A 3D Clinical Face Phenotype Space of Genetic Syndromes Using a Triplet-Based Singular Geometric Autoencoder
Clinical diagnosis of syndromes benefits strongly from objective facial phenotyping. This study introduces a novel approach to enhance clinical diagnosis through the development and exploration of a low-dimensional metric space referred to as the clinical face phenotypic space (CFPS). As a facial ma...
Saved in:
| Main Authors: | , , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10818677/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841536150009806848 |
|---|---|
| author | Soha S. Mahdi Eduarda Caldeira Harold Matthews Michiel Vanneste Nele Nauwelaers Meng Yuan Giorgos Bouritsas Gareth S. Baynam Peter Hammond Richard Spritz Ophir D. Klein Michael Bronstein Benedikt Hallgrimsson Hilde Peeters Peter Claes |
| author_facet | Soha S. Mahdi Eduarda Caldeira Harold Matthews Michiel Vanneste Nele Nauwelaers Meng Yuan Giorgos Bouritsas Gareth S. Baynam Peter Hammond Richard Spritz Ophir D. Klein Michael Bronstein Benedikt Hallgrimsson Hilde Peeters Peter Claes |
| author_sort | Soha S. Mahdi |
| collection | DOAJ |
| description | Clinical diagnosis of syndromes benefits strongly from objective facial phenotyping. This study introduces a novel approach to enhance clinical diagnosis through the development and exploration of a low-dimensional metric space referred to as the clinical face phenotypic space (CFPS). As a facial matching tool for clinical genetics, such CFPS can enhance clinical diagnosis. It helps to interpret facial dysmorphisms of a subject by placing them within the space of known dysmorphisms. In this paper, a triplet loss-based autoencoder developed by geometric deep learning (GDL) is trained using multi-task learning, which combines supervised and unsupervised learning approaches. Experiments are designed to illustrate the following properties of CFPSs that can aid clinicians in narrowing down their search space: a CFPS can 1) classify syndromes accurately, 2) generalize to novel syndromes, and 3) preserve the relatedness of genetic diseases, meaning that clusters of phenotypically similar disorders reflect functional relationships between genes. The proposed model consists of three main components: an encoder based on GDL optimizing distances between groups of individuals in the CFPS, a decoder enhancing classification by reconstructing faces, and a singular value decomposition layer maintaining orthogonality and optimal variance distribution across dimensions. This allows for the selection of an optimal number of CFPS dimensions as well as improving the classification capacity of the CFPS, which outperforms the linear metric learning baseline in both syndrome classification and generalization to novel syndromes. We further proved the usefulness of each component of the proposed framework, highlighting their individual impact. From a clinical perspective, the unique combination of these properties in a single CFPS results in a powerful tool that can be incorporated into current clinical practices to assess facial dysmorphism.INDEX TERMS 3D shape analysis, clinical genetics, computer-aided diagnosis, deep phenotyping, geometric deep learning, precision public health. |
| format | Article |
| id | doaj-art-0558fb2d9bf2466db4e2b6b70a15e88b |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-0558fb2d9bf2466db4e2b6b70a15e88b2025-01-15T00:03:14ZengIEEEIEEE Access2169-35362025-01-011311510.1109/ACCESS.2024.352442810818677A 3D Clinical Face Phenotype Space of Genetic Syndromes Using a Triplet-Based Singular Geometric AutoencoderSoha S. Mahdi0Eduarda Caldeira1https://orcid.org/0009-0002-4891-0057Harold Matthews2Michiel Vanneste3https://orcid.org/0000-0003-0222-5740Nele Nauwelaers4https://orcid.org/0000-0002-9763-6106Meng Yuan5https://orcid.org/0000-0003-0922-8012Giorgos Bouritsas6https://orcid.org/0000-0002-8476-4918Gareth S. Baynam7Peter Hammond8https://orcid.org/0000-0003-3208-4459Richard Spritz9https://orcid.org/0000-0002-8325-0026Ophir D. Klein10Michael Bronstein11Benedikt Hallgrimsson12https://orcid.org/0000-0002-7192-9103Hilde