal <p><strong><em><span lang="EN-US">Abstract</span></em></strong><strong><span lang="EN-US">—Pneumonia<span> </span>is<span> </span>a<span> </span>life-threatening<span> </span>respiratory<span> </span>infection that<span> </span>requires<span> </span>rapid<span> </span>and<span> </span>accurate<span> </span>diagnosis<span> </span>for<span> </span>effective<span> </span>treatment. In this study, we develop a deep learning-based pneumonia detection and classification model using chest X-ray images, distinguishing between normal, bacterial pneumonia, and viral pneumonia cases. The dataset, sourced from publicly available medical image repositories, is preprocessed and augmented to improve generalization. A Convolutional Neural Network (CNN) model is trained using optimized hyperparameters, with tech- niques such as batch normalization, dropout regularization, and early<span> </span>stopping<span> </span>to<span> </span>enhance<span> </span>accuracy<span> </span>and<span> </span>prevent<span> </span>overfitting. The model is evaluated on a separate test set, achieving a promising accuracy in detecting pneumonia subtypes. Further, performance metrics such as precision, recall, F1-score, and confusion matrices are analyzed. This research demonstrates the potential<span> </span>of<span> </span>deep<span> </span>learning<span> </span>in<span> </span>medical<span> </span>image<span> </span>analysis,<span> </span>offering a<span> </span>scalable<span> </span>and<span> </span>automated<span> </span>approach<span> </span>to<span> </span>assist<span> </span>radiologists<span> </span>in early pneumonia diagnosis. Future work includes leveraging transfer<span> </span>learning<span> </span>with<span> </span>ResNet50<span> </span>and<span> </span>ensemble<span> </span>models<span> </span>for<span> </span>further accuracy improvements.</span></strong></p> <p><strong><span lang="EN-US">Keywords:<span> </span>Pneumonia<span> </span>Detection,<span> </span>Deep<span> </span>Learning,<span> </span>Chest<span> </span>X-ray, CNN, Medical Image Classification, Machine Learning</span></strong></p> |
| title | ENHANCED PNEUMONIA DETECTION IN CHEST X-RAYS USING ATTENTION AND FNMS |
| url | https://doi.org/10.5281/zenodo.15532832 |