Image pre-processing: enhance the performance of medical image classification using various data augmentation technique

Abstract

The medical image classification system is an important subject in the field of biotechnology. Here, the network is trained with a large amount of computation to obtain high accuracy rate [1]. Chest X-rays images (CXRs) are broadly used in identifying the abnormalities in the chest area. Automatic detecting techniques are used in most of the diagnosing process, to improve the accuracy rate of abnormality detection. The main objective of this work is to prove the range of error, loss and accuracy by using the convolution neural networks (CNNs) model for detecting tuberculosis in the chest images. Tremendous progress has been made in deep learning models for classifying medical images.