Geostatistical Simulation of Medical Images for Data Augmentation in Deep Learning

Abstract

Data augmentation, which is the process for creating alternative copies of each sample in a small training data set, is important for extracting deep-learning features for medical image classification problems. However, data augmentation has not been well explored and existing methods are heuristic. In this paper, a geostatistical simulation of images is introduced as a data augmentation approach for extracting deep-learning features from medical images show that are characterized with texture. The stochastic simulation procedure is to generate realizations of an image by modeling its spatial variability through the generation of multiple equiprobable stochastic realizations. The approach employed for the geostatistical simulation is based on the concepts of regionalized variables and kriging formulation to create multiple textural variations of medical images. The experimental results on classifying two medical-image data sets show that the use of geostatistical simulation for extracting deep-learning features with several popular pre-trained deep-learning models (AlexNet, ResNet-50, and GoogLeNet/Inception) provided better accuracy rates and more balanced results in terms of sensitivity and specificity than either with or without the implementation of conventional data augmentation. The proposed approach can be applied to other pre-trained as well as those without data pre-training for effective deep-feature extraction from medical images. The proposed application of the theory of geostatistics for medical image data augmentation in deep learning is original. The novelty of this approach can also be applied to many other types of data that are inherently textural. The geostatistical simulation opens a new door to the development of state-of-the-art artificial intelligence in feature extraction of medical images.