Ability of artificial intelligence to identify self-reported race in chest x-ray using pixel intensity counts
Ability of artificial intelligence to identify self-reported race in chest x-ray using pixel intensity counts
复制标题
人工智能能够使用像素强度计数识别胸部 X 光检查中自我报告的种族
DOI：
10.1117/1.jmi.10.6.061106
复制
发表时间：
2023
影响因子：
2.4
通讯作者：
Tignanelli, Christopher
中科院分区：
文献类型：
--
作者：
Burns, John Lee;Zaiman, Zachary;Vanschaik, Jack;Luo, Gaoxiang;Peng, Le;Price, Brandon;Mathias, Garric;Mittal, Vijay;Sagane, Akshay;Tignanelli, Christopher
先前的研究表明，卷积神经网络可以使用胸部、手部和脊柱的X光片、胸部计算机断层扫描和乳房X光片来预测自我报告的种族。我们寻求对揭示X射线图像中种族的机制的理解，调查种族不是使用X射线图像中的物理结构预测的，而是嵌入在灰度像素强度中的可能性。方法回顾2021年全年，来自美国3个学术健康中心和MIMIC-CXR的298，827张AP/PA胸部X射线图像，按自我报告的种族标记，在这项研究中使用。通过对每个灰度值的数量求和并缩放到每图像百分比（PPI）来删除图像结构。使用Bonferroni多重比较调整和类平衡MANOVA的多变量方差分析（MANOVA）对所得数据进行测试。构建机器学习（ML）前馈网络（FFN）和决策树以仅使用灰度值计数来预测种族（二进制黑色或白色和二进制黑色或其他）。按照体重指数、年龄、性别、性别、患者类型、扫描仪品牌/型号、暴露和千伏峰值设置进行分层分析，以研究这些因素对种族预测的影响，遵循相同的方法。方差分析（F7.38，P < 0.0001）和平衡方差分析（F2.02，P < 0.0001）。最佳FFN性能是有限的[受试者工作特征下的面积（AUROC）为69.18%]。梯度提升树预测自我报告的种族使用灰度PPI（AUROC 77.24%）。ConclusionsWithin胸部X射线，像素强度值计数单独是统计学上显着的指标和足够的患者自我报告的种族ML分类任务。
PurposePrior studies show convolutional neural networks predicting self-reported race using x-rays of chest, hand and spine, chest computed tomography, and mammogram. We seek an understanding of the mechanism that reveals race within x-ray images, investigating the possibility that race is not predicted using the physical structure in x-ray images but is embedded in the grayscale pixel intensities.ApproachRetrospective full year 2021, 298,827 AP/PA chest x-ray images from 3 academic health centers across the United States and MIMIC-CXR, labeled by self-reported race, were used in this study. The image structure is removed by summing the number of each grayscale value and scaling to percent per image (PPI). The resulting data are tested using multivariate analysis of variance (MANOVA) with Bonferroni multiple-comparison adjustment and class-balanced MANOVA. Machine learning (ML) feed-forward networks (FFN) and decision trees were built to predict race (binary Black or White and binary Black or other) using only grayscale value counts. Stratified analysis by body mass index, age, sex, gender, patient type, make/model of scanner, exposure, and kilovoltage peak setting was run to study the impact of these factors on race prediction following the same methodology.ResultsMANOVA rejects the null hypothesis that classes are the same with 95% confidence (F7.38,P< 0.0001) and balanced MANOVA (F2.02,P< 0.0001). The best FFN performance is limited [area under the receiver operating characteristic (AUROC) of 69.18%]. Gradient boosted trees predict self-reported race using grayscale PPI (AUROC 77.24%).ConclusionsWithin chest x-rays, pixel intensity value counts alone are statistically significant indicators and enough for ML classification tasks of patient self-reported race.
击中目标：减少人工智能系统中的偏见。
DOI：
10.1148/ryai.220171
发表时间：
2022
期刊：
Radiology. Artificial intelligence
影响因子：
--
作者：
C. E. Kahn
通讯作者：
C. E. Kahn
影响因子：
82.9
作者：
Pierson, Emma;Cutler, David M.;Obermeyer, Ziad
通讯作者：
Obermeyer, Ziad