DEEP LEARNING BASED MUTLI CLASS DISEASES CLASSIFICATION FROM CHEST, X-RAY IMAGES

Abstract

Chest X-rays are indispensable for diagnosing a wide range of diseases,
play a pivotal role in diagnosing various diseases, but traditional methods relying on visual interpretation can
introduce subjectivity and inefficiency. For instance, diagnosing pneumonia, especially among pediatric
patients, poses significant challenges. but these methods can be subjective and inefficient. According to a study
published in the British Medical Journal (BMJ), misinterpretation rates for chest X-rays range from 2% to 20%,
depending on the condition and the experience of the radiologist. In response to these challenges, this study
proposes a novel approach utilizing Convolutional Neural Networks (CNNs) to enhance diagnostic accuracy.
CNNs have demonstrated remarkable capabilities in image recognition tasks, as evidenced by their widespread
use in various fields, including medical imaging. By harnessing the power of CNNs, this method aims to
mitigate the impact of human subjectivity and improve the efficiency of disease diagnosis. This has the potential
to revolutionize pulmonary disease diagnosis, leading to faster treatment initiation and better patient outcomes.
Furthermore, the scalability of CNN-based approaches allows for broader implementation across healthcare
facilities, thereby benefiting a larger population. This represents a significant advancement in the field of
radiology and has the potential to optimize healthcare resources and improve overall healthcare delivery.