人工智能引导的图像评估与当前烧伤评估方法的比较
该研究开发基于图像的人工智能系统,用1684张移动设备拍摄的不同深度烧伤图像训练卷积神经网络,并改造为边界注意力映射算法。回顾性验证144份病历,CNN-BAM烧伤面积分割与激光多普勒成像(LDI)相比准确率91.6%、敏感度78.2%、特异度93.4%,严重度预测与LDI愈合潜力 extrapolation 的 agreement 为66%。作者认为CNN-BAM嵌入移动设备时,烧伤深度检测准确性与LDI相当且更经济可及。
要点
- 临床评估对部分厚度烧伤深度的准确率为67%,目前仍是最一致的实践标准。
- CNN-BAM烧伤面积分割与LDI相比准确率91.6%、敏感度78.2%、特异度93.4%。
- CNN-BAM严重度预测与LDI愈合潜力 extrapolation 的 agreement 为66%。
核心结论
- CNN-BAM算法嵌入移动设备时,烧伤深度检测准确性与LDI相当,且应用更经济、更可及。
研究设计与样本
- 回顾性研究,检索144份包含临床评估、烧伤部位、总体表面积和LDI评估的患者病历进行验证。
- 使用1684张移动设备拍摄的不同深度烧伤图像训练改良EfficientNet架构,创建卷积神经网络(CNN),并改造为边界注意力映射(BAM)算法。
主要发现
- CNN采用4级烧伤严重度分类,准确率达85%(微/宏平均受试者工作特征评分)。
- CNN-BAM系统能以高置信度将烧伤与周围组织区分。
- CNN-BAM烧伤面积分割与LDI方法相比,准确率91.6%、敏感度78.2%、特异度93.4%。
- CNN-BAM严重度预测与LDI愈合潜力 extrapolation 的 agreement 为66%。
关键数值与推荐
- 临床评估对部分厚度烧伤深度的准确率为67%。
- CNN 4级烧伤严重度分类准确率为85%(微/宏平均受试者工作特征评分)。
- CNN-BAM烧伤面积分割准确率91.6%、敏感度78.2%、特异度93.4%(与LDI比较)。
- CNN-BAM严重度预测与LDI愈合潜力 extrapolation 的 agreement 为66%。
临床怎么用
- 作者认为CNN-BAM算法可作为热损伤管理中的分诊工具,嵌入移动设备时烧伤深度检测准确性与LDI相当且更经济可及。
局限性
- 原文未报告局限性
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
Appropriate identification of burn depth and size is paramount. Despite the development of burn depth assessment aids [eg, laser Doppler imaging (LDI)], clinical assessment, which assesses partial-thickness burn depth with 67% accuracy, currently remains the most consistent standard of practice. We sought to develop an image-based artificial intelligence system that predicts burn severity and wound margins for use as a triaging tool in thermal injury management. Modified EfficientNet architecture trained by 1684 mobile-device-captured images of different burn depths was previously used to create a convoluted neural network (CNN). The CNN was modified to a novel boundary attention mapping (BAM) algorithm using elements of saliency mapping, which was used to recognize the boundaries of burns. For validation, 144 patient charts that included clinical assessment, burn location, total body surface area, and LDI assessment were retrieved for a retrospective study. The clinical images underwent CNN-BAM assessment and were directly compared with the LDI assessment. CNN using a 4-level burn severity classification achieved an accuracy of 85% (micro/macro-averaged receiver operating characteristic scores). The CNN-BAM system can successfully highlight burns from surrounding tissue with high confidence. CNN-BAM burn area segmentations attained a 91.6% accuracy, 78.2% sensitivity, and 93.4% specificity, when compared to LDI methodology. Results comparing the CNN-BAM outputs to clinical and LDI assessments have shown a high degree of correlation between the CNN-BAM burn severity predictions to those extrapolated from LDI healing potential (66% agreement). CNN-BAM algorithm gives equivalent burn-depth detection accuracy as LDI with a more economical and accessible application when embedded in a mobile device.
引用
- Lee JJ, Abdolahnejad M, Morzycki A, et al. Comparing Artificial Intelligence Guided Image Assessment to Current Methods of Burn Assessment. J Burn Care Res. 2025. PMID: 38918900. doi:10.1093/jbcr/irae121
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。