Xgboost and Lightgbm Driven Multiclass Pneumonia Classification with Hybrid Vgg Feature Fusion
Year: 2025
Type: article
Abstract: Pneumonia is a serious lung infection that affects millions of people worldwide and is a leading cause of death among children and older adults. Early detection is crucial because timely diagnosis allows doctors to provide proper treatment and reduce health complications. Chest X-ray imaging is widely used for pneumonia detection, but manual analysis of these images can be slow and prone to errors. To address this, deep learning models have been developed; however, single models often fail to capture enough detailed features from the images, affecting overall accuracy. In this project, we employ advanced machine learning classifiers like XGBoost and LightGBM, which can handle complex feature patterns and are expected to boost accuracy. To extract complementary features from X-ray images, we propose a hybrid deep learning model that combines VGG16 and VGG19 to create a stronger feature representation by merging the outputs of the models. The features extracted by the deep learning model are used as input to the classifiers. The proposed system will perform multi-class classification, distinguishing between Normal, Viral Pneumonia, and Bacterial Pneumonia. It is expected that this hybrid approach will provide higher accuracy and reliability compared to using individual models, offering an efficient and scalable solution for pneumonia diagnosis.
Language: English
Topic: COVID-19 diagnosis using AI
Subfield: Radiology, Nuclear Medicine and Imaging
Field: Medicine
Domain: Health Sciences
Open Access status: diamond
OpenAlex ID: W7217464802
