scholarly journals Efficiency of Computer-Aided Facial Phenotyping (DeepGestalt) in Individuals With and Without a Genetic Syndrome: Diagnostic Accuracy Study

10.2196/19263 ◽  
2020 ◽  
Vol 22 (10) ◽  
pp. e19263
Author(s):  
Jean Tori Pantel ◽  
Nurulhuda Hajjir ◽  
Magdalena Danyel ◽  
Jonas Elsner ◽  
Angela Teresa Abad-Perez ◽  
...  
Keyword(s):  
High Sensitivity ◽  
Diagnostic Process ◽  
Support Vector ◽  
Genetic Syndromes ◽  
Convenience Sample ◽  
Genetic Syndrome ◽  
Computer Aided ◽  
Critical Interpretation ◽  
Dysmorphic Syndrome ◽  
Facial Images

Background Collectively, an estimated 5% of the population have a genetic disease. Many of them feature characteristics that can be detected by facial phenotyping. Face2Gene CLINIC is an online app for facial phenotyping of patients with genetic syndromes. DeepGestalt, the neural network driving Face2Gene, automatically prioritizes syndrome suggestions based on ordinary patient photographs, potentially improving the diagnostic process. Hitherto, studies on DeepGestalt’s quality highlighted its sensitivity in syndromic patients. However, determining the accuracy of a diagnostic methodology also requires testing of negative controls. Objective The aim of this study was to evaluate DeepGestalt's accuracy with photos of individuals with and without a genetic syndrome. Moreover, we aimed to propose a machine learning–based framework for the automated differentiation of DeepGestalt’s output on such images. Methods Frontal facial images of individuals with a diagnosis of a genetic syndrome (established clinically or molecularly) from a convenience sample were reanalyzed. Each photo was matched by age, sex, and ethnicity to a picture featuring an individual without a genetic syndrome. Absence of a facial gestalt suggestive of a genetic syndrome was determined by physicians working in medical genetics. Photos were selected from online reports or were taken by us for the purpose of this study. Facial phenotype was analyzed by DeepGestalt version 19.1.7, accessed via Face2Gene CLINIC. Furthermore, we designed linear support vector machines (SVMs) using Python 3.7 to automatically differentiate between the 2 classes of photographs based on DeepGestalt's result lists. Results We included photos of 323 patients diagnosed with 17 different genetic syndromes and matched those with an equal number of facial images without a genetic syndrome, analyzing a total of 646 pictures. We confirm DeepGestalt’s high sensitivity (top 10 sensitivity: 295/323, 91%). DeepGestalt’s syndrome suggestions in individuals without a craniofacially dysmorphic syndrome followed a nonrandom distribution. A total of 17 syndromes appeared in the top 30 suggestions of more than 50% of nondysmorphic images. DeepGestalt’s top scores differed between the syndromic and control images (area under the receiver operating characteristic [AUROC] curve 0.72, 95% CI 0.68-0.76; P<.001). A linear SVM running on DeepGestalt’s result vectors showed stronger differences (AUROC 0.89, 95% CI 0.87-0.92; P<.001). Conclusions DeepGestalt fairly separates images of individuals with and without a genetic syndrome. This separation can be significantly improved by SVMs running on top of DeepGestalt, thus supporting the diagnostic process of patients with a genetic syndrome. Our findings facilitate the critical interpretation of DeepGestalt’s results and may help enhance it and similar computer-aided facial phenotyping tools.

scholarly journals Efficiency of Computer-Aided Facial Phenotyping (DeepGestalt) in Individuals With and Without a Genetic Syndrome: Diagnostic Accuracy Study (Preprint)

2020 ◽  
Author(s):  
Jean Tori Pantel ◽  
Nurulhuda Hajjir ◽  
Magdalena Danyel ◽  
Jonas Elsner ◽  
Angela Teresa Abad-Perez ◽  
...  
Keyword(s):  
High Sensitivity ◽  
Diagnostic Process ◽  
Support Vector ◽  
Genetic Syndromes ◽  
Convenience Sample ◽  
Genetic Syndrome ◽  
Computer Aided ◽  
Critical Interpretation ◽  
Dysmorphic Syndrome ◽  
Facial Images

