深度卷积神经网络用于烧伤深度的非时间依赖性预测
本研究应用四种预训练深度卷积神经网络(VGG-16、GoogleNet、ResNet-50、ResNet-101),基于TiVi相机采集的烧伤早期彩色图像,对四类烧伤深度(含正常皮肤和背景)进行自动预测。ResNet-101取得最佳10折交叉验证结果,平均、最低和最高准确率分别为81.66%、72.06%和88.06%;四类烧伤深度的平均准确率、敏感性和特异性分别为90.54%、74.35%和94.25%。准确率与创面愈合后的临床诊断进行了比较,提示AI在烧伤深度预测方面具有应用前景。
要点
- ResNet-101在四类烧伤深度分类中10折交叉验证平均准确率为81.66%。
- 四类烧伤深度平均准确性90.54%、敏感性74.35%、特异性94.25%。
- AI预测准确率与创面愈合后临床诊断进行了比较。
核心结论
- AI用于烧伤深度预测很有前景,可作为辅助临床决策和初始治疗的有用工具。
研究设计与样本
- 应用四种预训练深度卷积神经网络(VGG-16、GoogleNet、ResNet-50、ResNet-101),对TiVi相机采集的烧伤早期彩色图像进行训练和测试,图像包括四类烧伤深度、正常皮肤和背景。
主要发现
- ResNet-101最佳10折交叉验证的平均、最低和最高准确率分别为81.66%、72.06%和88.06%。
- 四类烧伤深度的平均准确率、敏感性和特异性分别为90.54%、74.35%和94.25%。
- 准确率与创面愈合后获得的临床诊断进行了比较。
临床怎么用
- AI预测烧伤深度可帮助指导临床决策和烧伤创面的初始治疗。
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
We present in this paper the application of deep convolutional neural networks (CNNs), which is a state-of-the-art artificial intelligence (AI) approach in machine learning, for automated time-independent prediction of burn depth. Color images of four types of burn depth injured in first few days, including normal skin and background, acquired by a TiVi camera were trained and tested with four pretrained deep CNNs: VGG-16, GoogleNet, ResNet-50, and ResNet-101. In the end, the best 10-fold cross-validation results obtained from ResNet-101 with an average, minimum, and maximum accuracy are 81.66, 72.06, and 88.06%, respectively; and the average accuracy, sensitivity, and specificity for the four different types of burn depth are 90.54, 74.35, and 94.25%, respectively. The accuracy was compared with the clinical diagnosis obtained after the wound had healed. Hence, application of AI is very promising for prediction of burn depth and, therefore, can be a useful tool to help in guiding clinical decision and initial treatment of burn wounds.
引用
- Cirillo MD, Mirdell R, Sjöberg F, et al. Time-Independent Prediction of Burn Depth Using Deep Convolutional Neural Networks. J Burn Care Res. 2019. PMID: 31187119. doi:10.1093/jbcr/irz103
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。