Patient facial expression recognition method, device and equipment during radiotherapy and storage medium

By recognizing facial expressions of radiotherapy patients and using three-dimensional feature points and classification models to predict the patient's movements, the collision risk between the rack and the patient or the treatment bed in radiotherapy is solved, and the safety and efficiency of treatment are improved.

CN120220204APending Publication Date: 2025-06-27SUZHOU LINATECH MEDICAL SCI & TECH CO LTD
0 Cites 0 Cited by

Patent Information

Application Number
CN202510159882.4
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2025-02-13
Publication Date
2025-06-27

AI Technical Summary

Technical Problem

During the radiation therapy process, the risk of collision between the rack and the patient or the treatment bed is high, resulting in equipment damage, patient injury and treatment quality and safety.

Method used

A patient's facial expression recognition method is adopted during radiotherapy. By obtaining the patient's face three-dimensional point cloud data, three-dimensional feature points are extracted, and combined with two-dimensional feature images to map into the three-dimensional point cloud, calculating the three-dimensional Euclidean distance to build a feature vector, and using classification models to identify the patient's facial expressions, predicting possible dangerous actions of the patient.

Benefits of technology

It realizes accurate identification of patients' emotions and potentially dangerous actions during radiotherapy, ensures the smooth progress of treatment and the safety of patients, and reduces the risk of misjudgment of manual observation.

✦ Generated by Eureka AI based on patent content.
Patent Text Reader

Abstract

The invention discloses a method, a device and equipment for identifying facial expressions of a patient during radiotherapy, and a storage medium. The method comprises the following steps: acquiring face three-dimensional point cloud data of the patient during radiotherapy; extracting a plurality of three-dimensional feature points based on the face three-dimensional point cloud data; extracting a plurality of two-dimensional feature points based on a two-dimensional feature image corresponding to the face three-dimensional point cloud data, and mapping the two-dimensional feature points to the face three-dimensional point cloud data to obtain new three-dimensional feature points; calculating a three-dimensional Euclidean distance among the plurality of three-dimensional feature points based on the obtained three-dimensional feature points, and constructing a feature vector; and classifying the feature vectors by using a classification model, and identifying different facial expressions of the patient during radiotherapy. According to the method, the three-dimensional feature points of the face of the patient are extracted by using an algorithm, and the feature vectors are constructed based on the three-dimensional feature points for analysis, so that the emotion of the patient during radiotherapy is accurately identified, possible dangerous actions of the patient are pre-judged, smooth treatment and safety of the patient are guaranteed, and a physician can better concentrate on radiotherapy work.
Need to check novelty before this filing date? Find Prior Art