CN-119850673-B - Tumor state prediction method, system, equipment and medium

CN119850673BCN 119850673 BCN119850673 BCN 119850673BCN-119850673-B

Abstract

The application relates to the technical field of medical image processing and discloses a method, a system, equipment and a medium for predicting a tumor state, wherein the method, the system, the equipment and the medium comprise the steps of acquiring a CT image group of a lung of a target object in a current respiratory cycle, and constructing a three-dimensional tumor model of the lung tumor based on the CT image group; the method comprises the steps of obtaining a real volume and a real barycenter coordinate of a lung tumor, carrying out finite element analysis to obtain a finite element tumor model, calculating the simulated volume and the simulated barycenter coordinate of the lung tumor, comparing to obtain a volume retention ratio and a barycenter offset, carrying out motion state prediction of the lung tumor in the next respiratory cycle to obtain an initial motion state parameter of the lung tumor in the next respiratory cycle, and if the motion state prediction quality of the lung tumor meets the preset motion state prediction quality based on the volume retention ratio and the barycenter offset, taking the initial motion state parameter as a target motion state parameter, predicting to obtain the motion state of the lung tumor, thereby improving the accuracy and the accuracy of radiotherapy irradiation.

Inventors

HUANG SIJUAN
SHI JIAN
MA LIZHEN
YANG XIN
ZHENG LIHAN
DONG BAIQIANG
LI QIWEN
WU CHENFEI
HUANG XIAOYAN
CHEN MING
ZHAO WUYUAN

Assignees

中山大学
国科离子医疗科技有限公司

Dates

Publication Date: 20260505
Application Date: 20241113

Claims (10)

1. A method of predicting a tumor state, comprising: Acquiring a CT image group of the lung of a target object in a current respiratory cycle, and constructing a three-dimensional tumor model of the lung tumor based on the CT image group, wherein the lung tumor has a real volume and a real centroid coordinate; Performing finite element analysis on the three-dimensional tumor model to obtain a finite element tumor model, and calculating the simulation volume and the simulation centroid coordinates of the lung tumor based on the finite element tumor model; Comparing the real volume and the simulated volume to obtain a volume retention ratio; and comparing the real centroid coordinates with the simulated centroid coordinates to obtain a centroid offset; Predicting the motion state of the lung tumor in the next respiratory cycle by utilizing the finite element tumor model so as to obtain initial motion state parameters of the lung tumor in the next respiratory cycle; And if the motion state prediction quality of the lung tumor is judged to not meet the preset motion state prediction quality based on the volume retention ratio and the gravity center offset, adjusting the parameters of the finite element tumor model to adjust the obtained initial motion state parameters, and judging after adjustment until the motion state prediction quality of the lung tumor is judged to meet the preset motion state prediction quality.
2. The method of claim 1, wherein said constructing a three-dimensional volumetric tumor model of a lung tumor based on said set of CT images comprises: constructing a three-dimensional lung model containing the lung tumor based on the CT image set; And dividing the three-dimensional lung model to obtain a three-dimensional tumor model of the lung tumor.
3. The method of claim 2, wherein determining the true volume and true centroid coordinates of the lung tumor comprises: And acquiring the relative position and the relative size of the lung tumor in the lung based on the three-dimensional tumor model, and calculating the real volume and the real centroid coordinates of the lung tumor based on the relative position and the relative size.
4. The method of claim 1, wherein the finite element analysis of the three-dimensional volumetric tumor model to obtain a finite element tumor model comprises: Performing optimization processing on the three-dimensional tumor model to obtain a three-dimensional solid tumor model, wherein the optimization processing comprises at least one of grid division processing, defect repair processing, error repair processing and accurate curved surface processing; and carrying out finite element analysis on the three-dimensional solid tumor model to obtain a finite element tumor model.
5. The method of claim 4, wherein the three-dimensional tumor model is meshing processed by: grid parameters are set for the three-dimensional tumor model, the grid parameters comprise grid density parameters and edge smoothness parameters, and grid division is conducted on the three-dimensional tumor model based on the grid density parameters and the edge smoothness parameters.
6. The method of claim 1, wherein the calculating a simulated volume and simulated centroid coordinates of the lung tumor based on the finite element tumor model comprises: setting an elastic modulus and a poisson ratio of the lung tumor based on the finite element tumor model, the elastic modulus and the poisson ratio being used to characterize material properties of the lung tumor; And calculating the simulation volume and the simulation centroid coordinates of the lung tumor based on the elastic modulus and the poisson ratio.
7. The method of claim 1 or 6, wherein the initial motion state parameters include stress parameters, strain parameters, and displacement parameters; the predicting the motion state of the lung tumor in the next respiratory cycle by using the finite element tumor model comprises the following steps: setting analysis duration and step size of motion state prediction, and performing motion state prediction of the lung tumor in the next respiratory cycle by using the finite element tumor model based on the analysis duration and the step size.
8. The tumor state prediction system is characterized by comprising an acquisition module, an analysis module, a comparison module, a state prediction module and a quality judgment module; The acquisition module is configured to acquire a CT image group of the lung of a target object in the current respiratory cycle, and construct a three-dimensional tumor model of the lung tumor based on the CT image group, wherein the lung tumor has a real volume and a real centroid coordinate; The analysis module is configured to perform finite element analysis on the three-dimensional tumor model to obtain a finite element tumor model, and calculate a simulation volume and a simulation centroid coordinate of the lung tumor based on the finite element tumor model; the comparison module is configured to compare the real entity and the simulation volume to obtain a volume retention ratio, and compare the real centroid coordinate and the simulation centroid coordinate to obtain a centroid offset; the state prediction module is configured to predict the motion state of the lung tumor in the next respiratory cycle by utilizing the finite element tumor model so as to obtain initial motion state parameters of the lung tumor in the next respiratory cycle; The mass determination module is configured to determine the initial motion state parameter as a target motion state parameter of the lung tumor in the next respiratory cycle if the motion state prediction mass of the lung tumor meets a preset motion state prediction mass based on the volume retention ratio and the center of gravity offset.
9. A computer device, comprising: A memory and a processor, said memory and said processor being communicatively coupled to each other, said memory having stored therein computer instructions, said processor executing said computer instructions to perform a method of predicting a tumor status according to any one of claims 1 to 7.
10. A computer-readable storage medium having stored thereon computer instructions for causing a computer to perform a tumor status prediction method according to any one of claims 1 to 7.