BACKGROUND Collectively, an estimated 5% of the population have a genetic disease. Many of them feature characteristics that can be detected by facial phenotyping. Face2Gene CLINIC is an online app for facial phenotyping of patients with genetic syndromes. DeepGestalt, the neural network driving Face2Gene, automatically prioritizes syndrome suggestions based on ordinary patient photographs, potentially improving the diagnostic process. Hitherto, studies on DeepGestalt’s quality highlighted its sensitivity in syndromic patients. However, determining the accuracy of a diagnostic methodology also requires testing of negative controls. OBJECTIVE The aim of this study was to evaluate DeepGestalt's accuracy with photos of individuals with and without a genetic syndrome. Moreover, we aimed to propose a machine learning–based framework for the automated differentiation of DeepGestalt’s output on such images. METHODS Frontal facial images of individuals with a diagnosis of a genetic syndrome (established clinically or molecularly) from a convenience sample were reanalyzed. Each photo was matched by age, sex, and ethnicity to a picture featuring an individual without a genetic syndrome. Absence of a facial gestalt suggestive of a genetic syndrome was determined by physicians working in medical genetics. Photos were selected from online reports or were taken by us for the purpose of this study. Facial phenotype was analyzed by DeepGestalt version 19.1.7, accessed via Face2Gene CLINIC. Furthermore, we designed linear support vector machines (SVMs) using Python 3.7 to automatically differentiate between the 2 classes of photographs based on DeepGestalt's result lists. RESULTS We included photos of 323 patients diagnosed with 17 different genetic syndromes and matched those with an equal number of facial images without a genetic syndrome, analyzing a total of 646 pictures. We confirm DeepGestalt’s high sensitivity (top 10 sensitivity: 295/323, 91%). DeepGestalt’s syndrome suggestions in individuals without a craniofacially dysmorphic syndrome followed a nonrandom distribution. A total of 17 syndromes appeared in the top 30 suggestions of more than 50% of nondysmorphic images. DeepGestalt’s top scores differed between the syndromic and control images (area under the receiver operating characteristic [AUROC] curve 0.72, 95% CI 0.68-0.76; <i>P</i>&lt;.001). A linear SVM running on DeepGestalt’s result vectors showed stronger differences (AUROC 0.89, 95% CI 0.87-0.92; <i>P</i>&lt;.001). CONCLUSIONS DeepGestalt fairly separates images of individuals with and without a genetic syndrome. This separation can be significantly improved by SVMs running on top of DeepGestalt, thus supporting the diagnostic process of patients with a genetic syndrome. Our findings facilitate the critical interpretation of DeepGestalt’s results and may help enhance it and similar computer-aided facial phenotyping tools.

scholarly journals Autoimmunity and Genetic Syndromes: A Focus on Down Syndrome

Genes ◽  
2021 ◽  
Vol 12 (2) ◽  
pp. 268
Author(s):  
Marta Ferrari ◽  
Stefano Stagi
Keyword(s):  
Down Syndrome ◽  
Autoimmune Diseases ◽  
Normal Population ◽  
Underlying Mechanism ◽  
Short Review ◽  
Immune Dysregulation ◽  
Infectious Complications ◽  
Genetic Syndromes ◽  
Genetic Syndrome

Within immune system-related diseases, autoimmunity has always represented a field of great interest, although many aspects remain poorly understood even today. Genetic syndromes associated with immunity disorders are common and represent an interesting model for a better understanding of the underlying mechanism of autoimmunity predisposition. Among these conditions, Down syndrome (DS) certainly deserves special attention as it represents the most common genetic syndrome associated with immune dysregulation, involving both innate and adaptive immunity. Autoimmunity represents a well-known complication of DS: it is estimated that people affected by this disease present a risk four to six times higher than the normal population to develop autoimmune diseases such as celiac disease, type 1 diabetes mellitus, and hypo- or hyperthyroidism. Several factors have been considered as possible etiology, including genetic and epigenetic modifications and immune dysregulation. In times in which the life expectancy of people with DS has been extremely prolonged, thanks to improvements in the diagnosis and treatment of congenital heart disease and infectious complications, knowledge of the mechanisms and proper management of autoimmune diseases within this syndrome has become essential. In this short review, we aim to report the current literature regarding the genetic, immune, and environmental factors that have been proposed as the possible underlying mechanism of autoimmunity in individuals with DS, with the intent to provide insight for a comprehensive understanding of these diseases in genetic syndromes.

