Few-Shot Meta Learning for Recognizing Facial Phenotypes of Genetic Disorders
This work addresses the challenge of sparse labels and class imbalances in automated diagnosis of genetic disorders, aiding physicians in early decision-making, but it is incremental as it builds on existing few-shot and transfer learning methods.
The study tackled the problem of recognizing facial phenotypes of genetic disorders by using a facial recognition model pre-trained on healthy individuals and applying few-shot meta-learning strategies, resulting in improved retrieval performance that surpassed previous works like GestaltMatcher on the GestaltMatcher Database.
Computer vision-based methods have valuable use cases in precision medicine, and recognizing facial phenotypes of genetic disorders is one of them. Many genetic disorders are known to affect faces' visual appearance and geometry. Automated classification and similarity retrieval aid physicians in decision-making to diagnose possible genetic conditions as early as possible. Previous work has addressed the problem as a classification problem and used deep learning methods. The challenging issue in practice is the sparse label distribution and huge class imbalances across categories. Furthermore, most disorders have few labeled samples in training sets, making representation learning and generalization essential to acquiring a reliable feature descriptor. In this study, we used a facial recognition model trained on a large corpus of healthy individuals as a pre-task and transferred it to facial phenotype recognition. Furthermore, we created simple baselines of few-shot meta-learning methods to improve our base feature descriptor. Our quantitative results on GestaltMatcher Database show that our CNN baseline surpasses previous works, including GestaltMatcher, and few-shot meta-learning strategies improve retrieval performance in frequent and rare classes.