Intra- and inter-rater reliability of digital image analysis for skin color measurement.
Intra- and inter-rater reliability of digital image analysis for skin color measurement.
复制标题
用于肤色测量的数字图像分析的内部和评估者间可靠性。
DOI：
10.1111/srt.12072
复制
发表时间：
2013
期刊：
影响因子：
--
通讯作者：
Fargo,Jamison
中科院分区：
文献类型：
--
作者：
Sommers,Marilyn;Beacham,Barbara;Baker,Rachel;Fargo,Jamison
背景我们通过专家和新手分析师之间的数字图像颜色分析来确定数据的内部和评估者间可靠性。方法训练后，专家和新手独立分析 210 张随机排序的图像。两位分析师根据图像文件的类型使用 Adobe®Photoshop lasso 或颜色采样器工具。使用相机软件中的 Pictocolor® 进行色彩校正后，他们记录了所有皮肤部位的 L*a*b*（L*= 亮/暗；a*= 红/绿；b*= 黄/蓝）颜色值。我们使用一系列单向类内相关系数 (ICC) 计算了解剖区域、颜色值 (L*、a*、b*) 和技术（套索、颜色采样器）内评估者内和评估者间的一致性。结果评估者内一致性的 ICC 结果显示每个评估者对于套索技术具有高水平的内部一致性可靠性（ICC ≥ 0.99） 颜色采样器技术的一致性程度稍低但可以接受（专家 ICC = 0.91，新手 ICC = 0.81）。皮肤 L*、皮肤 b* 和阴唇 L* 值达到最高一致性水平（ICC ≥ 0.92），皮肤 a*、阴唇 b* 和阴道壁 b* 最低（ICC ≥ 0.64）。 结论 通过培训和使用详细的标准协议，新手分析师的数据可以与专家分析师的数据实现高度一致性。
BackgroundWe determined the intra‐ and inter‐rater reliability of data from digital image color analysis between an expert and novice analyst.MethodsFollowing training, the expert and novice independently analyzed 210 randomly ordered images. Both analysts used Adobe®Photoshop lasso or color sampler tools based on the type of image file. After color correction with Pictocolor®in camera software, they recorded L*a*b* (L*=light/dark; a*=red/green; b*=yellow/blue) color values for all skin sites. We computed intra‐rater and inter‐rater agreement within anatomical region, color value (L*, a*, b*), and technique (lasso, color sampler) using a series of one‐way intra‐class correlation coefficients (ICCs).ResultsResults of ICCs for intra‐rater agreement showed high levels of internal consistency reliability within each rater for the lasso technique (ICC ≥ 0.99) and somewhat lower, yet acceptable, level of agreement for the color sampler technique (ICC = 0.91 for expert, ICC = 0.81 for novice). Skin L*, skin b*, and labia L* values reached the highest level of agreement (ICC ≥ 0.92) and skin a*, labia b*, and vaginal wall b* were the lowest (ICC ≥ 0.64).ConclusionData from novice analysts can achieve high levels of agreement with data from expert analysts with training and the use of a detailed, standard protocol.