Median sagittal plane construction method based on artificial neural network model

Abstract

The invention relates to a median sagittal plane construction method based on an artificial neural network model. The method comprises the following steps: (1) establishing an artificial neural network model suitable for constructing the median sagittal plane through a three-dimensional face data PA association method; and (2) establishing an intelligent weight regulation and control mechanism ofthe artificial network model aiming at the PA anatomical mark point, and realizing a training mode and a feedback mechanism of the expert-level logic strategy. According to the method, the artificialneural network algorithm model can be applied to symmetry analysis of oral medical three-dimensional face data, an algorithm idea of constructing a median sagittal plane through an 'artificial neuralnetwork PA association method' is innovatively provided, intelligent weight regulation and control of PA mark points are achieved, and the effect of simulating a clinical expert-level diagnosis strategy is achieved.

Description

technical field [0001] The invention relates to applying an artificial neural network algorithm model to the symmetry analysis of three-dimensional facial data in stomatology; in particular, it relates to a method for constructing a median sagittal plane based on an artificial neural network model. Background technique [0002] Facial symmetry analysis is a clinical basic problem closely related to multiple disciplines of stomatology, such as the design of orthognathic surgery in oral and maxillofacial surgery, the design of craniofacial repair surgery in trauma and tumor surgery, the design of orthodontic treatment programs and In terms of oral aesthetic restoration design, facial symmetry analysis is a key link, and the construction of the median sagittal plane (MSP) is the premise and basis for facial symmetry analysis. [0003] Under the new model of "three-dimensional" and "digital" oral medicine that is becoming mainstream today, all kinds of digital orthognathic surge...

AI Technical Summary

Problems solved by technology

[0008] The characteristic of the "landmark point method" is that the doctor can select an anatomical landmark point with good symmetry suitable for the patient's individualized facial features to determine the median sagittal plane according to his own subjective experience. High dependence, poor reproducibility of the method between different users and different patients (especially in the case of complex facial deformities), it is difficult to form a common method with certain clinical universality, and the development prospect of related automatic algorithms is not good good

[0009] (2) The method of constructing the median sagittal plane based on the ontology-mirror association model has developed rapidly and become the mainstream, but it does not take into account the subjective factors of doctors well

Although this has improved the universality of the ICP algorithm for complex facial deformities to a certain extent, due to the re-introduction of human intervention, it is necessary to rely on the subjective experience of senior doctors for area selection and exclusion, which also reduces the promotion and popularization of the algorithm at the grassroots level. The advantages

[0017] In addition, the ICP or regional ICP correlation method also has an inherent limitation of the algorithm: the three-dimensional data provides a wealth of facial information, which plays a different role in assisting doctors in symmetry analysis clinically. Some important landmark points of facial anatomy (such as inner canthus, outer canthus, corner of mouth, glabella, nasion, tip of nose, front of chin, etc.) occupy a higher reference value, and the three-dimensional shape of the facial feature area (such as nose tip area, chin area, etc.) followed by non-characteristic area shape (such as cheek area, forehead area, etc.) followed by

However, there are only studies on the discrimination of two-dimensional medical image features and disease classification and diagnosis, and there are no related reports in the field of symmetry analysis of three-dimensional facial digital models.

Images