Convolutional Neural Networks in Computer-Aided Diagnosis of Colorectal Polyps and Cancer: A Review

2021 ◽  
Author(s):  
Kamyab Keshtkar
Keyword(s):  
Colorectal Cancer ◽  
Neural Networks ◽  
Deep Learning ◽  
Computer Aided Diagnosis ◽  
Colorectal Polyps ◽  
Support Vector ◽  
Training Process ◽  
Computer Aided ◽  
Conventional Models ◽  
Aided Diagnosis

As a relatively high percentage of adenoma polyps are missed, a computer-aided diagnosis (CAD) tool based on deep learning can aid the endoscopist in diagnosing colorectal polyps or colorectal cancer in order to decrease polyps missing rate and prevent colorectal cancer mortality. Convolutional Neural Network (CNN) is a deep learning method and has achieved better results in detecting and segmenting specific objects in images in the last decade than conventional models such as regression, support vector machines or artificial neural networks. In recent years, based on the studies in medical imaging criteria, CNN models have acquired promising results in detecting masses and lesions in various body organs, including colorectal polyps. In this review, the structure and architecture of CNN models and how colonoscopy images are processed as input and converted to the output are explained in detail. In most primary studies conducted in the colorectal polyp detection and classification field, the CNN model has been regarded as a black box since the calculations performed at different layers in the model training process have not been clarified precisely. Furthermore, I discuss the differences between the CNN and conventional models, inspect how to train the CNN model for diagnosing colorectal polyps or cancer, and evaluate model performance after the training process.

scholarly journals Microduplication of 15q13.3 and Microdeletion of 18q21.32 in a Patient with Moyamoya Syndrome

2018 ◽  
Vol 19 (11) ◽  
pp. 3675 ◽  
Author(s):  
Francesca Luisa Sciacca ◽  
Ambra Rizzo ◽  
Gloria Bedini ◽  
Fioravante Capone ◽  
Vincenzo Di Lazzaro ◽  
...  
Keyword(s):  
Internal Carotid ◽  
Neurofibromatosis Type ◽  
Genetic Syndromes ◽  
Genetic Syndrome ◽  
Susceptibility Factors ◽  
The Relationship ◽  
Genic Mutation ◽  
Internal Carotid Arteries ◽  
Cerebral Angiopathy

Moyamoya angiopathy (MA) is a cerebrovascular disease determining a progressive stenosis of the terminal part of the internal carotid arteries (ICAs) and their proximal branches and the compensatory development of abnormal “moyamoya” vessels. MA occurs as an isolated cerebral angiopathy (so-called moyamoya disease) or in association with various conditions (moyamoya syndromes) including several heritable conditions such as Down syndrome, neurofibromatosis type 1 and other genomic defects. Although the mechanism that links MA to these genetic syndromes is still unclear, it is believed that the involved genes may contribute to the disease susceptibility. Herein, we describe the case of a 43 years old woman with bilateral MA and peculiar facial characteristics, having a 484-kb microduplication of the chromosomal region 15q13.3 and a previously unreported 786 kb microdeletion in 18q21.32. This patient may have a newly-recognized genetic syndrome associated with MA. Although the relationship between these genetic variants and MA is unclear, our report would contribute to widening the genetic scenario of MA, in which not only genic mutation, but also genome unbalances are possible candidate susceptibility factors.

Exerting Cost-Sensitive and Feature Creation Algorithms for Coronary Artery Disease Diagnosis

2012 ◽  
Vol 3 (1) ◽  
pp. 59-79 ◽  
Author(s):  
Roohallah Alizadehsani ◽  
Mohammad Javad Hosseini ◽  
Reihane Boghrati ◽  
Asma Ghandeharioun ◽  
Fahime Khozeimeh ◽  
...  
Keyword(s):  
Coronary Artery Disease ◽  
Coronary Artery ◽  
High Sensitivity ◽  
Disease Diagnosis ◽  
Major Type ◽  
Support Vector ◽  
K Nearest Neighbors ◽  
Diagnostic Modality ◽  
Data Mining Algorithms ◽  
Artery Disease

One of the main causes of death the world over is the family of cardiovascular diseases, of which coronary artery disease (CAD) is a major type. Angiography is the principal diagnostic modality for the stenosis of heart arteries; however, it leads to high complications and costs. The present study conducted data-mining algorithms on the Z-Alizadeh Sani dataset, so as to investigate rule based and feature based classifiers and their comparison, and the reason for the effectiveness of a preprocessing algorithm on a dataset. Misclassification of diseased patients has more side effects than that of healthy ones. To this end, this paper employs 10-fold cross-validation on cost-sensitive algorithms along with base classifiers of Naïve Bayes, Sequential Minimal Optimization (SMO), K-Nearest Neighbors (KNN), Support Vector Machine (SVM), and C4.5 and the results show that the SMO algorithm yielded very high sensitivity (97.22%) and accuracy (92.09%) rates.

