Deep Learning-Based Analysis of Face Images as a Screening Tool for Genetic Syndromes
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 y...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-10-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/19/6595 |
| _version_ | 1797515733244051456 |
|---|---|
| author | Maciej Geremek Krzysztof Szklanny |
| author_facet | Maciej Geremek Krzysztof Szklanny |
| author_sort | Maciej Geremek |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T06:51:28Z |
| format | Article |
| id | doaj.art-bc2ce670e5f143e296069911aa9f6208 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T06:51:28Z |
| publishDate | 2021-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-bc2ce670e5f143e296069911aa9f62082023-11-22T16:48:30ZengMDPI AGSensors1424-82202021-10-012119659510.3390/s21196595Deep Learning-Based Analysis of Face Images as a Screening Tool for Genetic SyndromesMaciej Geremek0Krzysztof Szklanny1Department of Medical Genetics, Institute of Mother and Child, 01-211 Warsaw, PolandMultimedia Department, Polish-Japanese Academy of Information Technology, 02-008 Warsaw, PolandApproximately 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.https://www.mdpi.com/1424-8220/21/19/6595dysmorphic features detectionface recognitiongenetic diseaseDNNclassifier |
| spellingShingle | Maciej Geremek Krzysztof Szklanny Deep Learning-Based Analysis of Face Images as a Screening Tool for Genetic Syndromes Sensors dysmorphic features detection face recognition genetic disease DNN classifier |
| title | Deep Learning-Based Analysis of Face Images as a Screening Tool for Genetic Syndromes |
| title_full | Deep Learning-Based Analysis of Face Images as a Screening Tool for Genetic Syndromes |
| title_fullStr | Deep Learning-Based Analysis of Face Images as a Screening Tool for Genetic Syndromes |
| title_full_unstemmed | Deep Learning-Based Analysis of Face Images as a Screening Tool for Genetic Syndromes |
| title_short | Deep Learning-Based Analysis of Face Images as a Screening Tool for Genetic Syndromes |
| title_sort | deep learning based analysis of face images as a screening tool for genetic syndromes |
| topic | dysmorphic features detection face recognition genetic disease DNN classifier |
| url | https://www.mdpi.com/1424-8220/21/19/6595 |
| work_keys_str_mv | AT maciejgeremek deeplearningbasedanalysisoffaceimagesasascreeningtoolforgeneticsyndromes AT krzysztofszklanny deeplearningbasedanalysisoffaceimagesasascreeningtoolforgeneticsyndromes |