Exponentiating pixel values for data augmentation to improve deep learning image classification in chest X-rays

Abstract

A previous study reported that exponentiating pixel values of a medical can be used for DA through enhancing contrast of the image. However, it is still unclear whether exponentiating pixel values of CXR images can be used for DA with CNN. The aim of this study is to evaluate the effectiveness of exponentiating pixel values for DA using CNN in the task of classifying normal and abnormal CXR images. In constructing an image for DA, each pixel value of the original images was exponentiated by the exponent ranging from 1 to 10, incrementing by 0.5. We call this image as exponentiated image (EI). For each exponent (1.0, 1.5, 1.5, 2.0,..., 10.0), the CNN model was trained using the original training dataset and EI for 40 epochs. Test accuracy was calculated at the end of each epoch using the test dataset. The maximum test accuracy (MTA) among the 40 test accuracies was saved for statistical analysis. This process was repeated 50 times for each exponent (1.0, 1.5, 1.5, 2.0,..., 10.0). The mean MTA for each exponent (1.5, 1.5, 2.0,..., 10.0) was compared using Students t-test, to that of 1.0. The mean MTA when the exponent was 1.0 was 0.749 (reference). The mean MTA was higher than the reference at exponent values 4.5(MTA=0.762, p-value=0.014), 5.0(0.762, 0.019), 5.5(0.772, 2.9 x 10-5), and 6.5(0.763, 0.010). Exponentiating pixel values can be used for DA with CNN to classify normal and abnormal CXR images.