Detecting Pneumonia from Chest X-Ray Images Using Deep Learning
Prof.S.Visalini1 , Nikitha M, Sharavani DN, Sowjanya G, Thulasi R Asst.
Dept. of ISE
The Oxford College of Engineering ,
Bengaluru-68
visalini.su1gmail.com
Abstract—Pneumonia continues to be a major worldwide health concern, and prompt treatment and better patient outcomes depend on an early and precise diagnosis. The Pneumonia diagnosis has been completely transformed by recent developments in diagnostic imaging combined with the potency of deep learning techniques. One common and potentially fatal respiratory illness is Pneumonia, which is frequently identified via chest X-ray imaging. This work proposes a method for automatically detecting the disease Pneumonia from chest X-ray pictures. It emphasizes the value of image processing techniques and describes how deep learning might improve the precision and effectiveness of Pneumonia identification. Chest X-rays and computed tomography scans are two of the imaging modalities that are frequently used to diagnose pneumonia. By the use of learning strategies and convolutional neural networks, our model performs well in recognizing pneumonia patients. High sensitivity is attained through the training remarking the specificity of the model and attaining validation using a sizable dataset of annotated chest X-ray pictures. In this research, convolutional neural networks (CNNs) and its modifications, among other cutting-edge deep learning techniques for pneumonia diagnosis, are thoroughly reviewed. Moreover, it delve into preprocessing techniques, data augmentation strategies, and transfer learning methods utilized to enhance model performance. Furthermore, it address challenges such as interpretability, model robustness, and real-world deployment, offering insights into potential solutions and future research directions. These results imply that deep learning- based methods have potential to boost the precision and efficiency of pneumonia diagnosis, which could help doctors make treatment decisions on time.
Keywords—Medical imaging, transfer learning, preprocessing techniques, deep learning, accuracy
