# Computer-vision analysis of craniofacial dysmorphology in 22q11.2 deletion syndrome and psychosis spectrum disorders

**Authors:** David R. Roalf, Donna M. McDonald-McGinn, Joelle Jee, Mckenna Krall, T. Blaine Crowley, Paul J. Moberg, Christian Kohler, Monica E. Calkins, Andrew J.D. Crow, Nicole Fleischer, R. Sean Gallagher, Virgilio Gonzenbach, Kelly Clark, Ruben C. Gur, Emily McClellan, Daniel E. McGinn, Arianna Mordy, Kosha Ruparel, Bruce I. Turetsky, Russell T. Shinohara, Lauren White, Elaine Zackai, Raquel E. Gur

PMC · DOI: 10.1186/s11689-024-09547-8 · 2024-06-25

## TL;DR

This study uses computer vision to analyze facial features in 22q11DS and psychosis spectrum disorders, aiming to identify early signs of developmental disruptions linked to psychosis.

## Contribution

The study introduces a novel approach combining two computer-vision techniques to detect overlapping craniofacial patterns in 22q11DS and psychosis.

## Key findings

- F2G reliably identified 22q11DS patients and linked PS patients to genetic conditions like FragileX.
- PCA-derived facial patterns showed unique and overlapping features in 22q11DS and PS.
- 22q11DS individuals had smaller eye and nose measurements compared to typically developing controls.

## Abstract

Minor physical anomalies (MPAs) are congenital morphological abnormalities linked to disruptions of fetal development. MPAs are common in 22q11.2 deletion syndrome (22q11DS) and psychosis spectrum disorders (PS) and likely represent a disruption of early embryologic development that may help identify overlapping mechanisms linked to psychosis in these disorders.

Here, 2D digital photographs were collected from 22q11DS (n = 150), PS (n = 55), and typically developing (TD; n = 93) individuals. Photographs were analyzed using two computer-vision techniques: (1) DeepGestalt algorithm (Face2Gene (F2G)) technology to identify the presence of genetically mediated facial disorders, and (2) Emotrics—a semi-automated machine learning technique that localizes and measures facial features.

F2G reliably identified patients with 22q11DS; faces of PS patients were matched to several genetic conditions including FragileX and 22q11DS. PCA-derived factor loadings of all F2G scores indicated unique and overlapping facial patterns that were related to both 22q11DS and PS. Regional facial measurements of the eyes and nose were smaller in 22q11DS as compared to TD, while PS showed intermediate measurements.

The extent to which craniofacial dysmorphology 22q11DS and PS overlapping and evident before the impairment or distress of sub-psychotic symptoms may allow us to identify at-risk youths more reliably and at an earlier stage of development.

The online version contains supplementary material available at 10.1186/s11689-024-09547-8.

## Linked entities

- **Diseases:** 22q11.2 deletion syndrome (MONDO:0008564)

## Full-text entities

- **Diseases:** PS (MESH:D011618), 22q11.2 deletion syndrome (MESH:D004062), MPAs (MESH:D004832), craniofacial dysmorphology (MESH:D005157), congenital morphological abnormalities (MESH:D000013), facial disorders (MESH:D005155)
- **Species:** Homo sapiens (human, species) [taxon 9606]

## Figures

5 figures with captions in the complete paper: https://tomesphere.com/paper/PMC11201300/full.md

---
Source: https://tomesphere.com/paper/PMC11201300