Dataset Information

Assessment of Facial Morphologic Features in Patients With Congenital Adrenal Hyperplasia Using Deep Learning.

ABSTRACT: Importance: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. Objective:To investigate differences in facial morphologic features between patients with CAH and control individuals with use of machine learning. Design, Setting, and Participants: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. Main Outcomes and Measures: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. Results: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). Conclusions and Relevance: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.

SUBMITTER: AbdAlmageed W

PROVIDER: S-EPMC7675110 | biostudies-literature | 2020 Nov

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Assessment of Facial Morphologic Features in Patients With Congenital Adrenal Hyperplasia Using Deep Learning.

AbdAlmageed Wael W Mirzaalian Hengameh H Guo Xiao X Randolph Linda M LM Tanawattanacharoen Veeraya K VK Geffner Mitchell E ME Ross Heather M HM Kim Mimi S MS

JAMA network open 20201102 11

<h4>Importance</h4>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.<h4>Objective</h4>To investigate differences in facial morphologic features between patients with CAH and control individuals with use of machine learning.<h4>Design, se ...[more]

PMID: 33206189

Similar Datasets

Project description:IntroductionAdrenocortical hyperplasia and adrenal rest tumor (ART) formation are common in congenital adrenal hyperplasia (CAH). Although driven by excessive corticotropin, much is unknown regarding the morphology and transformation of these tissues. Our study objective was to characterize CAH-affected adrenals and ART and compare with control adrenal and gonadal tissues.Patients/methodsCAH adrenals, ART and control tissues were analyzed by histology, immunohistochemistry, and transcriptome sequencing. We investigated protein expression of the ACTH receptor (MC2R), steroidogenic (CYP11B2, CYP11B1, CYB5A) and immune (CD20, CD3, CD68) biomarkers, and delta-like 1 homolog (DLK1), a membrane bound protein broadly expressed in fetal and many endocrine cells. RNA was isolated and gene expression was analyzed by RNA sequencing (RNA-seq) followed by principle component, and unsupervised clustering analyses.ResultsBased on immunohistochemistry, CAH adrenals and ART demonstrated increased zona reticularis (ZR)-like CYB5A expression, compared to CYP11B1, and CYP11B2, markers of zona fasciculata and zona glomerulosa respectively. CYP11B2 was mostly absent in CAH adrenals and absent in ART. DLK1 was present in CAH adrenal, ART, and also control adrenal and testis, but was absent in control ovary. Increased expression of adrenocortical marker MC2R, was observed in CAH adrenals compared to control adrenal. Unlike control tissues, significant nodular lymphocytic infiltration was observed in CAH adrenals and ART, with CD20 (B-cell), CD3 (T-cell) and CD68 (macrophage/monocyte) markers of inflammation. RNA-seq data revealed co-expression of adrenal MC2R, and testis-specific INSL3, HSD17B3 in testicular ART indicating the presence of both gonadal and adrenal features, and high expression of DLK1 in ART, CAH adrenals and control adrenal. Principal component analysis indicated that the ART transcriptome was more similar to CAH adrenals and least similar to control testis tissue.ConclusionsCAH-affected adrenal glands and ART have similar expression profiles and morphology, demonstrating increased CYB5A with ZR characteristics and lymphocytic infiltration, suggesting a common origin that is similarly affected by the abnormal hormonal milieu. Immune system modulators may play a role in tumor formation of CAH.

Project description:PurposeThe purpose of this study was to analyze the choroidal sublayer morphologic features in emmetropic and myopic children using an automatic segmentation model, and to explore the relationship between choroidal sublayers and spherical equivalent refraction (SER).MethodsWe collected data on 92 healthy children (92 eyes) from the Ophthalmology Department of Peking University First Hospital. The data were allocated to three groups: emmetropia (+0.50 diopters [D] to -0.50 D), low myopia (-0.75 D to -3.00 D), and moderate myopia (-3.25 D to -5.75 D). We performed standardized optical coherence tomography (OCT) and developed a new segmentation technique to measure choroidal thickness (CT), large-vessel choroidal layer (LVCL), medium-vessel choroidal layer (MVCL), and small-vessel choroidal layer thickness (SVCL), and evaluated the choroidal vascular system (choroidal vascular volume [VV], choroidal vascular index [CVI], and choroidal vascular density [CVD]).ResultsAll choroidal sublayers (LVCL, MVCL, and SVCL) were significantly thinner in myopic than in emmetropic eyes (P < 0.05), the thinnest choroidal region being the nasal outer subfield (P < 0.05). In all choroidal regions of SVCL, a positive correlation was found between SER and thickness ratio (P < 0.001). In most subfields of MVCL, a similar correlation was found (P < 0.050), the exceptions being the two nasal subfields (0.050 < P < 0.300). In contrast, the thickness ratio of LVCL decreased in all subfields (P < 0.050). VV correlated with SER negatively in LVCL in all subfields (all P < 0.001) and most subfields in MVCL except for two temporal subfields (0.050 < P < 0.200). However, no significant correlations were found between CVI and SER in LVCL (P > 0.050) and MVCL (with the exception being the temporal inner subfield, P = 0.011).ConclusionsThickness of choroidal sublayers was reduced with higher myopic SER, whereas changes in thickness ratio varied between sublayers. No significant correlations between CVI and SER suggested that both choroidal stromal and vascular volume decreases proportionately.Translational relevanceAutomatic segmentation model will be helpful for future clinical trials to quantify choroidal sublayer morphologic features in myopia.

Dataset Information

Assessment of Facial Morphologic Features in Patients With Congenital Adrenal Hyperplasia Using Deep Learning.

Publications

Assessment of Facial Morphologic Features in Patients With Congenital Adrenal Hyperplasia Using Deep Learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets