Computer-implemented method for operating an imaging x-ray apparatus, x-ray apparatus, computer program product and electronically readable data carrier
By using a trained position determination function in an imaging X-ray device, and leveraging machine learning and CNN techniques, the virtual patient model is automatically located, solving the problem of inaccurate positioning in existing technologies and improving the accuracy and efficiency of dose information calculation.
Patent Information
- Authority / Receiving Office
- CN Β· China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SIEMENS HEALTHINEERS AG
- Filing Date
- 2025-12-02
- Publication Date
- 2026-06-05
AI Technical Summary
In existing technologies, imaging X-ray equipment suffers from insufficient accuracy in locating virtual patient models, especially in the coordinate system of the imaging X-ray equipment, which makes it difficult to accurately locate the patient model and leads to inaccurate dose information calculation.
A trained position determination function is used to automatically locate a virtual patient model based on the patient's X-ray images using machine learning methods. The position of the patient model in the X-ray equipment coordinate system is determined by analyzing the X-ray images through a convolutional neural network (CNN) and an encoder, thus avoiding the need for additional sensor technology.
It achieves accurate positioning of the virtual patient model in the X-ray equipment coordinate system, improves the accuracy of dose information calculation, reduces user errors, saves time, and does not require additional hardware equipment.
Smart Images

Figure CN122156448A_ABST