文献速递烧伤创面修复

卷积神经网络用于彩色图像烧伤区域分割

Convolution neural network for effective burn region segmentation of color images.
PubMed 文献 · Burns · 2020-09-12

本研究构建像素级标注的烧伤图像数据集,探索深度学习用于烧伤区域分割,提出一种使用空洞卷积和ResNet-101预训练模型的CNN方法。该方法在自建数据集上达到MCC 77.6%和准确率93.4%,在精确率、Dice系数、Jaccard指数和特异度上均优于第二优方法。像素级分割方法有望用于准确高效地估计烧伤面积和严重程度。

要点

  • 自建像素级标注烧伤图像数据集,系统评估现有语义分割技术。
  • 提出结合空洞卷积与ResNet-101的CNN,在自建数据集上MCC达77.6%、准确率达93.4%。
  • 该方法相比第二优方法在精确率、Dice、Jaccard和特异度上分别提升11.6/5.8/6.9/1.2%。

核心结论

  • 提出的CNN方法在彩色图像烧伤区域分割中表现有效,优于现有方法。
  • 像素级分割方法有望准确、高效地估计烧伤面积和严重程度。

研究设计与样本

  • 研究为方法学开发与评估,构建了像素级标注的新烧伤图像数据集。
  • 探索深度学习用于烧伤区域分割,并比较现有基于彩色图像的语义分割技术。

主要发现

  • 所提方法在自建烧伤图像数据集上达到MCC 77.6%和准确率93.4%。
  • 相比第二优性能,精确率提升11.6%、Dice相似系数提升5.8%、Jaccard指数提升6.9%、特异度提升1.2%。

关键数值与推荐

  • 所提CNN使用空洞卷积编码丰富上下文信息,并利用预训练ResNet-101提取低层和中层特征。

临床怎么用

  • 该分割方法可用于辅助估计烧伤面积和烧伤严重程度,有望提高时效性。
  • 需在自建数据集上进一步验证后考虑临床转化。

局限性

  • 研究基于自建烧伤图像数据集,未报告外部验证或多中心数据。
  • 未报告样本量、置信区间或P值等统计细节。

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

BACKGROUND: Burn injuries are one of the most severe forms of wounds and trauma across the globe. Automated burn diagnosis methods are needed to provide timely treatment to the concerned patients. Artificial intelligence is playing a vital role in developing automated tools and techniques for medical problems. However, the use of advanced AI techniques for color images based burn region segmentation is not much explored. METHOD: In this work, we explore the use of deep learning for the challenging problem of burn region segmentation. We prepared a pixel-wise labelled new burn images dataset for segmentation and investigated the efficacy of existing state-of-the-art color images based semantic image segmentation techniques. Lately, we proposed a new convolution neural network (CNN) that uses atrous convolution for encoding rich contextual information and utilizes pre-trained model ResNet-101 for better extraction of low-level and middle-level layer features. RESULTS: The proposed approach achieves the state-of-the-art performance on the prepared burn image dataset with 77.6% of Mathews correlation coefficient (MCC) and 93.4% of accuracy. The improvement of 11.6/5.8/6.9/1.2% is observed in precision, Dice similarity coefficient, Jaccard index and specificity, in comparison to the second best performance. CONCLUSION: In this work, we propose a CNN based novel method for performing burn-region segmentation in color images and evaluate it using newly prepared Burn Images dataset. The experimental results illustrate its effectiveness in comparison to existing approaches. Further, the proposed pixel-level segmentation method could be useful in estimating the burn surface area and burn severity in an accurate and time efficient manner.

来源:Burns,查看原文。版权归原作者所有。

引用

  1. Chauhan J, Goyal P. Convolution neural network for effective burn region segmentation of color images. Burns. 2020. PMID: 33158632. doi:10.1016/j.burns.2020.08.016

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。