多光谱成像人工智能算法评估烧伤创面深度的改进:扩展概念验证研究
该多中心前瞻性概念验证研究利用多光谱成像传感器采集烧伤创面图像,转换为像素级数据后训练十种卷积神经网络算法。研究纳入100名成人和24名儿童受试者,共采集1037张图像和161份活检,最佳算法曲线下面积为0.95,且伤后时间作为协变量具有显著性。
要点
- 最佳CNN算法AUC为0.95,准确率89.29%,敏感度90.51%,特异度87.22%。
- 伤后时间是显著协变量(P < .0001),伤后1-2天准确率最低88.5%,3-4天最高93.5%。
- 学习曲线预测未来训练研究纳入374名受试者后准确率可达94.04%。
核心结论
- 确定了最佳CNN架构及伤后时间作为协变量的重要性,为后续算法训练和验证研究的设计与把握度提供依据。
研究设计与样本
- 三个烧伤中心前瞻性将受试者分为可能21天内非手术愈合组和需手术组,两组均从入组至出院/切除每日进行多光谱成像。
- 非手术组在21天时评估,手术组进行活检;由烧伤专家组成的「Truthing Panel」创建每处创面的「ground truth」并转换为像素级数据。
- 使用像素级数据训练十种CNN(8种独特深度学习算法和2种集成深度学习算法)。
主要发现
- 从100名成人和24名儿童受试者中收集了1037张MSI图像和161份活检。
- 最有效的CNN算法曲线下面积为0.95(准确率=89.29%,敏感度=90.51%,特异度=87.22%),协变量「伤后时间」具有显著性(P < .0001)。
- 伤后1-2天准确率最低为88.5%,伤后3-4天最高为93.5%。
- CNN学习曲线预测,未来训练研究纳入374名受试者后准确率可达94.04%。
局限性
- 原文未述局限性
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: With the advent of convolutional neural networks (CNNs), artificial intelligence is now applicable to visual fields. We used multispectral imaging (MSI) sensors capable of detecting wavelengths outside visible spectra to image burn wounds. The output was converted to pixel-level data and analyzed by an array of CNNs to inform the development of a deep learning (DL) algorithm for burn assessment. METHODS: Three burn centers prospectively grouped consenting subjects into those with wounds likely to heal nonoperatively by 21 days, or those benefiting from surgery. Both groups underwent MSI sensor imaging at enrollment and once daily until discharge/excision. Nonoperative subjects were evaluated at 21 days, while operative subjects underwent biopsies. A "Truthing Panel" of burn experts created a "ground truth" for each wound that was converted to pixel-level data and used to train ten CNNs (8 unique DL algorithms and 2 ensemble DL algorithms). RESULTS: 1037 MSI images and 161 biopsies were collected from 100 adult and 24 pediatric subjects. The most effective CNN algorithm exhibited an area under the curve of 0.95 (accuracy = 89.29%, sensitivity = 90.51%, and specificity = 87.22%) with the covariate "time-since-injury" found to be significant (P < .0001). Accuracy was lowest, 88.5%, at 1-2 days after injury and highest, 93.5%, at 3-4 days. The CNN's learning curve predicted an accuracy of 94.04% after enrolling 374 subjects in a future training study. CONCLUSIONS: An optimal CNN architecture and the importance of "time-since-injury" as a covariate were identified, informing the design/powering of upcoming algorithm training and validation studies.
引用
- Carter JE, Shupp JW, Phelan HA, et al. Refinement of an Artificial Intelligence Algorithm for Enhanced Burn Wound Depth Assessment Using Multispectral Imaging: An Expanded Proof of Concept Study. J Burn Care Res. 2025. PMID: 40452490. doi:10.1093/jbcr/iraf057
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。