Center for Biomedical Engineering, Indian Institute of Technology Ropar, Punjab, India.
Center for Biomedical Engineering, Indian Institute of Technology Ropar, Punjab, India; Computer Science and Engineering, Indian Institute of Technology Ropar, Punjab, India.
Burns. 2020 Sep;46(6):1407-1423. doi: 10.1016/j.burns.2020.03.007. Epub 2020 May 4.
Burns are a serious health problem leading to several thousand deaths annually, and despite the growth of science and technology, automated burns diagnosis still remains a major challenge. Researchers have been exploring visual images-based automated approaches for burn diagnosis. Noting that the impact of a burn on a particular body part can be related to the skin thickness factor, we propose a deep convolutional neural network based body part-specific burns severity assessment model (BPBSAM).
Considering skin anatomy, BPBSAM estimates burn severity using body part-specific support vector machines trained with CNN features extracted from burnt body part images. Thus BPBSAM first identifies the body part of the burn images using a convolutional neural network in training of which the challenge of limited availability of burnt body part images is successfully addressed by using available larger-size datasets of non-burn images of different body parts considered (face, hand, back, and inner forearm). We prepared a rich labelled burn images datasets: BI & UBI and trained several deep learning models with existing models as pipeline for body part classification and feature extraction for severity estimation.
The proposed novel BPBSAM method classified the severity of burn from color images of burn injury with an overall average F1 score of 77.8% and accuracy of 84.85% for the test BI dataset and 87.2% and 91.53% for the UBI dataset, respectively. For burn images body part classification, the average accuracy of around 93% is achieved, and for burn severity assessment, the proposed BPBSAM outperformed the generic method in terms of overall average accuracy by 10.61%, 4.55%, and 3.03% with pipelines ResNet50, VGG16, and VGG19, respectively.
The main contributions of this work along with burn images labelled datasets creation is that the proposed customized body part-specific burn severity assessment model can significantly improve the performance in spite of having small burn images dataset. This highly innovative customized body part-specific approach could also be used to deal with the burn region segmentation problem. Moreover, fine tuning on pre-trained non-burn body part images network has proven to be robust and reliable.
烧伤是一种严重的健康问题，每年导致数千人死亡，尽管科学技术不断发展，自动化烧伤诊断仍然是一个主要挑战。研究人员一直在探索基于视觉图像的自动化烧伤诊断方法。鉴于烧伤对特定身体部位的影响可能与皮肤厚度因素有关，我们提出了一种基于深度卷积神经网络的特定身体部位烧伤严重程度评估模型（BPBSAM）。
考虑到皮肤解剖结构，BPBSAM 使用基于 CNN 特征的特定身体部位支持向量机来评估烧伤严重程度，这些特征是从烧伤身体部位图像中提取的。因此，BPBSAM 首先使用卷积神经网络识别烧伤图像的身体部位，在训练中，通过使用考虑到不同身体部位（面部、手部、背部和内前臂）的更大尺寸非烧伤图像的现有较大数据集，成功解决了烧伤身体部位图像可用性有限的挑战。我们准备了一个丰富的标记烧伤图像数据集：BI 和 UBI，并使用现有的模型作为管道，对几种深度学习模型进行了训练，用于身体部位分类和严重程度估计的特征提取。
所提出的新颖的 BPBSAM 方法从烧伤损伤的彩色图像中分类烧伤严重程度，对于测试 BI 数据集，总体平均 F1 得分为 77.8%，准确率为 84.85%，对于 UBI 数据集，分别为 87.2%和 91.53%。对于烧伤图像的身体部位分类，平均准确率达到 93%左右，对于烧伤严重程度评估，与通用方法相比，所提出的 BPBSAM 在总体平均准确率方面分别提高了 10.61%、4.55%和 3.03%，使用的管道分别为 ResNet50、VGG16 和 VGG19。
这项工作的主要贡献是创建了标记的烧伤图像数据集，提出的定制特定身体部位的烧伤严重程度评估模型可以显著提高性能，尽管烧伤图像数据集较小。这种高度创新的定制特定身体部位的方法也可用于解决烧伤区域分割问题。此外，在预训练的非烧伤身体部位图像网络上进行微调已被证明是稳健可靠的。
