Three-dimensional dynamic quantitative study of facial movement based on deep neural network

Content

The mean reason which restrict the diagnosis and treatment of facial paralysis is the lack of an objective, accurate and unified facial muscle movement evaluation system. In recent years, AI (Artificial Intelligence) technology has been developing rapidly and gradually applied to the field of medicine science and healthcare, and it provides a new idea for the objective and quantitative and convenient evaluation method of facial muscle movement. With the previous paralysis of three-dimensional dynamic analysis scheme and prototype trial, we will screen and optimize the evaluation index of three-dimensional quantitative measurement of facial nerve paralysis based on deep neural network, including the index of static, dynamic, complications (spasm and synkinesis), aiming to find the characteristics and patterns of the interaction of the different regions of the face. It can provide theoretical and technical support for evaluating the degree, treatment effect, prognosis of facial paralysis and facial reconstruction. The current project is based on the clinical demand, especially for the prognosis of facial paralysis, the continuous measurement will be followed up for more than a half year, facial index curve will be finished, and then explore the prognosis patterns of the disease, for the evaluation of medical or surgical treatment is effective and establish a more scientific and reasonable classification system for the objective basis of facial paralysis. It will provide an objective basis for the evaluation of effectiveness of facial paralysis treatment and establish a more scientific and reasonable facial paralysis grading system.

Poster-PDF A-1642.pdf

Chinese National Natural Science Foundation No.81870735

Conflict of interest

Der Erstautor gibt keinen Interessenskonflikt an.

Publikationsverlauf

Artikel online veröffentlicht:
13. Mai 2021