Automatic evaluation of the degree of facial nerve paralysis

doi:10.1007/s11042-015-2696-0

Paper

Automatic evaluation of the degree of facial nerve paralysis

Published Jun 5, 2015 · Ting Wang, Shu Zhang, Junyu Dong

Multimedia Tools and Applications

Q1 SJR score

55

Citations

1

Influential Citations

Full text

Semantic Scholar

Abstract

Facial paralysis affects both mental and physical health of patients. Evaluation of facial paralysis in clinical practice is normally based on the static facial asymmetry at the maximal movement state and the dynamic change of facial muscle movement. However, most existing research only considers one of these two aspects when evaluating the degree of facial paralysis. This will result in an incomplete utilization of the diagnosis information leading to a low evaluation accuracy, or even misjudgment. In this paper, a novel method is presented for evaluating the degree of facial paralysis considering both static facial asymmetry and dynamic transformation factors. A quantitative approach of static facial asymmetry based on local mirror asymmetry is proposed. The method compares the differences of the corresponding local regions between both sides of the face. This makes it effective analyzing the left and right side asymmetry for abnormal faces. A quantitative evaluation of static facial asymmetry is achieved through three steps: localization of local facial regions, extraction of asymmetry features and quantification of bilateral facial asymmetry. Once the static facial asymmetry is quantified, its dynamic counterparts can be calculated using the speed of changings in different regions caused by facial muscle movement. Then we combine the static and dynamic quantification results to evaluate the degree of facial nerve paralysis. The efficiency and effectiveness of the proposed method have been tested using our facial paralysis database with 62 patients. The experiments show that our method produced encouraging performance compared with ground truth.

Study Snapshot

Key takeawayOur novel method effectively evaluates facial paralysis by considering both static facial asymmetry and dynamic transformation factors, improving evaluation accuracy.

PopulationOlder adults (50-71 years)

Sample size24

MethodsObservational

OutcomesBody Mass Index projections

ResultsSocial networks mitigate obesity in older groups.

Sign up to use Study Snapshot

Consensus is limited without an account. Create an account or sign in to get more searches and use the Study Snapshot.

Create an account

Paper

Automatic evaluation of the degree of facial nerve paralysis

Sign up to use Study Snapshot

References

Analysis of Facial Paralysis Disease using Image Processing Technique

The IECM algorithm effectively evaluates facial paralysis degrees by analyzing facial expressions and measuring distances between eye brows, infra orbital, and mouth edges.

A preliminary investigation into the use of machine vision techniques for automating facial paralysis rehabilitation therapy

Machine vision techniques show potential in developing an automatic feedback system for facial paralysis rehabilitation therapy, potentially enhancing patient engagement, performance, efficacy, and outcome.

Evaluation of Facial Paralysis Degree Based on Regions

This study proposes a new method to estimate facial paralysis degree by comparing multiple facial regions, using four images for each movement.

Facial expression recognition based on Local Binary Patterns: A comprehensive study

Local Binary Patterns (LBP) are effective and efficient for person-independent facial expression recognition, even in low-resolution images and video sequences.

Quantitative Analysis of Facial Paralysis Using Local Binary Patterns in Biomedical Videos

This paper presents a novel framework for objective measurement of facial paralysis using local binary patterns in biomedical videos, demonstrating its accuracy and efficiency in evaluating facial symmetry.

An Approach for Quantitative Evaluation of the Degree of Facial Paralysis Based on Salient Point Detection

The proposed method effectively estimates the degree of facial paralysis using salient point detection, providing a more accurate evaluation for patients.

Biomedical Image Sequence Analysis with Application to Automatic Quantitative Assessment of Facial Paralysis

This paper presents an automatic facial paralysis assessment system using video data, with the radial basis function neural network showing superior performance.

Automated Facial Image Analysis: Detecting Improvement in Abnormal Facial Movement After Treatment With Botulinum Toxin A

Automated Facial Image Analysis (AFA) can detect subtle changes in facial movement after Botox injections, detecting improvements in abnormal facial movements in patients with facial nerve disorders.

Objective grading of facial paralysis using artificial intelligence analysis of video data

This AI-based system accurately quantifies facial paralysis using video data, providing a quantitative, reliable tool for assessing patients' condition in neurootology.

Citations

Artificial Intelligence-Based Facial Palsy Evaluation: A Survey

AI-based facial palsy evaluation shows promise in improving facial functional treatment and rehabilitation, but current research challenges and future directions need to be addressed.

Facial paralysis classification method integrated with generative adversarial network

A facial palsy classification model incorporating generative adversarial networks achieves higher classification accuracy compared to methods without data augmentation, improving clinical applications.

ALGRNet: Multi-Relational Adaptive Facial Action Unit Modelling for Face Representation and Relevant Recognitions

ALGRNet effectively estimates the severity of facial paralysis by analyzing facial action units and their relationships with facial appearance and texture changes.

AFLFP: A Database With Annotated Facial Landmarks for Facial Palsy

The AFLFP database effectively detects facial landmarks in facial palsy images, outperforming mainstream machine- and deep-learning methods.

Automatic Evaluation of Facial Paralysis with Transfer Learning and Improved ResNet34 Neural Network

This paper proposes an objective facial paralysis assessment method using transfer learning and an improved ResNet34 network model, achieving 97%, 87%, and 88% accuracy rates for eyes, nasolabial folds, and mouth.

Automatic Facial Palsy, Age and Gender Detection Using a Raspberry Pi

This study proposes a real-time facial palsy detection system using a Raspberry Pi and deep learning algorithm, achieving 98% accuracy and facilitating diagnosis for both doctors and patients.

DeepSmile: Anomaly Detection Software for Facial Movement Assessment

DeepSmile, an open-source deep learning model, effectively assesses facial movements during smiling, improving diagnosis, follow-up, drug therapy, and surgical treatment.