Simple U-net Based Synthetic Polyp Image Generation: Polyp to Negative and Negative to Polyp

TL;DR

This paper introduces a deep learning framework using a simple conditional GAN to generate synthetic polyp images from negative images, aiding medical data augmentation for improved detection and segmentation.

Contribution

A novel method that converts polyp images to negative images and back, enabling controllable synthetic polyp generation for training without extra labeling.

Findings

Synthetic images improve detection and segmentation performance.

The framework generates diverse polyps with controllable features.

Adding synthetic images enhances model training results.

Abstract

Synthetic polyp generation is a good alternative to overcome the privacy problem of medical data and the lack of various polyp samples. In this study, we propose a deep learning-based polyp image generation framework that generates synthetic polyp images that are similar to real ones. We suggest a framework that converts a given polyp image into a negative image (image without a polyp) using a simple conditional GAN architecture and then converts the negative image into a new-looking polyp image using the same network. In addition, by using the controllable polyp masks, polyps with various characteristics can be generated from one input condition. The generated polyp images can be used directly as training images for polyp detection and segmentation without additional labeling. To quantitatively assess the quality of generated synthetic polyps, we use public polyp image and video datasets combined with the generated synthetic images to examine the performance improvement of several detection and segmentation models. Experimental results show that we obtain performance gains when the generated polyp images are added to the training set.