文献速递烧伤创面修复

基于Burn-GAN的烧伤图像分割

Burn Images Segmentation Based on Burn-GAN.
PubMed 文献 · J Burn Care Res · 2021-01-01

本文提出Burn-GAN烧伤图像生成框架,包含基于Style-GAN生成烧伤创面、颜色调整无缝克隆融合、三维真实场景模拟及坐标变换获取标注数据集四部分。使用NSLR2损失与CASC时分割网络效果最佳,精度达90.75%,像素准确率96.88%,Dice系数从84.5提升至89.3%。该框架可自动生成大量烧伤图像数据集,提高分割精度并节省标注时间。

要点

  • Burn-GAN可自动生成带标注的烧伤图像数据集,节省人工标注时间。
  • 采用NSLR2损失与CASC时分割网络精度90.75%、PA 96.88%、DC 89.3%。
  • 生成数据可提升分割网络精度,辅助%TBSA计算与治疗方案制定。

核心结论

  • Burn-GAN烧伤数据生成框架能提升分割网络精度,自动分割烧伤图像较传统方法精度更高且耗时更少。

研究设计与样本

  • 提出Burn-GAN烧伤图像生成框架,包含基于Style-GAN生成创面、CASC融合、三维场景模拟及坐标变换获取标注数据集四部分。
  • 使用precision、Pixel Accuracy(PA)和Dice Coefficient(DC)评估框架。

主要发现

  • 采用NSLR2与CASC时分割网络获得最佳结果。
  • 框架精度达90.75%,PA达96.88%,DC从84.5提升至89.3%。

临床怎么用

  • 可利用Burn-GAN自动生成带标注烧伤图像数据集,用于训练分割网络以提高烧伤创面分割精度。
  • 准确分割创面有助于提高%TBSA计算精度,辅助确定治疗方案。

局限性

  • 原文指出因相关图像训练数据收集困难,现有深度学习方法常无法达到精细分割。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

Burn injuries are severe problems for human. Accurate segmentation for burn wounds in patient surface can improve the calculation precision of %TBSA (total burn surface area), which is helpful in determining treatment plan. Recently, deep learning methods have been used to automatically segment wounds. However, owing to the difficulty of collecting relevant images as training data, those methods cannot often achieve fine segmentation. A burn image-generating framework is proposed in this paper to generate burn image datasets with annotations automatically. Those datasets can be used to increase segmentation accuracy and save the time of annotating. This paper brings forward an advanced burn image generation framework called Burn-GAN. The framework consists of four parts: Generating burn wounds based on the mainstream Style-GAN network; Fusing wounds with human skins by Color Adjusted Seamless Cloning (CASC); Simulating real burn scene in three-dimensional space; Acquiring annotated dataset through three-dimensional and local burn coordinates transformation. Using this framework, a large variety of burn image datasets can be obtained. Finally, standard metrics like precision, Pixel Accuracy (PA) and Dice Coefficient (DC) were utilized to assess the framework. With nonsaturating loss with R2 regularization (NSLR2) and CASC, the segmentation network gains the best results. The framework achieved precision at 90.75%, PA at 96.88% and improved the DC from 84.5 to 89.3%. A burn data-generating framework have been built to improve the segmentation network, which can automatically segment burn images with higher accuracy and less time than traditional methods.

来源:J Burn Care Res,查看原文。版权归原作者所有。

引用

  1. Dai F, Zhang D, Su K, et al. Burn Images Segmentation Based on Burn-GAN. J Burn Care Res. 2021. PMID: 33336696. doi:10.1093/jbcr/iraa208

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。