Boston-based biotech and digital health tech company FDNA has developed a deep learning application, Face2Gene, which can help doctors spot rare genetic disorders. The system can be deployed on a smartphone, achieves 91 percent top-10-accuracy in identifying over 215 different genetic syndromes, and has outperformed clinical experts in three separate experiments.
The FDNA team’s research paper, Identifying facial phenotypes of genetic disorders using deep learning, has been published in Nature Medicine.
Using deep learning algorithms and brain-like neural networks, the Face3Gene app can predict congenital and neural developmental disorders in people through the detection of distinctive facial features in photos. Face2Gene builds on a technique the FDNA team introduced last January in the paper DeepGestalt – Identifying Rare Genetic Syndromes Using Deep Learning.
Researchers started by training an AI system to distinguish two conditions which cause distinct facial features — Cornelia de Langs syndrome and Angelman syndrome — from other, similar conditions. They also taught the model to recognize a third disorder, Noonan syndrome. They then fed the deep learning algorithm with more than 17,000 images of diagnosed cases spanning 216 distinct syndromes to build the trained Face2Gene model and push accuracy to over 90 percent.
“This is a long-awaited breakthrough in medical genetics that has finally come to fruition,” says paper co-author and FDNA CEO Dr. Karen Gripp. “With this study, we’ve shown that adding an automated facial analysis framework, such as DeepGestalt, to the clinical workflow can help achieve earlier diagnosis and treatment, and promise an improved quality of life.”
FDNA has made the Face2Gene app available to doctors free of charge. This will help the company obtain the additional data it needs to continue developing this technology and accelerating disease diagnosis. So far the database contains about 150,000 images, and “the program’s accuracy has improved slightly as more healthcare professionals upload patient photos to the app,” says paper co-author Yaron Gurovich.
Author: Victor Lu | Editor: Michael Sarazen