Peeters13Peter Claes14https://orcid.org/0000-0001-9489-9819ETRO, Vrije Universiteit Brussel, Ixelles, BelgiumESAT/PSI—UZ Leuven, MIRC, KU Leuven, Leuven, BelgiumESAT/PSI—UZ Leuven, MIRC, KU Leuven, Leuven, BelgiumDepartment of Human Genetics, KU Leuven, Leuven, BelgiumESAT/PSI—UZ Leuven, MIRC, KU Leuven, Leuven, BelgiumESAT/PSI—UZ Leuven, MIRC, KU Leuven, Leuven, BelgiumDepartment of Informatics and Telecommunications, Archimedes AI Unit/Athena RC, University of Athens, Athens, GreeceSchool of Earth and Planetary Sciences, Faculty of Science and Engineering, Curtin University, Perth, AustraliaDepartment of Human Genetics, KU Leuven, Leuven, BelgiumSchool of Medicine, Human Medical Genetics and Genomics Program, University of Colorado, Aurora, CO, USADepartment of Orofacial Sciences, Institute for Human Genetics, University of California at San Francisco, San Francisco, CA, USADepartment of Computer Science, University of Oxford, Oxford, U.K.Department of Cell Biology and Anatomy, Cumming School of Medicine, University of Calgary, Calgary, AB, CanadaDepartment of Human Genetics, KU Leuven, Leuven, BelgiumESAT/PSI—UZ Leuven, MIRC, KU Leuven, Leuven, BelgiumClinical diagnosis of syndromes benefits strongly from objective facial phenotyping. This study introduces a novel approach to enhance clinical diagnosis through the development and exploration of a low-dimensional metric space referred to as the clinical face phenotypic space (CFPS). As a facial matching tool for clinical genetics, such CFPS can enhance clinical diagnosis. It helps to interpret facial dysmorphisms of a subject by placing them within the space of known dysmorphisms. In this paper, a triplet loss-based autoencoder developed by geometric deep learning (GDL) is trained using multi-task learning, which combines supervised and unsupervised learning approaches. Experiments are designed to illustrate the following properties of CFPSs that can aid clinicians in narrowing down their search space: a CFPS can 1) classify syndromes accurately, 2) generalize to novel syndromes, and 3) preserve the relatedness of genetic diseases, meaning that clusters of phenotypically similar disorders reflect functional relationships between genes. The proposed model consists of three main components: an encoder based on GDL optimizing distances between groups of individuals in the CFPS, a decoder enhancing classification by reconstructing faces, and a singular value decomposition layer maintaining orthogonality and optimal variance distribution across dimensions. This allows for the selection of an optimal number of CFPS dimensions as well as improving the classification capacity of the CFPS, which outperforms the linear metric learning baseline in both syndrome classification and generalization to novel syndromes. We further proved the usefulness of each component of the proposed framework, highlighting their individual impact. From a clinical perspective, the unique combination of these properties in a single CFPS results in a powerful tool that can be incorporated into current clinical practices to assess facial dysmorphism.INDEX TERMS 3D shape analysis, clinical genetics, computer-aided diagnosis, deep phenotyping, geometric deep learning, precision public health.https://ieeexplore.ieee.org/document/10818677/3D Shape AnalysisClinical GeneticsComputer-aided DiagnosisDeep PhenotypingGeometric Deep LearningPrecision Public Health |
| spellingShingle | Soha S. Mahdi Eduarda Caldeira Harold Matthews Michiel Vanneste Nele Nauwelaers Meng Yuan Giorgos Bouritsas Gareth S. Baynam Peter Hammond Richard Spritz Ophir D. Klein Michael Bronstein Benedikt Hallgrimsson Hilde Peeters Peter Claes A 3D Clinical Face Phenotype Space of Genetic Syndromes Using a Triplet-Based Singular Geometric Autoencoder IEEE Access 3D Shape Analysis Clinical Genetics Computer-aided Diagnosis Deep Phenotyping Geometric Deep Learning Precision Public Health |
| title | A 3D Clinical Face Phenotype Space of Genetic Syndromes Using a Triplet-Based Singular Geometric Autoencoder |