Description

Tumor state prediction method, system, equipment and medium Technical Field The present application relates to the field of medical image processing technologies, and in particular, to a method, a system, an apparatus, and a medium for predicting a tumor state. Background The mechanical properties of the lung are non-uniform in space, and the physiological structure of the chest has a limiting effect on the movement of the lung, so that the movement behaviors of the lung tumor such as growth, expansion or metastasis of the lung are anisotropic in nature and show different properties in different directions. However, in the related art, the motion of the lung tumor is often described clinically by using uniformly distributed outer expansion boundaries, so that the prediction of the motion state of the lung tumor is not accurate enough, and a doctor is not enough to conform to a real tumor area when making a radiation plan, and a new tumor state prediction method needs to be provided. Disclosure of Invention The application provides a tumor state prediction method, a system, equipment and a medium, which predict the motion state of a lung tumor by modeling and simulating the lung tumor, solve the technical problem that the prediction of the motion state of the lung tumor is not accurate enough in the related art, and achieve the technical effects of accurately predicting the motion state of the lung tumor so as to improve the accuracy and the correctness of radiotherapy irradiation. In order to achieve the above purpose, the main technical scheme adopted by the application comprises the following steps: in a first aspect, an embodiment of the present application provides a method for predicting a tumor state, including: Acquiring a CT image group of the lung of a target object in a current respiratory cycle, and constructing a three-dimensional tumor model of the lung tumor based on the CT image group, wherein the lung tumor has a real volume and a real centroid coordinate; Performing finite element analysis on the three-dimensional tumor model to obtain a finite element tumor model, and calculating the simulation volume and the simulation centroid coordinates of the lung tumor based on the finite element tumor model; Comparing the real volume and the simulated volume to obtain a volume retention ratio; and comparing the real centroid coordinates with the simulated centroid coordinates to obtain a centroid offset; Predicting the motion state of the lung tumor in the next respiratory cycle by utilizing the finite element tumor model so as to obtain initial motion state parameters of the lung tumor in the next respiratory cycle; And if the motion state prediction quality of the lung tumor meets the preset motion state prediction quality based on the volume retention ratio and the gravity center offset, taking the initial motion state parameter as a target motion state parameter of the lung tumor in the next respiratory cycle. According to the application, a two-dimensional 4D-CT image of the lung of a patient is converted into a three-dimensional tumor model which has a spatial sense and can be observed and measured at multiple angles in a biophysical modeling and simulation mode, and finite element analysis is carried out to simulate the state of the lung tumor under respiratory motion so as to predict the motion state of the lung tumor. By enabling the motion state prediction quality to meet the preset motion state prediction quality, accuracy of the target motion state parameters is guaranteed. According to the specific conditions of different target objects, a personalized radiotherapy scheme is designed, the motion trail and range of lung tumors of different target objects are predicted, and the boundary of a radiotherapy target area is timely reduced so as to protect normal tissues. Not only ensures that the lung tumor obtains sufficient radiation, but also reduces the damage to normal tissues in the lung, and improves the accuracy and the accuracy of radiotherapy irradiation. The application omits the complex rib movement of the chest, does not have the complex segmentation of diaphragm, does not consider the influence of posture and gravity load, reduces modeling difficulty and modeling time cost, ensures the timeliness of radiotherapy treatment, and overcomes the problems of high modeling difficulty and low simulation accuracy caused by extracting lung tumors through simulating lung respiratory movement in the related technology. Optionally, the constructing a three-dimensional tumor model of the lung tumor based on the CT image group includes: constructing a three-dimensional lung model containing the lung tumor based on the CT image set; And dividing the three-dimensional lung model to obtain a three-dimensional tumor model of the lung tumor. Optionally, determining the true volume and true centroid coordinates of the lung tumor comprises: And acquiring the relative position and the relative size of