Automatic Grading of Palsy Using Asymmetrical Facial Features: A Study Complemented by New Solutions

Abstract

Facial palsy caused by nerve damage results in loss of facial symmetry and expression. A reliable palsy grading system for large-scale applications is still missing in the literature. Although numerous approaches have been reported on facial palsy quantification and grading, most employ hand-crafted features on relatively smaller datasets which limit the classification accuracy due to non-optimal face representation. In contrast, convolutional neural networks (CNNs) automatically learn the discriminative features facilitating the accurate classification of underlying tasks. In this paper, we propose to apply a typical deep network on a large dataset to extract palsy-specific features from face images. To prevent the inherent limitation of overfitting frequently occurring in CNNs, a generative adversial network (GAN) is applied to augment the training dataset. The deeply learned features are then used to classify the palsy disease into five benchmarked grades. The experimental results show that the proposed approach offers superior palsy grading performance compared to some existing methods. Such an approach is useful for palsy grading at large scale, such as primary health care.

Region Based Parallel Hierarchy Convolutional Neural Network for Automatic Facial Nerve Paralysis Evaluation

“…The accuracy of landmark directly affects the line segment map. Sajid et al [28] proposed a CNN-based model combined with a data augmentation strategy to classify facial palsy images into five grades. It claimed to be the first study for palsy grade classification on a large dataset.…”

Content‐Based Image Retrieval and Feature Extraction: A Comprehensive Review

“…Asymmetric face features have been used to grade face palsy disease in [101]. More specifically, the generative adversarial network (GAN) has been used to estimate the severity of facial palsy disease for a given face image.…”

“…In the above-presented studies [98][99][100][101][102][103][104][105], handcrafted and deeply learned face features have been introduced for robust face recognition.…”

Neurologist Standard Classification of Facial Nerve Paralysis with Deep Neural Networks

“…Sajid et al [24] used a CNN model to classify face images with FNP into the five distinct degrees established by House and Brackmann. Sajid used GAN to prevent overfitting in training (Column 3, VGG-16 Net with GAN).…”

“…Esteva et al [15] used a pretrained GoogleNet Inception v3 CNN on skin cancer classification, which matched the performance of dermatologists in three key diagnostic tasks: melanoma classification, melanoma classification using dermoscopy, and carcinoma classification. Sajid et al [24] used a CNN model to classify facial images affected by FNP into the five distinct degrees established by House and Brackmann. Sajid used a Generative Adversarial Network (GAN) to prevent overfitting in training.…”