CFCPalsy: Facial Image Synthesis with Cross-Fusion Cycle Diffusion Model for Facial Paralysis Individuals

2024-09-11

AI Summary

Facial palsy diagnosis relies heavily on subjective clinical assessment, and the scarcity of authentic clinical data severely hinders the development of automated diagnostic models. To address this, we propose the Cross-Fused Cyclic Palsy (CFCPalsy) generation model—a novel diffusion-based framework integrating cross-feature fusion to jointly model multi-regional pathological manifestations, incorporating cyclic consistency constraints to preserve identity, and enhancing fine-grained texture synthesis for improved pathological fidelity. Evaluated on a public clinical dataset, CFCPalsy achieves an 18.7% reduction in Fréchet Inception Distance (FID) and a 23.4% improvement in identity preservation rate; generated images receive high clinical validation from domain experts. Furthermore, we construct the first high-fidelity synthetic facial palsy image dataset, providing critical training data to advance robust diagnostic and therapeutic intervention models.

Technology Category

• Computer Vision: Diffusion Models for Vision
• Natural Language Processing: Generation
• Constraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

• User Modeling, Personalization and Recommendation: Federated recommendation systems and personalization
• Web Mining and Content Analysis: Large pretrained models with web data
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

Currently, the diagnosis of facial paralysis remains a challenging task, often relying heavily on the subjective judgment and experience of clinicians, which can introduce variability and uncertainty in the assessment process. One promising application in real-life situations is the automatic estimation of facial paralysis. However, the scarcity of facial paralysis datasets limits the development of robust machine learning models for automated diagnosis and therapeutic interventions. To this end, this study aims to synthesize a high-quality facial paralysis dataset to address this gap, enabling more accurate and efficient algorithm training. Specifically, a novel Cross-Fusion Cycle Palsy Expression Generative Model (CFCPalsy) based on the diffusion model is proposed to combine different features of facial information and enhance the visual details of facial appearance and texture in facial regions, thus creating synthetic facial images that accurately represent various degrees and types of facial paralysis. We have qualitatively and quantitatively evaluated the proposed method on the commonly used public clinical datasets of facial paralysis to demonstrate its effectiveness. Experimental results indicate that the proposed method surpasses state-of-the-art methods, generating more realistic facial images and maintaining identity consistency.

Problem

• Diagnosing facial paralysis relies on subjective clinician judgment
• Scarcity of facial paralysis datasets limits ML model development
• Synthesizing high-quality facial paralysis dataset for accurate algorithm training

Innovation

• Cross-Fusion Cycle Diffusion Model synthesis
• Combines facial features for enhanced details
• Generates realistic facial paralysis images