aiqbench analysis
This research addresses the critical data scarcity issue in Parkinson's disease screening by proposing FICAug, a method that generates clinically plausible synthetic facial images based on Action Unit feature clusters rather than random perturbations. By integrating this intermediate representation learning step with a ResNet18 model, the approach significantly outperforms standard baselines and self-supervised alternatives like DINO on limited clinical datasets. The study demonstrates that structurally guided data augmentation can effectively expand training distributions for low-data medical AI applications.
FICAug: Feature-Informed Clustering and Augmentation for Facial-Expression-Based Parkinson's Disease Screening
arXiv:2409.17685v3 Announce Type: replace Abstract: Hypomimia has drawn growing interest as a digital marker for screening Parkinson's disease (PD). However, developing reliable facial-expression-based screening models is challenging because clinical PD datasets are small, exposing models to only a narrow range of how hypomimia can appear across individuals. Standard augmentation strategies do not solve this problem; recombining or perturbing existing samples produces variation, but not new facial configurations that are plausible and clinically meaningful. We introduce FICAug to address this gap. The framework clusters Action Unit (AU) feature vectors extracted from facial expression images, discards clusters that mix labels inconsistently, and generates synthetic AU vectors within the retained clusters with Gaussian sampling. GANimation then reconstructs these synthetic vectors into realistic facial images. A ResNet18 model is pretrained on these reconstructed images, and then fine-tuned on real clinical data. Using the UT-MoDaPark dataset, FICAug achieved 88.63% cross-validation accuracy and 94.00% test accuracy, outperforming both a standard ResNet18 baseline and self-supervised alternatives, including DINO and MSN. These results suggest that synthetic image generation, when guided by label consistency and clinical feature structure, can function as an effective intermediate representation-learning step for facial-expression-based PD screening in settings where clinical data remain scarce.
Abstract:Hypomimia has drawn growing interest as a digital marker for screening Parkinson's disease (PD). However, developing reliable facial-expression-based screening models is challenging because clinical PD datasets are small, exposing models to only a narrow range of how hypomimia can appear across individuals. Standard augmentation strategies do not solve this problem; recombining or perturbing existing samples produces variation, but not new facial configurations that are plausible and clinically meaningful. We introduce FICAug to address this gap. The framework clusters Action Unit (AU) feature vectors extracted from facial expression images, discards clusters that mix labels inconsistently, and generates synthetic AU vectors within the retained clusters with Gaussian sampling. GANimation then reconstructs these synthetic vectors into realistic facial images. A ResNet18 model is pretrained on these reconstructed images, and then fine-tuned on real clinical data. Using the UT-MoDaPark dataset, FICAug achieved 88.63% cross-validation accuracy and 94.00% test accuracy, outperforming both a standard ResNet18 baseline and self-supervised alternatives, including DINO and MSN. These results suggest that synthetic image generation, when guided by label consistency and clinical feature structure, can function as an effective intermediate representation-learning step for facial-expression-based PD screening in settings where clinical data remain scarce.
Artificial Intelligence (cs.AI); Machine Learning (cs.LG)
arXiv:2409.17685 [cs.AI]
(or arXiv:2409.17685v3 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2409.17685 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 288 words
Related coverage
Exploring Hierarchical Interest Representation For Meta Ads Deep Funnel Optimization
Meta Engineering · Jul 15, 2026
The J-Space Debate, Agent Swarms, and Pacing Frontier AI - Digital Minds Newsletter #4
LessWrong · Sep 18, 2026
How to Build In-Vehicle AI Agents with NVIDIA: From Cloud to Car
NVIDIA · May 5, 2026
MCRL2: Multi-resource Cross-attention-based Representation Learning-augmented Reinforcement Learning for Cloud Microservice Scheduling
arXiv · Sep 14, 2026