Accurate and Private Diagnosis of Rare Genetic Syndromes from Facial Images with Federated Deep Learning

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ünal, Ali Burak, Baykara, Cem Ata, Krawitz, Peter, Akgün, Mete
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866909785951043584
author Ünal, Ali Burak
Baykara, Cem Ata
Krawitz, Peter
Akgün, Mete
author_facet Ünal, Ali Burak
Baykara, Cem Ata
Krawitz, Peter
Akgün, Mete
contents Machine learning has shown promise in facial dysmorphology, where characteristic facial features provide diagnostic clues for rare genetic disorders. GestaltMatcher, a leading framework in this field, has demonstrated clinical utility across multiple studies, but its reliance on centralized datasets limits further development, as patient data are siloed across institutions and subject to strict privacy regulations. We introduce a federated GestaltMatcher service based on a cross-silo horizontal federated learning framework, which allows hospitals to collaboratively train a global ensemble feature extractor without sharing patient images. Patient data are mapped into a shared latent space, and a privacy-preserving kernel matrix computation framework enables syndrome inference and discovery while safeguarding confidentiality. New participants can directly benefit from and contribute to the system by adopting the global feature extractor and kernel configuration from previous training rounds. Experiments show that the federated service retains over 90% of centralized performance and remains robust to both varying silo numbers and heterogeneous data distributions.
format Preprint
id arxiv_https___arxiv_org_abs_2509_10635
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Accurate and Private Diagnosis of Rare Genetic Syndromes from Facial Images with Federated Deep Learning
Ünal, Ali Burak
Baykara, Cem Ata
Krawitz, Peter
Akgün, Mete
Machine Learning
Cryptography and Security
Computer Vision and Pattern Recognition
Machine learning has shown promise in facial dysmorphology, where characteristic facial features provide diagnostic clues for rare genetic disorders. GestaltMatcher, a leading framework in this field, has demonstrated clinical utility across multiple studies, but its reliance on centralized datasets limits further development, as patient data are siloed across institutions and subject to strict privacy regulations. We introduce a federated GestaltMatcher service based on a cross-silo horizontal federated learning framework, which allows hospitals to collaboratively train a global ensemble feature extractor without sharing patient images. Patient data are mapped into a shared latent space, and a privacy-preserving kernel matrix computation framework enables syndrome inference and discovery while safeguarding confidentiality. New participants can directly benefit from and contribute to the system by adopting the global feature extractor and kernel configuration from previous training rounds. Experiments show that the federated service retains over 90% of centralized performance and remains robust to both varying silo numbers and heterogeneous data distributions.
title Accurate and Private Diagnosis of Rare Genetic Syndromes from Facial Images with Federated Deep Learning
topic Machine Learning
Cryptography and Security
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2509.10635