Classification of Pneumonia Using Deep Convolutional Neural Network

Pneumonia is considered a serious and fatal disease worldwide. In fact, pneumonia can be an individual's life-endangering if not treated promptly by drugs. Therefore, the early detection of enhances chances recovery, which helps reduce mortality. It worth noting that X-rays are one most important diagnostic tools for diagnosing pneumonia. Chest X-ray widely used in diagnosis many lung diseases (such as: Breast Cancer, Pneumonia, Tuberculosis, etc.), due to lower costs. Indeed, diagnoses subjective reasons example appearance unclear chest images or confused with other diseases. Hence, enhancing level guide clinicians, computer-aided systems will needed. this paper, we put forward develop structure classify from using Convolutional Neural Network (CNN) residual network architecture. Clearly, determine person infected not, two well-known CNN pre-trained models (ResNet50 ResNet101), multi-class Support Vector Machine (SVM) transfer learning extract features. Thus, proposed framework takes image size 224 x pixels as input gives final prediction Normal Pneumonia. The experimental results showed classification proved effective, accuracy range 97% 98.3%. More precisely, extraction features Resnet50 + SVM Transfer Learning methods achieve highest performance Accuracy 98.3% 97.8%, respectively.