PtosisDiffusion: a training-free workflow for precisely predicting post-operative appearance in blepharoptosis patients based on diffusion models.

Abstract

<h4>Purpose</h4>This study aims to develop a diffusion-based workflow to precisely predict postoperative appearance in blepharoptosis patients.<h4>Methods</h4>We developed PtosisDiffusion, a training-free workflow that combines face mesh with ControlNet for accurate post-operative predictions, and evaluated it using 39 preoperative photos from blepharoptosis patients. The performance of PtosisDiffusion was compared against three other diffusion-based methods: Conditional Diffusion, Repaint, and Dragon Diffusion.<h4>Results</h4>PtosisDiffusion demonstrated superior performance in subjective evaluations, including overall rating, correction, and double eyelid formation. Statistical analyses confirmed that PtosisDiffusion achieved the highest overlap ratio (0.87 ± 0.07) and an MPLPD ratio close to 1 (1.01 ± 0.10). The model also showed robustness in extreme cases, and ablation studies confirmed the necessity of each model component.<h4>Conclusion</h4>PtosisDiffusion generates accurate postoperative appearance predictions for ptosis patients using only preoperative photographs. Among the four models tested, PtosisDiffusion consistently outperformed the others in both subjective and statistical evaluation.