US-20260123997-A1 - MARKER POSITIONING METHOD, DEVICE AND SYSTEM BASED ON MODEL FUSION

US20260123997A1US 20260123997 A1US20260123997 A1US 20260123997A1US-20260123997-A1

Abstract

Provided are a marker positioning method, device and system based on model fusion, which are applicable to the technical field of intelligent manufacturing. The method includes the following steps: acquiring pre-scanning data corresponding to a target site of a patient; constructing a structural model corresponding to the target site of the patient by using the pre-scanning data, the structural model containing surface features and internal features of the target site; acquiring surface scanning data corresponding to the target site of the patient; constructing a surface contour model on the basis of the surface scanning data; and fusing the structural model and the surface contour model to obtain a surgical guidance model, the surgical guidance model indicating position parameters of a marker.

Inventors

Dan Tang

Assignees

Hunan Zhuoshi Chuangsi Technology Co., Ltd.

Dates

Publication Date: 20260507
Application Date: 20260104
Priority Date: 20230706

Claims (10)

1 . A marker positioning method based on model fusion, comprising the following steps: acquiring pre-scanning data corresponding to a target site of a patient, wherein the pre-scanning data are scanning data acquired before setting a marker on a surface of the target site of the patient; and the marker comprises an artificial marker set on the surface; constructing a structural model corresponding to the target site of the patient by using the pre-scanning data, wherein the structural model contains surface features and internal features of the target site; acquiring surface scanning data corresponding to the target site of the patient, wherein the surface scanning data are scanning data corresponding to the surface of the target site of the patient after setting the marker on the surface of the target site of the patient; constructing a surface contour model on the basis of the surface scanning data, wherein the surface contour model comprises the surface features and position parameters of the marker; and fusing the structural model and the surface contour model to obtain a surgical guidance model, wherein the surgical guidance model indicates the position parameters of the marker.
2 . The method according to claim 1 , wherein the pre-scanning data comprise CT/MR scanning data; and the surface scanning data comprise scanning data acquired by a three-dimensional scanner.
3 . The method according to claim 1 , wherein the pre-scanning data comprise a tomographic image; and the step of constructing the structural model corresponding to the target site of the patient by using the pre-scanning data, comprises: determining a surface contour structure according to a peripheral shape of the tomographic image; determining an internal tissue structure according to inner features of the tomographic image; and constructing the structural model corresponding to the target site of the patient according to the surface contour structure and the internal tissue structure.
4 . The method according to claim 1 , wherein the step of constructing the surface contour model on the basis of the surface scanning data, comprises: constructing a candidate scanning model according to the surface scanning data; and identifying and removing a background region from the candidate scanning model to obtain the surface contour model.
5 . The method according to claim 1 , wherein the step of fusing the structural model and the surface contour model to obtain the surgical guidance model, comprises: determining outer contour features of the surface contour model; and fusing the structural model and the surface contour model to obtain the surgical guidance model on the basis of the outer contour features of the surface contour model and the surface features of the structural model.
6 . The method according to claim 1 , wherein, after the step of fusing the structural model and the surface contour model to obtain the surgical guidance model, the method further comprises the following steps: determining position parameters of a lesion according to internal features in the surgical guidance model; and constructing a surgical approach by using the position parameters of the lesion, wherein the surgical approach has a pose relationship corresponding to position parameters of each marker.
7 . The method according to claim 1 , wherein, after the step of fusing the structural model and the surface contour model to obtain the surgical guidance model, the method further comprises the following steps: determining a model registration accuracy according to the surgical guidance model; and when the model registration accuracy meets a model fusion requirement, applying the surgical guidance model to a surgery, or when the model registration accuracy does not meet the model fusion requirement, adjusting the surgical guidance model.
8 . A marker positioning device based on model fusion, comprising: a pre-scanning data acquiring module, configured for acquiring pre-scanning data corresponding to a target site of a patient, wherein the pre-scanning data are scanning data acquired before setting a marker on a surface of the target site of the patient; and the marker comprises an artificial marker set on the surface; a structural model constructing module, configured for constructing a structural model corresponding to the target site of the patient by using the pre-scanning data, wherein the structural model contains surface features and internal features of the target site; a surface scanning data acquiring module, configured for acquiring surface scanning data corresponding to the target site of the patient, wherein the surface scanning data are scanning data corresponding to the surface of the target site of the patient after setting the marker on the surface of the target site of the patient; a surface contour model constructing module, configured for constructing a surface contour model on the basis of the surface scanning data, wherein the surface contour model comprises the surface features and position parameters of the marker; and a model fusing module, configured for fusing the structural model and the surface contour model to obtain a surgical guidance model, wherein the surgical guidance model indicates the position parameters of the marker.
9 . A marker positioning system based on model fusion, comprising a pre-scanning device, a three-dimensional scanning device and a computing device; wherein, the pre-scanning device is used for scanning a target site of a patient to obtain pre-scanning data, wherein the pre-scanning data are scanning data acquired before setting a marker on a surface of the target site of the patient; the pre-scanning data comprise data obtained by scanning surface and internal parts; and the marker comprises an artificial marker set on the surface; the three-dimensional scanning device is used for scanning the target site of the patient to obtain surface scanning data, wherein the surface scanning data are scanning data corresponding to the surface of the target site of the patient after setting the marker on the surface of the target site of the patient; and the computing device stores a computer program/instruction, and the computing device is used for acquiring the pre-scanning data and the surface scanning data, and executing the computer program/instruction to implement the steps of the method according to any one of claims 1 to 7 .
10 . A computer storage medium, on which a computer program/instruction is stored, wherein, the computer program/instruction, when executed, is used for implementing the steps of the method according to any one of claims 1 to 7 .

