# Quantitative Assessment of Facial Paralysis Using Dynamic 3D Photogrammetry and Deep Learning: A Hybrid Approach Integrating Expert Consensus

## TL;DR

A new method using 3D imaging and deep learning accurately assesses facial paralysis, outperforming traditional subjective evaluations.

## Contribution

A hybrid approach combining dynamic 3D photogrammetry and expert consensus with PointNet for objective facial paralysis assessment.

## Key findings

- The new approach achieved an accuracy exceeding 95% in assessing facial paralysis.
- The objective method outperformed subjective clinical assessments in reproducibility.
- PointNet effectively integrated facial movement data with expert grading for severity quantification.

## Abstract

PointNet trained with preprocessed point clouds of facial movements can provide accurate assessment of facial paralysis.

What are the main findings?

The accuracy of the new approach was higher than 95%.

The objective approach offers better assessment than the subjective approach.

What are the implications of the main findings?

The automated objective assessment of facial paralysis is achievable.

The deep learning approach enhanced dynamic 3D photogrammetry for facial paralysis assessment.

The subjective assessment of facial paralysis relies on the expertise of clinicians; the main limitation is intra-observer and inter-observer reproducibility. In this paper, we proposed a deep learning approach combining point clouds of facial movements with expert consensus to objectively quantify the severity of facial paralysis. A dynamic 3D photogrammetry imaging system was used to capture the facial movements of five facial expressions. Point clouds of the face at rest and at maximum expressions were extracted. These were integrated with the experts grading of the severity of facial paralysis to train a PointNet network to quantify the severity of facial paralysis. The results showed an accuracy exceeding 95% for assessing facial paralysis.