Pneumonia Classification Using Sparse Auxiliary Pneumonia Detection Network
Main Article Content
Abstract
Pneumonia is a serious pulmonary condition that impacts millions globally. An early analysis of pneumonia is essential for effective treatment and improved survival rates. This has created an urgent requirement for rapid detection and classification methods for pneumonia to facilitate efficient treatment and prompt recovery of affected individuals. The advancement and cost-effectiveness of chest X-ray technology, coupled with the progress in artificial intelligence, have led to increased global interest in pneumonia identification utilising deep learning and chest X-ray imaging. This study examines the use of Sparse Auxiliary Pneumonia Detection Networks (SAPD-net) for classifying pneumonia through chest X-ray images. Consequently, SAN is an efficient system developed to address the challenge of adapting to recent discrimination in pneumonia images. The objective is to develop an interpretable evaluation framework for pneumonia infection classification, utilising deep classification and transfer learning techniques.
The proposed method's experimental results are validated using the benchmark chest X-rays database. The simulation results indicated the superior performance of the proposed method compared to alternative techniques. The results indicate that deep features yield precise and reliable attributes for pneumonia detection. The proposed method enables radiologists to evaluate pneumonia patients and provide a swift diagnosis.