| title_full | A 3D Clinical Face Phenotype Space of Genetic Syndromes Using a Triplet-Based Singular Geometric Autoencoder |
| title_fullStr | A 3D Clinical Face Phenotype Space of Genetic Syndromes Using a Triplet-Based Singular Geometric Autoencoder |
| title_full_unstemmed | A 3D Clinical Face Phenotype Space of Genetic Syndromes Using a Triplet-Based Singular Geometric Autoencoder |
| title_short | A 3D Clinical Face Phenotype Space of Genetic Syndromes Using a Triplet-Based Singular Geometric Autoencoder |
| title_sort | 3d clinical face phenotype space of genetic syndromes using a triplet based singular geometric autoencoder |
| topic | 3D Shape Analysis Clinical Genetics Computer-aided Diagnosis Deep Phenotyping Geometric Deep Learning Precision Public Health |
| url | https://ieeexplore.ieee.org/document/10818677/ |
| work_keys_str_mv | AT sohasmahdi a3dclinicalfacephenotypespaceofgeneticsyndromesusingatripletbasedsingulargeometricautoencoder AT eduardacaldeira a3dclinicalfacephenotypespaceofgeneticsyndromesusingatripletbasedsingulargeometricautoencoder AT haroldmatthews a3dclinicalfacephenotypespaceofgeneticsyndromesusingatripletbasedsingulargeometricautoencoder AT michielvanneste a3dclinicalfacephenotypespaceofgeneticsyndromesusingatripletbasedsingulargeometricautoencoder AT nelenauwelaers a3dclinicalfacephenotypespaceofgeneticsyndromesusingatripletbasedsingulargeometricautoencoder AT mengyuan a3dclinicalfacephenotypespaceofgeneticsyndromesusingatripletbasedsingulargeometricautoencoder AT giorgosbouritsas a3dclinicalfacephenotypespaceofgeneticsyndromesusingatripletbasedsingulargeometricautoencoder AT garethsbaynam a3dclinicalfacephenotypespaceofgeneticsyndromesusingatripletbasedsingulargeometricautoencoder AT peterhammond a3dclinicalfacephenotypespaceofgeneticsyndromesusingatripletbasedsingulargeometricautoencoder AT richardspritz a3dclinicalfacephenotypespaceofgeneticsyndromesusingatripletbasedsingulargeometricautoencoder AT ophirdklein a3dclinicalfacephenotypespaceofgeneticsyndromesusingatripletbasedsingulargeometricautoencoder AT michaelbronstein a3dclinicalfacephenotypespaceofgeneticsyndromesusingatripletbasedsingulargeometricautoencoder AT benedikthallgrimsson a3dclinicalfacephenotypespaceofgeneticsyndromesusingatripletbasedsingulargeometricautoencoder AT hildepeeters a3dclinicalfacephenotypespaceofgeneticsyndromesusingatripletbasedsingulargeometricautoencoder AT peterclaes a3dclinicalfacephenotypespaceofgeneticsyndromesusingatripletbasedsingulargeometricautoencoder AT sohasmahdi 3dclinicalfacephenotypespaceofgeneticsyndromesusingatripletbasedsingulargeometricautoencoder AT eduardacaldeira 3dclinicalfacephenotypespaceofgeneticsyndromesusingatripletbasedsingulargeometricautoencoder AT haroldmatthews 3dclinicalfacephenotypespaceofgeneticsyndromesusingatripletbasedsingulargeometricautoencoder AT michielvanneste 3dclinicalfacephenotypespaceofgeneticsyndromesusingatripletbasedsingulargeometricautoencoder AT nelenauwelaers 3dclinicalfacephenotypespaceofgeneticsyndromesusingatripletbasedsingulargeometricautoencoder AT mengyuan 3dclinicalfacephenotypespaceofgeneticsyndromesusingatripletbasedsingulargeometricautoencoder AT giorgosbouritsas 3dclinicalfacephenotypespaceofgeneticsyndromesusingatripletbasedsingulargeometricautoencoder AT garethsbaynam 3dclinicalfacephenotypespaceofgeneticsyndromesusingatripletbasedsingulargeometricautoencoder AT peterhammond 3dclinicalfacephenotypespaceofgeneticsyndromesusingatripletbasedsingulargeometricautoencoder AT richardspritz 3dclinicalfacephenotypespaceofgeneticsyndromesusingatripletbasedsingulargeometricautoencoder AT ophirdklein 3dclinicalfacephenotypespaceofgeneticsyndromesusingatripletbasedsingulargeometricautoencoder AT michaelbronstein 3dclinicalfacephenotypespaceofgeneticsyndromesusingatripletbasedsingulargeometricautoencoder AT benedikthallgrimsson 3dclinicalfacephenotypespaceofgeneticsyndromesusingatripletbasedsingulargeometricautoencoder AT hildepeeters 3dclinicalfacephenotypespaceofgeneticsyndromesusingatripletbasedsingulargeometricautoencoder AT peterclaes 3dclinicalfacephenotypespaceofgeneticsyndromesusingatripletbasedsingulargeometricautoencoder |