Evaluation of Deep Convolutional Generative Adversarial Networks for Data Augmentation of Chest X-ray Images

Abstract

Medical image datasets are usually imbalanced due to the high costs of obtaining the data and time-consuming annotations. Training a deep neural network model on such datasets to accurately classify the medical condition does not yield the desired results as they often over-fit the majority class samples’ data. Data augmentation is often performed on the training data to address the issue by position augmentation techniques such as scaling, cropping, flipping, padding, rotation, translation, affine transformation, and color augmentation techniques such as brightness, contrast, saturation, and hue to increase the dataset sizes. Radiologists generally use chest X-rays for the diagnosis of pneumonia. Due to patient privacy concerns, access to such data is often protected. In this study, we performed data augmentation on the Chest X-ray dataset to generate artificial chest X-ray images of the under-represented class through generative modeling techniques such as the Deep Convolutional Generative Adversarial Network (DCGAN). With just 1341 chest X-ray images labeled as Normal, artificial samples were created by retaining similar characteristics to the original data with this technique. Evaluating the model resulted in a Fréchet Distance of Inception (FID) score of 1.289. We further show the superior performance of a CNN classifier trained on the DCGAN augmented dataset.

Data Augmentation using Generative Adversarial Network with Enhanced Deep Convolutional Neural Network for Pneumonia Chest X-ray Images

“…They also discussed that data augmentation of liver lesion data could improve the performance of liver lesion medical image classification by using CNN. Kora Venu et al [22] proposed a generative modeling method that includes DCGAN to produce fake CXR images from an under-represented class from the Chest X-ray dataset (DCGAN). This method constructed artificial samples by keeping identical properties to the actual data.…”

Generation of High-Precision Ground Penetrating Radar Images Using Improved Least Square Generative Adversarial Networks

“…GAN can generate artificial images by using two adversarial networks. A GAN architecture is composed of two component parts, including a generation model G and a discriminant model D (Figure 1) [34]. The G model is responsible for producing spurious data whereas the D model is in charge of distinguishing the authenticity of the produced data.…”

CXR-IRGen: An Integrated Vision and Language Model for the Generation of Clinically Accurate Chest X-Ray Image-Report Pairs

“…For this purpose, deep generative models are utilized to augment the CXR image dataset. Previous studies have demonstrated the generation of CXR images using deep generative models, including generative adversarial networks (GANs) and diffusion models [2,3,5,6,19,21,27,31,43]. CXR images are typically annotated with radiology reports detailing clinical observations made by radiologists, as depicted in Fig.…”

“…The generated CXR reports exhibit promising performance in terms of both natural language metrics and clinical efficacy metrics. In recent years, Generative Adversarial Networks (GANs) are frequently adopted for generating CXR images, and promising results were attained [2,3,19,21,27,31,39,46]. Nonetheless, GANs exhibit problems including mode collapse and training instabilities, which increase training difficulties, and degrade generation quality.…”