Development and validation of a collaborative framework for assessment of peripheral facial paralysis using facial image regions of interest.

Abstract

Background: While accurate evaluation of PFP is crucial for determining optimal treatment strategies, current clinical assessments rely heavily on subjective evaluations, leading to considerable variability between inter- and intra-observer ratings.

Objective: This study aimed to develop and validate a collaborative framework for evaluating PFP based on regions of interest in facial images.

Methods: We developed and tested two approaches: (1) a collaborative framework integrating image interpretation techniques (representation learning via CNN) with predefined handcrafted features based on regions of interest in facial images, and (2) a convolutional neural network (CNN) model trained exclusively on full-face patient images. The diagnostic accuracy of both systems was evaluated using a test set and compared with otologists' assessments.

Results: The collaborative framework achieved a mean Area Under the Curve (AUC) of 0.92 for PFP prediction in the test set, surpassing the 0.76 AUC achieved by the CNN trained on full-face images. The framework's performance matched that of experienced otologists (accuracy: 80.0% vs. 77.2%; sensitivity: 85.3% vs. 77.7%). Moreover, system assistance improved primary clinicians' mean accuracy by 17.7 percentage points.

Conclusions: These findings demonstrate that our collaborative framework-based automated diagnosis system can effectively assist clinicians in PFP diagnosis.