Ongoing Projects

Oct. 2nd 2025

Principal Investigator: Mr. Akshit Chikara

Institution: National Institue Of Technology, Rourkela, India

We are conducting non-commercial academic research at the Department of Computer Science & Engineering, National Institute of Technology Rourkela, an Institute of National Importance in India. Our project develops and evaluates machine learning approaches to analyze facial images of rare genetic disorders to improve early diagnosis and support clinicians. We will also study explainability...

Nov. 17th 2025

Principal Investigator: Dr. abderrahim benmohamed

Institution: computer science department soukahras

Genetic disorders often present with distinctive but subtle facial phenotypical features, making computer-aided facial analysis a valuable diagnostic aid. Recent systems such as GestaltMatcher and DeepGestalt have demonstrated the feasibility of syndrome classification from 2D facial images, yet remain limited by their black-box nature. This research proposes a framework that both...

Nov. 3rd 2025

Principal Investigator: Ms. Ayat El Houda Kechroud

Institution: Souk Ahras University

Genetic disorders often present with distinctive but subtle facial phenotypical features, making computer-aided facial analysis a valuable diagnostic aid. Recent systems such as GestaltMatcher and DeepGestalt have demonstrated the feasibility of syndrome classification from 2D facial images, yet remain limited by their black-box nature. This research proposes a framework that both...

Nov. 10th 2025

Principal Investigator: Mr. Hemant Darur

Institution: KLE Technological University

This project aims to improve few-shot facial phenotype recognition for rare genetic disorders using the GestaltMatcher Database (GMDB). We propose to enhance by integrating a modern ConvNeXt-v2 backbone with the AdaFace adaptive-margin loss function. The approach employs a meta-learning setup to better generalize across syndromes with limited data. The model will first be pretrained on...

Dec. 23rd 2025

Principal Investigator: Mr. Vyacheslav Kumov

Institution: Bauman Moscow State Technical University

The aim of the study is to develop methods for recognizing genetic syndromes from facial images. To improve interpretability, we propose a combined approach that uses both neural network features and geometric features from anthropometry. To extract geometric features, we plan to develop a method for reconstructing the 3D facial shape from a series of patient photographs. A separate...

Dec. 23rd 2025

Principal Investigator: Dr. Farshid Hajati

Institution: University of New England

Next-generation phenotyping systems such as GestaltMatcher have shown great promise in supporting the diagnosis of rare genetic disorders from facial images. However, deploying these models robustly in real-world clinical environments remains challenging. In particular, performance can degrade substantially when models are applied to new hospitals, imaging devices, ethnic populations, or age...

Jan. 26th 2026

Principal Investigator: Prof. Carlos Steiner

Institution: Universidade Estadual de Campinas (Unicamp), Brazil

Wiedemann-Steiner syndrome (WDSTS; OMIM #605130) is characterized by neurodevelopmental disabilities, growth deficit, and distinctive facial features, with or without additional congenital anomalies that include cerebral, visceral, and skeletal malformations. The primary differential diagnoses include other chromatinopathies such as Cornelia de Lange syndrome, Kabuki syndrome, Rubinstein-Taybi...

Jun. 3rd 2026

Principal Investigator: Mr. 斌 权

Institution: Beijing University of Chemical Technology

We have previously developed a classification model for Goldenhar syndrome subtypes (96.8% accuracy), but it is limited to a single disease. With access to GMDB, we aim to extend our research to multi-disease rare disease diagnosis. The specific goals are: (1) Externally validate the cross-disease generalization of our existing model; (2) Build an assistive diagnostic model covering hundreds...

Jun. 3rd 2026

Principal Investigator: Prof. Pingzhao Hu

Institution: Western University (The University of Western Ontario)

Rare disease diagnosis remains a significant clinical challenge due to phenotypic heterogeneity and limited access to specialized expertise. In this project, we propose an agentic artificial intelligence (AI) framework for diagnostic support that integrates facial image analysis with structured phenotype information. Leveraging controlled access to the GMDB dataset, we combine compact visual...

Jun. 3rd 2026

Principal Investigator: Prof. Sebastien Gaboury

Institution: Université du Québec à Chicoutimi

Our research project, Explainable Computer Vision for Rare Disease Identification from Facial, Hand, and Foot Morphological Data, aims to develop an interpretable AI-based diagnostic support system for identifying rare disease-related morphological patterns from non-invasive visual data. While the long-term objective is to build a multimodal pipeline integrating facial, hand, and foot images,...

Jun. 3rd 2026

Principal Investigator: Mr. Aidos Sadyrbekov

Institution: International IT University, Almaty, Kazakhstan

This project aims to develop a research prototype that, given a frontal facial photograph, returns a ranked short-list of candidate genetic syndromes with calibrated confidence scores — intended as clinical decision support, not a diagnostic device. The system will apply transfer learning from a face-pretrained backbone (ArcFace/VGGFace2-based ResNet) to classify five syndromes: Down syndrome,...