DeciFace: Decipher the Influence of Ethnic Backgrounds on the Facial Dysmorphic Features of Rare Mendelian Disorders

Rare Diseases Clinical Trial

Official title:

DeciFace: Decipher the Influence of Ethnic Backgrounds on the Facial Dysmorphic Features of Rare Mendelian Disorders

Clinical Trial Details — Status: Not yet recruiting

Administrative data

• NCT number: NCT05913843
• Other study ID #: 202302053RIND
• Status: Not yet recruiting
• Start date: June 30, 2023
• Est. completion date: June 30, 2026

Study information

• Verified date: May 2023
• Source: National Taiwan University Hospital
• Contact: Ni-Chung Lee, M.D., Ph.D.
• Phone: 886-2-23123456
• Email: ncleentu[@]ntu.edu.tw
• Is FDA regulated: No
• Study type: Observational

Clinical Trial Summary

There are more than 7000 known genetic disorders, and the number of affected is estimated to be about 6-10% of the population. Around 30 to 40% of genetic disorders have physical changes in the face and skull such as Down's syndrome or Fragile X syndrome. Therefore, the known facial phenotype of many genetic disorders is highly informative to clinical diagnosis. Since a large number of genetic diseases are associated with special facial phenotypes that are difficult to remember, automated facial analysis such as Face2Gene and GestaltMatcher can assist in the identification and diagnosis of facial phenotypes related to various genetic diseases. Although the current advances in whole exome sequencing (whole exome sequencing) or whole genome sequencing (whole genome sequencing) have greatly improved the diagnostic rate of genetic diseases, about half of the patients are still undiagnosed. For patients with special facial phenotypes, the investigators believe that by combining automated facial analysis and whole exome sequencing data, it should be possible to provide a fast and accurate diagnostic model of genetic mutations for genetic diseases. GestaltMatcher Database is a medical imaging database of rare diseases developed by Professor Peter Krawitz of the University of Bonn, Germany. The database's artificial intelligence module will infer a patient's possible diagnosis based on the patient's photo, age, gender, race, and clinical description. The database will be open to medical researchers in related fields to improve the diagnosis of rare diseases. The investigators will use GestaltMatcher to assist in the diagnosis of patients, and compare the accuracy and significant differences in facial deformities between Taiwanese patients and patients from different countries. And use Eye Tracker to analyze how doctors diagnose patients through facial photos, and compare whether there are significant differences between foreign patients and Taiwanese patients in the diagnosis literature of Taiwanese doctors. The project will also analyze how genetic doctors at the University of Bonn in Germany diagnose patients, and compare it with Taiwanese doctors to better understand the differences in the process of doctors diagnosing patients and ethnic backgrounds.

Description:

Genetic disorder and facial phenotype There are more than 7000 known genetic disorders, and the number of affected is estimated to be about 6-10% of the population1. Around 30 to 40% of genetic disorders have physical changes in the face and skull such as Down's syndrome or Fragile X syndrome. Therefore, the known facial phenotype of many genetic disorders is highly informative to clinical diagnosis. As everyone knows, a fast and accurate diagnosis of genetic disorders is essential to prevent potential health problems. For clinical geneticists and pediatricians, it needs a high degree of experience and expertise to diagnosing genetic disorders through facial phenotype. However, there have some dilemmas for this issue. First, recognition of non-classical presentation or ultra-rare genetic disorder is constrained by the individual human expert's prior experience. Second, some genetic disorders will be confused in the clinic because they have a few subtypes (more than one typical phenotype) or overlapping facial characteristics with other disorders, such as the Cornelia de Lange syndrome. Lastly, the difficulty of diagnosis will increase due to facial phenotype sometimes being wide spectrum or becoming more prominent by age, like mucopolysaccharidosis. Briefly, genetic disorder diagnosis through facial phenotype still has a challenge. Automated facial analysis The research of computer-aided recognition has long been dealing with facial analysis-related problems, especially for non-classical presentation or ultra-rare genetic disorders. In other words, using computerized systems as an aid or reference for clinicians is becoming increasingly important2-6. In recent years, Face2Gene (FDNA Inc., Boston MA, USA) has been a novel and widely used tool to detect facial phenotype and recognize dysmorphic features from two-dimensional (2D) frontal photographs2. The facial dysmorphism novel analysis (FDNA) technology in Face2Gene is called DeepGestalt, which builds on deep convolutional neural networks (DCNNs) and uses computer vision and deep learning algorithms. The high-level flow of DeepGestalt is as described by Yaron Gurovich et al.. First is preprocessing a new input image to achieve face detection, landmarks detection, and alignment and then cropping the input image into facial regions. Second is feeding each region into a DCNN and obtain a softmax vector which indicate its correspondence to each syndrome in the model. Third is aggregating and sorting the output vectors of all regional DCNNs to obtain the final ranked list of genetic disorders. The part for the DCNN architecture of DeepGestalt is as a follow-up. There are ten convolutional layers in the network, and all but the last one are followed by batch normalization and a rectified linear unit (ReLU). A pooling layer is applied after each pair of convolutional (CONV) layer (maximum pooling after the first four pairs and average pooling after the fifth pair). And then the CONV layers are followed by a full connected layer with dropout (0.5) and a softmax layer. Therefore, a sample heatmap appears after each pooling layer. Comparing the low-level features of the first layers and the high-level features of final layer, the latter can identify more complex features in the input image and have tended to emerge distinctive facial traits when identity-related features disappear. Currently, the DeepGestalt model is trained on a dataset of over 17,000 images covering more than 200 different genetic disorders curated through Face2Gene, a community-driven phenotyping platform. The article identifying facial phenotypes of genetic disorders using deep learning provide the reliability of DeepGestalt to diagnose genetic disorders through automated facial analysis. The binary gestalt model distinguishes a specific disorder from a set of other disorders. For Cornelia de Lange syndrome, DeepGestalt achieves 96.88% accuracy, 95.67% sensitivity, and 100% specificity. For Angelman syndrome, DeepGestalt achieve 92% accuracy, 80% sensitivity, and 100% specificity. Compared with previous related study, both have more precise diagnosis ability. The specialized gestalt model is used to classify different genotypes of the same syndrome. Noonan syndrome with a gene mutation in PTPN11, SOS1, RAF1, RIT1, or KRAS is a model used for testing the performance of DeepGestalt. In this study, DeepGestalt is a truncated version and predicts only the five desired classes. The result is the top-1 accuracy of 64%, which is superior to the random chance of 20%, allowing geneticists to investigate phenotype-genotype correlations. Multi-class gestalt model is that DeepGestalt performs facial gestalt analysis at scale. DeepGestalt has a 90.6% top-10 accuracy on the clinical test set and 89.4% on the publication test set. The top-5 and top-1 accuracy for the clinical test set achieve 85.4% and 61.3%, respectively, and for the publications test set, 83.2% and 68.7%, respectively. Therefore, the clinical can reach better prioritization and diagnosis of genetic disorders through an automated facial analysis framework. Potentially, DeepGestalt adds considerable value to evaluating the facial phenotype of a genetic disorder in clinical genetics, molecular study, and research. In 2022, based on the previous work, Hsieh et al. proposed GestaltMatcher6, which utilized DCNNs trained on patients' photos as an encoder to convert facial photos into feature vectors to form a Clinical Face Phenotype Space (CFPS). They then quantified the similarity among patients by the cosine distance of two vectors in CFPS. With this approach, the investigators can support the ultra-rare syndromes that lack images to be trained and push the supported syndromes into the next level (from 299 to 1,115 syndromes). GestaltMatcher can also identify novel disorders. Moreover, it contributes to the longstanding discussion about distinguishability within the nosology of genetic diseases. Currently, there are 11 novel disease genes under analysis, and four of them were submitted to the peer-review journal.

Recruitment information / eligibility

• Status: Not yet recruiting
• Enrollment: 100
• Est. completion date: June 30, 2026
• Est. primary completion date: June 30, 2026
• Accepts healthy volunteers: No
• Gender: All
• Age group: N/A and older

Eligibility

Inclusion Criteria:

• Cases with abnormal appearance of clinical symptoms and suspected genetic diseases

Exclusion Criteria:

• Unable to cooperate with the examiner

Related Conditions & MeSH terms

• Rare Diseases

Intervention

Device:
• Take photo
We will use the camera to take 2 front and side images of the participant, and select one of the better images to upload to the facial analysis system (GestaltMatcher Database) for analysis.

Locations

Country	Name	City	State
n/a

Sponsors (2)

Lead Sponsor	Collaborator
National Taiwan University Hospital	University of Bonn

Outcome

Type	Measure	Description	Time frame	Safety issue
Primary	The diagnosis accuracy rate of use GestaltMatcher to analysis participant facial features in rare diseases	GestaltMatcher is a automated facial analysis software, which utilized deep convolutional neural networks trained on patients' photos as an encoder to convert facial photos into feature vectors to form a Clinical Face Phenotype Space (CFPS). And quantified the similarity among patients by the cosine distance of two vectors in CFPS. With this approach, the investigators can support the ultra-rare syndromes that lack images to be trained and push the supported syndromes.; Base on on this technology, the investigators use GestaltMatcher to analysis participant facial features and compare those vectors which are similar to patients to find possible syndromes. The investigators will verify more clinical phenotype and genetic data of the participants for verification.	1 month
Primary	The significant difference in facial deformities between Taiwan participant and participant from different countries by GestaltMatcher	The investigators will ues those facial feature vectors from GestaltMatcher Database to compare with Taiwan participants in the research platform within the GestaltMatcher Database to find the facial differences between Taiwan and other different countries participants by pairwise matrix. To find out where is the difference between Taiwan and different countries participants, improving the diagnostic perspectives in Taiwanese groups.	3 years
Secondary	Criteria for doctors to diagnose participants from facial features assessed by eye trackers	Use Eye Tracker to mark out where and when are the doctors pays attention to when observing the participant dysmorphic features. To analyze how doctors diagnose patients through facial photos.	3 years
Secondary	Diagnosis differences between Taiwan and Bonn University genetics doctors	Compare whether there are significant differences between Taiwanese doctors using literature data and phenotypic analysis to diagnose foreign patients and Taiwanese patients, and analyzing how geneticists at Bonn University diagnose patients	3 years