Computer-Aided Detection of Polyps in CT Colonography by Means of Feature Selection and Massive-Training Support Vector Regression

2012 ◽  
pp. 178-201
Author(s):  
Jian-Wu Xu ◽  
Kenji Suzuki
Keyword(s):  
Feature Selection ◽  
Support Vector Regression ◽  
Ct Colonography ◽  
Feature Selection Method ◽  
Selection Method ◽  
Support Vector ◽  
Computer Aided Detection ◽  
Training Time ◽  
Computer Aided ◽  
Wilks Lambda

One of the major challenges in current Computer-Aided Detection (CADe) of polyps in CT Colonography (CTC) is to improve the specificity without sacrificing the sensitivity. If a large number of False Positive (FP) detections of polyps are produced by the scheme, radiologists might lose their confidence in the use of CADe. In this chapter, the authors used a nonlinear regression model operating on image voxels and a nonlinear classification model with extracted image features based on Support Vector Machines (SVMs). They investigated the feasibility of a Support Vector Regression (SVR) in the massive-training framework, and the authors developed a Massive-Training SVR (MTSVR) in order to reduce the long training time associated with the Massive-Training Artificial Neural Network (MTANN) for reduction of FPs in CADe of polyps in CTC. In addition, the authors proposed a feature selection method directly coupled with an SVM classifier to maximize the CADe system performance. They compared the proposed feature selection method with the conventional stepwise feature selection based on Wilks’ lambda with a linear discriminant analysis classifier. The FP reduction system based on the proposed feature selection method was able to achieve a 96.0% by-polyp sensitivity with an FP rate of 4.1 per patient. The performance is better than that of the stepwise feature selection based on Wilks’ lambda (which yielded the same sensitivity with 18.0 FPs/patient). To test the performance of the proposed MTSVR, the authors compared it with the original MTANN in the distinction between actual polyps and various types of FPs in terms of the training time reduction and FP reduction performance. The authors’ CTC database consisted of 240 CTC datasets obtained from 120 patients in the supine and prone positions. With MTSVR, they reduced the training time by a factor of 190, while achieving a performance (by-polyp sensitivity of 94.7% with 2.5 FPs/patient) comparable to that of the original MTANN (which has the same sensitivity with 2.6 FPs/patient).

scholarly journals Developing a Task Switching Training Game for Children With a Rare Genetic Syndrome Linked to Intellectual Disability

2019 ◽  
Vol 50 (2) ◽  
pp. 160-179 ◽  
Author(s):  
Nigel Robb ◽  
Annalu Waller ◽  
Kate A. Woodcock
Keyword(s):  
Intellectual Disability ◽  
Cognitive Training ◽  
Task Switching ◽  
Participatory Design ◽  
Matched Control ◽  
Lessons Learned ◽  
Genetic Syndromes ◽  
Design And Development ◽  
Genetic Syndrome ◽  
Wide Range

Background. The ability to rapidly switch between tasks is important in a variety of contexts. Training in task switching may be particularly valuable for children with intellectual disability (ID), specifically ID linked to genetic syndromes such as Prader-Willi syndrome (PWS). We have developed a cognitive training game for children with PWS and performed a pilot evaluation of the programme to inform future game development. Here, we describe and critically reflect on the development and pilot evaluation process. Methods. Several novel aspects of our approach are highlighted in this paper, including the involvement (in various roles) of children with a rare genetic syndrome (PWS) in the development and evaluation of the software (participatory design) and the development of a matched control, or placebo version of the game for use in the pilot evaluation. Results. Children with PWS were capable of contributing to the design and development of a cognitive training game in various roles. In the subsequent pilot evaluation, playing the active version of the game was associated with greater improvement in task switching performance than playing the matched control (placebo) version of the game. However, attrition was an issue during both the design phase and the pilot evaluation. Conclusions. The lessons learned from our work have relevance in a wide range of contexts, such as the development of future cognitive training games; the evaluation of serious games in general; and the involvement of end-users with cognitive disabilities and/or rare syndromes in the design and development of software.

Sign in / Sign up

Export Citation Format

Share Document