Assessment of Facial Morphologic Features in Patients With Congenital Adrenal Hyperplasia Using Deep Learning.
Assessment of Facial Morphologic Features in Patients With Congenital Adrenal Hyperplasia Using Deep Learning.
复制标题
DOI：
10.1001/jamanetworkopen.2020.22199
复制
发表时间：
2020-11-02
影响因子：
13.8
通讯作者：
Kim MS
中科院分区：
文献类型：
--
作者：
AbdAlmageed W;Mirzaalian H;Guo X;Randolph LM;Tanawattanacharoen VK;Geffner ME;Ross HM;Kim MS
这项横断面研究评估了机器学习在基于不同面部形态特征预测先天性肾上腺皮质增生症中的应用。先天性肾上腺增生症（CAH）患者是否具有可通过深度学习区分的独特面部形态特征？在这项针对102名CAH患者和144名对照参与者的横断面研究中，深度学习方法实现了92%的受试者工作特征曲线下面积，用于从面部图像预测CAH。面部特征将CAH患者与对照组区分开来，面部区域的分析发现鼻子和上面部是最有贡献的。研究结果表明，通过深度神经网络技术分析的面部形态特征可以用作预测CAH的表型生物标志物。先天性肾上腺皮质增生（CAH）是儿童最常见的原发性肾上腺皮质功能不全，早在妊娠第七周就出现雄激素过多，继发于类固醇生成中断。尽管CAH中可见脑结构异常，但对面部形态学知之甚少。使用机器学习研究CAH患者和对照个体之间的面部形态特征差异。这项横断面研究于2017年11月至2019年12月在南加州的一家儿科三级中心进行。从临床招募年龄小于30岁的典型CAH生化诊断患者（由于21-羟化酶缺乏）和其他健康对照组，并采集面部图像。从公共面部图像数据集中选择额外的对照。主要结果是通过机器学习（线性判别分析，随机森林，深度神经网络）预测CAH。手工制作的功能和学习的表示进行了研究CAH评分预测，面部标志和区域分析的变形分析。使用6重交叉验证策略以避免过度拟合和偏倚。该研究包括来自诊所的102名CAH患者（62名[60.8%]女性;平均[SD]年龄，11.6 [7.1]岁）和59名对照（30名[50.8%]女性;平均[SD]年龄，9.0 [5.2]岁）以及来自面部数据库的85名对照（48名[60%]女性;年龄，<29岁）。通过使用深度神经网络，发现平均（SD）AUC为92%（3%），可准确预测CAH超过6倍。通过使用经典机器学习和手工制作的面部特征，在线性判别分析中获得了86%（5%）的平均（SD）AUC，在随机森林中获得了83%（3%）的AUC，用于预测CAH超过6倍。使用面部标志模板生成的变形场，组间面部特征存在偏差。区域分析和类别激活图（区域的深度学习）显示，鼻子和上面部的贡献最大（平均[SD] AUC：分别为69% [17%]和71% [13%]）。研究结果表明，CAH患者的面部形态特征是独特的，深度学习可以发现微妙的面部特征来预测CAH。面部形态作为表型生物标志物的纵向研究可能有助于扩大对CAH患者不良寿命结局的理解。
This cross-sectional study evaluates the use of machine learning for prediction of congenital adrenal hyperplasia based on distinct facial morphologic features. Do patients with congenital adrenal hyperplasia (CAH) have distinct facial morphologic features that are distinguishable by deep learning? In this cross-sectional study of 102 patients with CAH and 144 control participants, deep learning methods achieved a mean area under the receiver operating characteristic curve of 92% for predicting CAH from facial images. Facial features distinguished patients with CAH from controls, and analyses of facial regions found that the nose and upper face were most contributory. The findings suggest that facial morphologic features, as analyzed by deep neural network techniques, can be used as a phenotypic biomarker to predict CAH. Congenital adrenal hyperplasia (CAH) is the most common primary adrenal insufficiency in children, involving excess androgens secondary to disrupted steroidogenesis as early as the seventh gestational week of life. Although structural brain abnormalities are seen in CAH, little is known about facial morphology. To investigate differences in facial morphologic features between patients with CAH and control individuals with use of machine learning. This cross-sectional study was performed at a pediatric tertiary center in Southern California, from November 2017 to December 2019. Patients younger than 30 years with a biochemical diagnosis of classical CAH due to 21-hydroxylase deficiency and otherwise healthy controls were recruited from the clinic, and face images were acquired. Additional controls were selected from public face image data sets. The main outcome was prediction of CAH, as performed by machine learning (linear discriminant analysis, random forests, deep neural networks). Handcrafted features and learned representations were studied for CAH score prediction, and deformation analysis of facial landmarks and regionwise analyses were performed. A 6-fold cross-validation strategy was used to avoid overfitting and bias. The study included 102 patients with CAH (62 [60.8%] female; mean [SD] age, 11.6 [7.1] years) and 59 controls (30 [50.8%] female; mean [SD] age, 9.0 [5.2] years) from the clinic and 85 controls (48 [60%] female; age, <29 years) from face databases. With use of deep neural networks, a mean (SD) AUC of 92% (3%) was found for accurately predicting CAH over 6 folds. With use of classical machine learning and handcrafted facial features, mean (SD) AUCs of 86% (5%) in linear discriminant analysis and 83% (3%) in random forests were obtained for predicting CAH over 6 folds. There was a deviation of facial features between groups using deformation fields generated from facial landmark templates. Regionwise analysis and class activation maps (deep learning of regions) revealed that the nose and upper face were most contributory (mean [SD] AUC: 69% [17%] and 71% [13%], respectively). The findings suggest that facial morphologic features in patients with CAH is distinct and that deep learning can discover subtle facial features to predict CAH. Longitudinal study of facial morphology as a phenotypic biomarker may help expand understanding of adverse lifespan outcomes for patients with CAH.
登录
查看更多内容
影响因子：
7.9
作者：
Kesterke, Matthew J.;Raffensperger, Zachary D.;Weinberg, Seth M.
通讯作者：
Weinberg, Seth M.
影响因子：
3.7
作者：
Engberg, Hedvig;Butwicka, Agnieszka;Landen, Mikael
通讯作者：
Landen, Mikael
影响因子：
3.3
作者：
Lefevre, Carmen E.;Etchells, Peter J.;Penton-Voak, Ian S.
通讯作者：
Penton-Voak, Ian S.
影响因子：
3.7
作者：
Hines, M;Fane, BA;Brook, C
通讯作者：
Brook, C
影响因子：
5.8
作者：
Falhammar, Henrik;Butwicka, Agnieszka;Frisen, Louise
通讯作者：
Frisen, Louise