Systems and methods for determining position of region of interest

1. A system for positioning a region of interest (ROI) of an object, comprising:

at least one storage device including a set of instructions; and

at least one processor in communication with the at least one storage device, wherein when executing the set of instructions, the at least one processor is directed to perform operations including:

obtaining an initial image of the object acquired by performing a preliminary scan on the object using an imaging device;

obtaining geometric information of the ROI in the initial image, the geometric information of the ROI includes a size and a shape of the ROI; and

obtaining an image of the object that is acquired by performing, using the imaging device, a tracker scan on the object to monitor a concentration of a contrast agent in the ROI;

obtaining feature information of the ROI in the object based on the image, the feature information of the ROI including imaging parameter information associated with the ROI, the imaging parameter information corresponding to the concentration of the contrast agent; and

determining position information of the ROI in the image using a positioning model based on the geometric information of the ROI in the initial image and the feature information of the ROI.

2. The system of claim 1 , wherein the obtaining feature information of the ROI in the object includes:

obtaining marking information of the ROI from the initial image of the object, the marking information including at least one of a size of the ROI, a shape of the ROI, or a position of the ROI in the initial image; and

obtaining the feature information of the ROI.

3. The system of claim 1 , wherein:

the feature information of the ROI further includes at least one of the size of the ROI, the shape of the ROI, an anatomical feature of the ROI, or pixel information associated with the ROI.

4. The system of claim 1 , wherein the imaging parameter information associated with the ROI includes at least one of CT values of the ROI, an average CT value of the ROI, a variance of the CT values of the ROI, or a contrast of the ROI in a subtraction image of the image.

5. The system of claim 3 , wherein the at least one processor is directed to perform the operations further including:

updating the imaging parameter information associated with the ROI based on the position information of the ROI in the image;

determining whether the updated imaging parameter information associated with the ROI satisfies a condition relating to the concentration of the contrast agent; and

performing imaging operations based on a determination result of whether the imaging parameter information associated with the ROI satisfies the condition.

6. The system of claim 5 , wherein:

the determination result includes that the updated imaging parameter information associated with the ROI satisfies the condition; and

the imaging operations include:

obtaining a second image of the object captured by the imaging device at a second time point subsequent to a first time point when the image is acquired;

identifying the ROI in the second image using the positioning model based on image information of the second image and feature information of the ROI in the second image; and

determining whether updated imaging parameter information associated with the ROI in the second image satisfies the condition.

7. The system of claim 5 , wherein:

the determination result includes that the updated imaging parameter information associated with the ROI does not satisfy the condition; and

the imaging operations include performing a medical procedure on the object.

8. The system of claim 5 , wherein the at least one processor is directed to perform operations further including:

determining a curve indicating a change of the updated imaging parameter information associated with the ROI corresponding to a plurality of images acquired at different time points; and

transmitting the curve to a terminal device for displaying.

9. The system of claim 1 , wherein the determining position information of the ROI in the image using a positioning model based on the geometric information of the ROI in the initial image and the feature information of the ROI includes:

inputting the geometric information of the ROI in the initial image and the feature information of the ROI into the positioning model; and

determining the position information of the ROI in the image based on an output of the positioning model.

10. The system of claim 9 , wherein the positioning model is obtained by a training process including:

obtaining a plurality of training samples, each of the plurality of training samples including a sample image, image information of the sample image, an ROI in the sample image, feature information of the ROI in the sample image, and reference position information of the ROI in the sample image; and

obtaining the positioning model by training a preliminary positioning model based on the plurality of training samples.

11. The system of claim 1 , wherein the positioning model includes a machine learning model or a regression model.

12. A method for positioning a region of interest (ROI) of an object, the method being implemented on a computing device including at least one processor and at least one storage device, the method comprising:

obtaining an initial image of the object acquired by performing a preliminary scan on the object using an imaging device;

obtaining geometric information of the ROI in the initial image, the geometric information of the ROI including a size and a shape of the ROI;

obtaining an image of the object that is acquired by performing, using the imaging device, a tracker scan on the object to monitor a concentration of a contrast agent in the ROI;

obtaining feature information of the ROI in the object based on the image, the feature information of the ROI including imaging parameter information associated with the ROI, the imaging parameter information corresponding to the concentration of the contrast agent; and

determining position information of the ROI in the image using a positioning model based on the geometric information of the ROI in the initial image and the feature information of the ROI.

13. The method of claim 12 , wherein the obtaining feature information of the ROI in the object includes:

obtaining marking information of the ROI from the initial image of the object, the marking information including at least one of a size of the ROI, a shape of the ROI, or a position of the ROI in the initial image; and

obtaining the feature information of the ROI.

14. The method of claim 12 , wherein:

the feature information of the ROI further includes at least one of the size of the ROI, the shape of the ROI, an anatomical feature of the ROI, or pixel information associated with the ROI.

15. The method of claim 12 , wherein the imaging parameter information associated with the ROI includes at least one of CT values of the ROI, an average CT value of the ROI, a variance of the CT values of the ROI, or a contrast of the ROI in a subtraction image of the image.

16. The method of claim 14 , the method further comprising:

updating the imaging parameter information associated with the ROI based on the determined position information of the ROI in the image;

determining whether the updated imaging parameter information associated with the ROI satisfies a condition relating to the concentration of the contrast agent; and

performing imaging operations based on a determination result of whether the imaging parameter information associated with the ROI satisfies the condition.

17. The method of claim 12 , wherein the positioning model is obtained by a training process including:

obtaining a plurality of training samples, each of the plurality of training samples including a sample image, image information of the sample image, an ROI in the sample image, feature information of the ROI in the sample image, and reference position information of the ROI in the sample image; and

obtaining the positioning model by training a preliminary positioning model based on the plurality of training samples.

18. A non-transitory computer readable medium, comprising executable instructions that, when executed by at least one processor, direct the at least one processor to perform a method, the method comprising:

obtaining an initial image of an object acquired by performing a preliminary scan on the object using an imaging device;

obtaining geometric information of a region of interest (ROI) of the object in the initial image, the geometric information of the ROI including a size and shape of the ROI;

obtaining an image of the object that is acquired by performing, using the imaging device, a tracker scan on the object to monitor a concentration of a contrast agent in the ROI;

obtaining feature information of the ROI in the object based on the image, the feature information of the ROI including imaging parameter information associated with the ROI, the imaging parameter information corresponding to the concentration of the contrast agent; and

determining position information of the ROI in the image using a positioning model based on the geometric information of the ROI in the initial image and the feature information of the ROI.