Description

CROSS-REFERENCE TO RELATED APPLICATIONS This application is a continuation of International Patent Application No. PCT/CN 2024/104088 with a filing date of Jul. 5, 2024, designating the United States, now pending, and further claims priority to Chinese Patent Application No. 202310825931.4 with a filing date of Jul. 6, 2023. The content of the aforementioned applications, including any intervening amendments thereto, are incorporated herein by reference. TECHNICAL FIELD The embodiments in the specification relate to the technical field of intelligent manufacturing, particularly to a marker positioning method, device and system based on model fusion. BACKGROUND OF THE PRESENT INVENTION It is very important to determine a position of a deep structure of a patient when performing a surgery. A tomographic image of a scanned site can be acquired by CT or MR scanning, and then a relative position relationship between an internal deep structure and a surface marker structure can be acquired by a three-dimensional reconstruction technology, so that the position of the deep structure is positioned on the basis of a position of a surface recognizable structure during the surgery, for example, a position of an internal hematoma is positioned through a position of a surface marker, such as an external auditory canal and an eye, so as to plan a surgical approach. However, in practical application, due to the lack of obvious recognizable structures in some surgical sites, such as the absence of the marker structure on a surface of brain, the low resolving accuracy of the recognizable structure on a surface of the site, and other factors, the positioning performed by directly using the surface recognizable structure in some application scenarios is poor in effect and accuracy. Aiming at this problem, an artificial marker, such as an electrode patch, a fiducial marker, a skull pin and a stereotactic frame, may be set on the surface of the surgical site of the patient, and then the artificial marker is identified and positioned. At present, when the marker is used, the marker is usually attached to a specific position of the surgical site of the patient first, then the patient is subjected to CT scanning, and finally, CT scanning results acquired include overall scanning results of the surgical site and position information of the marker at the same time. However, this method has a high requirement of coordination between a marker device and radiology scanning, which cannot even be completed in an emergency surgery. In addition, this method needs to ensure that the position of the marker must be fixed from the setting of the marker to the execution of surgery, but a non-invasive marker is difficult to meet this requirement, while an invasive marker may bring an additional wound to the patient. At present, the method of positioning the depth structure on the basis of the marker does not have good application effect. Therefore, there is an urgent need for a convenient and effective positioning method based on the marker. SUMMARY OF THE PRESENT INVENTION The embodiments in the specification aim to provide a marker positioning method, device and system based on model fusion, so as to solve the problem about how to position a marker conveniently and effectively. In order to solve the above technical problem, the embodiments in the specification provide a marker positioning method based on model fusion, which includes the following steps: acquiring pre-scanning data corresponding to a target site of a patient, wherein the pre-scanning data are scanning data acquired before setting a marker on a surface of the target site of the patient; constructing a structural model corresponding to the target site of the patient by using the pre-scanning data, wherein the structural model contains surface features and internal features of the target site; acquiring surface scanning data corresponding to the target site of the patient, wherein the surface scanning data are scanning data corresponding to the surface of the target site of the patient after setting the marker on the surface of the target site of the patient; constructing a surface contour model on the basis of the surface scanning data; and fusing the structural model and the surface contour model to obtain a surgical guidance model, wherein the surgical guidance model indicates the position parameters of the marker. In some embodiments, the pre-scanning data include CT/MR scanning data; and the surface scanning data include scanning data acquired by a three-dimensional scanner. In some embodiments, the pre-scanning data include a tomographic image; and the step of constructing the structural model corresponding to the target site of the patient by using the pre-scanning data, includes: determining a surface contour structure according to a peripheral shape of the tomographic image; determining an internal tissue structure according to inner features of the tomographic image; and