Deep Learning-Based Analysis of Face Images as a Screening Tool for Genetic Syndromes

Abstract

Approximately 4% of the world’s population suffers from rare diseases. A vast majority of these disorders have a genetic background. The number of genes that have been linked to human diseases is constantly growing, but there are still genetic syndromes that remain to be discovered. The diagnostic yield of genetic testing is continuously developing, and the need for testing is becoming more significant. Due to limited resources, including trained clinical geneticists, patients referred to clinical genetics units must be accurately selected. Around 30–40% of genetic disorders are associated with specific facial characteristics called dysmorphic features. As part of our research, we analyzed the performance of classifiers based on deep learning face recognition models in detecting dysmorphic features. We tested two classification problems: a multiclass problem (15 genetic disorders vs. controls) and a two-class problem (disease vs. controls). In the multiclass task, the best result reached an accuracy level of 84%. The best accuracy result in the two-class problem reached 96%. More importantly, the binary classifier detected disease features in patients with diseases that were not previously present in the training dataset. The classifier was able to generalize differences between patients and controls, and to detect abnormalities without information about the specific disorder. This indicates that a screening tool based on deep learning and facial recognition could not only detect known diseases, but also detect patients with diseases that were not previously known. In the future, this tool could help in screening patients before they are referred to the genetic unit.

Face recognition in identifying genetic diseases: a progress review

“…The various architectures of CNN itself successfully identify diseases from various medical images because of the high frequency and excellent recognition rate [35]. So, of course, in the last five years, many studies have focused on the development of CNN in detecting genetic diseases through facial recognition [7], [20], [36]- [40]. Developments also lead to more complex problems, whereas Singh and Kisku in 2018 [36] and Gurovich et al in 2019 [37] have identified various genetic diseases and the results obtained are pretty good.…”

“…The results of this study get an accuracy of 84%, where the model can detect abnormalities without requiring information about specific abnormalities. The system does not have to be trained with all genetic diseases to detect genetic features on existing faces [40]. A summary of all the research described can be seen in Table 1.…”

Analytics and Applications of Audio and Image Sensing Techniques

“…M. Geremek and K. Szklanny in [ 9 ] investigated deep learning based detection of genetic diseases from face images, for 15 genetic disorders associated with facial dysmorphism. The authors achieved 84% accuracy for 15 classes, and up to 96% for binary classification of particular diseases.…”

A Decision Support System for Face Sketch Synthesis Using Deep Learning and Artificial Intelligence

“…Sim G, as mentioned in Equation (11), is their similarity based on the GM only, and Sim L is their combined similarity at the point of consideration. Sim L is measured by the relation given in Equation (12).…”

“…The formulation of face sketches based on learning from the reference photos and their corresponding forensic sketches has been an active field since the last two decades [12,13]. It helps the law enforcement agencies in the search, isolation, and identification of suspects by enabling them to match sketches against possible candidates from the mug-shot library [14][15][16] and/or photo dataset of the target population [17,18].…”