Pulmonary Image Classification with Appropriate Neural Network Selection and Ensemble Learning
Classification at a medical diagnosis is a complex process that is extremely error prone. Since medical imaging is a major contributor to the overall diagnostic process, the Chest X-ray film is the most widely used and common method of clinical examination for pulmonary nodules. However, the number of radiologists obviously cannot keep up with the outburst due to the sharp increase in the number of Infectious Diseases, which is also a major potential source of diagnostic error. The existing system using inception-v3 transfer learning model to classify pulmonary images, and augmented the data of pulmonary images, then used the fine-tuned Inception-v3 model based on transfer learning to extract features automatically, and used different classifiers (Softmax , Logistic, SVM) to classify the pulmonary images. In the proposing system the classification of Pulmonary Images and the performance can be increased by the study of appropriate neural network selection and by using ensemble learning.The ensemble technique performs better on benchmark datasets than other state-of-the-art methods.