This Intestine Does Not Exist: Multiscale Residual Variational Autoencoder for Realistic Wireless Capsule Endoscopy Image Generation

TL;DR

This paper introduces TIDE, a multiscale residual variational autoencoder that generates highly realistic wireless capsule endoscopy images, effectively replacing real datasets for training without loss of classification accuracy.

Contribution

The novel TIDE architecture enables high-quality, diverse WCE image synthesis from limited data, surpassing GAN-based methods and fully substituting real datasets.

Findings

TIDE produces realistic and diverse WCE images.

Synthetic datasets with TIDE maintain classification performance.

Qualitative evaluations confirm medical realism of generated images.

Abstract

Medical image synthesis has emerged as a promising solution to address the limited availability of annotated medical data needed for training machine learning algorithms in the context of image-based Clinical Decision Support (CDS) systems. To this end, Generative Adversarial Networks (GANs) have been mainly applied to support the algorithm training process by generating synthetic images for data augmentation. However, in the field of Wireless Capsule Endoscopy (WCE), the limited content diversity and size of existing publicly available annotated datasets, adversely affect both the training stability and synthesis performance of GANs. Aiming to a viable solution for WCE image synthesis, a novel Variational Autoencoder architecture is proposed, namely "This Intestine Does not Exist" (TIDE). The proposed architecture comprises multiscale feature extraction convolutional blocks and residual connections, which enable the generation of high-quality and diverse datasets even with a limited number of training images. Contrary to the current approaches, which are oriented towards the augmentation of the available datasets, this study demonstrates that using TIDE, real WCE datasets can be fully substituted by artificially generated ones, without compromising classification performance. Furthermore, qualitative and user evaluation studies by experienced WCE specialists, validate from a medical viewpoint that both the normal and abnormal WCE images synthesized by TIDE are sufficiently realistic.