WG ² AN: Synthetic wound image generation using generative adversarial network

Abstract

In part due to its ability to mimic any data distribution, Generative Adversarial Network (GAN) algorithms have been successfully applied to many applications, such as data augmentation, text-to-image translation, image-to-image translation, and image inpainting. Learning from data without crafting loss functions for each application provides broader applicability of the GAN algorithm. Medical image synthesis is also another field that the GAN algorithm has great potential to assist clinician training. This paper proposes a synthetic wound image generation model based on GAN architecture to increase the quality of clinical training. The proposed model is trained on chronic wound datasets with various sizes taken from real hospital environments. Hyperparameters such as epoch count and dataset size for training tasks are studied to find optimum training conditions as well. The performance of the developed model was evaluated through a mean squared error (MSE) metric to determine the similarity between generated and actual wounds. Visual inspection is performed to examine generated wound images. The results show that the proposed synthetic wound image generation (WG 2 AN) model has great potential to be used in medical training and performs well in producing synthetic wound images with a 1000-image training dataset and 200 epochs of training.This is an open access article under the terms of the Creative Commons Attribution License, which permits use, distribution and reproduction in any medium, provided the original work is properly cited.

The Enlightening Role of Explainable Artificial Intelligence in Chronic Wound Classification

“…The ROC curve and the AUC provide a visualization related to the performance of the model on the classification task. The performance of the model could be improved with a larger training dataset [45] and fine-tuning the hyperparameters [46].…”

Generative Adversarial Network for Real‐Time Flash Drought Monitoring: A Deep Learning Study

“…Training the model with less than 400 epochs leads to an abundant amount of noise in the simulated SSI maps. When the epoch number is increased from 600 to 1,000, it potentially results in a decline in In most of the studies, GANs need a large epoch number (>100) to reach the best performance (Bird et al, 2022;Robic-Butez & Win, 2019;Sarp, Kuzlu, Pipattanasomporn, & Guler, 2021;Sarp, Kuzlu, Wilson, & Guler, 2021); while there are a few studies that reported lower epoch numbers to train their proposed GAN or use an already existing GAN for an application (Laloy et al, 2018;Li et al, 2020). Generally, there is no universal agreement on the optimal epoch number for training a GAN network.…”

Modern Design Intelligent Training Assistance Platform based on Lingnan Architectural Image Generation Algorithm

“…Early non-parametric image style transfer is a method of then analyzing style images, drawing a physical model or a mathematical statistical model according to the style, and then synthesizing the texture of the transferred image to make it more in line with the established model [1,2,3]. This method requires the establishment of complex models, which has high theoretical requirements, and each style needs to be modeled separately, which is time-consuming and laborintensive [4,5,6].…”