Capturing Variabilities from Computed Tomography Images with Generative Adversarial Networks
This addresses data scarcity in medical imaging for researchers and practitioners, but it is incremental as it applies existing GAN methods to CT images without major methodological breakthroughs.
The paper tackled the problem of data insufficiency in medical imaging for deep learning by proposing a novel unsupervised data-driven approach using Generative Adversarial Networks (GANs) to generate 2D Computed Tomography (CT) images, resulting in visually realistic images that capture global and local variabilities for data augmentation.
With the advent of Deep Learning (DL) techniques, especially Generative Adversarial Networks (GANs), data augmentation and generation are quickly evolving domains that have raised much interest recently. However, the DL techniques are data demanding and since, medical data is not easily accessible, they suffer from data insufficiency. To deal with this limitation, different data augmentation techniques are used. Here, we propose a novel unsupervised data-driven approach for data augmentation that can generate 2D Computed Tomography (CT) images using a simple GAN. The generated CT images have good global and local features of a real CT image and can be used to augment the training datasets for effective learning. In this proof-of-concept study, we show that our proposed solution using GANs is able to capture some of the global and local CT variabilities. Our network is able to generate visually realistic CT images and we aim to further enhance its output by scaling it to a higher resolution and potentially from 2D to 3D.