Systems and methods for image processing

Abstract

A method may include obtaining an image representing a region of interest (ROI) of an object. The ROI may include two or more sub-regions. The method may include determining an average value of quantitative indexes associated with elements in the image corresponding to a first region of the ROI. The method may include determining, for each of the two or more sub-regions of the ROI, a threshold based on the average value; identifying target elements in the image based on the thresholds of the two or more sub-regions. The method may include assigning a presentation value to each of at least some of the target elements based on the average value and the quantitative index of the each target element. The method may include generating a presentation of the image based on the presentation values.

1 - 20 . (canceled) 
     
     
         21 . A system 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 cause the system to perform operations including:
 obtaining an image representing a region of interest (ROI) of an object, the ROI including two or more sub-regions, the image being generated based on imaging signals corresponding to the ROI; 
 for each of the two or more sub-regions of the ROI, determining a threshold using a threshold model based on at least one of basic information of the object, a physiological condition of the ROI, medical history of the object, a goal to scan the object, or a treatment plan of the object, the thresholds of at least two of the two or more sub-regions being different; 
 identifying target elements in the image based on the thresholds of the two or more sub-regions; and 
 generating a presentation of the target elements. 
   
     
     
         22 . The system of  claim 21 , wherein the ROI includes a volume of interest (VOI). 
     
     
         23 . The system of  claim 21 , wherein the threshold model includes a trained machine learning model. 
     
     
         24 . The system of  claim 23 , wherein the trained machine learning model is generated by training a preliminary model using a plurality of sets of sample data, each of the plurality of sets of sample data including at least one of basic information of a patient, medical history of the patient, physiological condition of the patient, treatment plan of the patient, a goal to scan the patient, or a threshold of a sub-region. 
     
     
         25 . The system of  claim 21 , wherein the physiological condition includes at least one of a condition of the ROI, a disease of the ROI, or tissue included in the sub-region. 
     
     
         26 . The system of  claim 21 , wherein a quantitative index of each of the target elements being equal to or larger than the threshold of the corresponding sub-region. 
     
     
         27 . The system of  claim 26 , wherein the quantitative index associated with the element includes signal intensity of the imaging signal associated with the element. 
     
     
         28 . The system of  claim 26 , wherein the identifying the target elements in the image includes:
 determining candidate elements in the image, the quantitative index corresponding to each of the candidate elements being equal to or larger than the threshold of the corresponding sub-region;   dividing the candidate elements into one or more groups based on the locations of the candidate elements in the image;   determining a count of candidate elements in each of the one or more groups;   for each of the one or more groups,
 determining whether the count of candidate elements in the group exceeds a count threshold; and 
 in response to determining that the count of candidate elements in the group exceeds the count threshold, determining the candidate elements in the group as the target elements. 
   
     
     
         29 . The system of  claim 26 , wherein the generating a presentation of the target elements includes:
 determining an average value of quantitative indexes associated with elements in the image corresponding to a first region of the ROI;   assigning a presentation value to each of at least some of the target elements based on the average value and the quantitative index of the each target element; and   generating a presentation of the image based on the presentation values.   
     
     
         30 . The system of  claim 29 , wherein the first region of the ROI includes normal tissue within the ROI. 
     
     
         31 . The system of  claim 29 , wherein the assigning the presentation value to each of at least some of the target elements based on the average value and the quantitative index of the each target element includes:
 determining a difference between the average value and the quantitative index corresponding to the each target element; and   determining the presentation value of the each target element based on the difference,   wherein target elements whose differences are within a same range have a same presentation value.   
     
     
         32 . The system of  claim 29 , wherein the presentation value of one of at least some of the target elements is a color value. 
     
     
         33 . The system of  claim 29 , wherein the image includes a plurality of two-dimensional (2D) image slices. 
     
     
         34 . The system of  claim 33 , wherein
 each of the plurality of 2D image slices includes a target area corresponding to the ROI, and   the at least one processor is further directed to cause the system to perform at least one of the following operations including:
 determining a second region in at least one of the plurality of 2D image slices, the second region including at least a portion of the target elements; 
 determining a first ratio between an area of the second region and an area of the target area of the at least one of the plurality of 2D image slices; 
 determining a third region including all the target elements; 
 determining a second ratio between a volume of the third region and a volume of the ROI; or 
 determining a third ratio between the volume of the third region and a volume of an American Heart Association (AHA) segmental model. 
   
     
     
         35 . The system of  claim 34 , wherein the presentation includes an illustration of at least one of the second region, the target area, the third region, the ROI, the first ratio, the second ratio, the third ratio, or the AHA segmental model. 
     
     
         36 . The system of  claim 33 , wherein the presentation includes at least one of the plurality of 2D image slices that includes an illustration of presentation values of the target elements within the at least one 2D image slice. 
     
     
         37 . The system of  claim 29 , wherein the presentation includes a three-dimensional (3D) model corresponding to at least a portion of the ROI. 
     
     
         38 . The system of  claim 37 , wherein the 3D model includes an illustration of presentation values of at least a portion of at least some target elements. 
     
     
         39 . A method implemented on a machine having one or more processors and one or more storage devices, comprising:
 obtaining an image representing a region of interest (ROI) of an object, the ROI including two or more sub-regions, the image being generated based on imaging signals corresponding to the ROI;   for each of the two or more sub-regions of the ROI, determining a threshold using a threshold model based on at least one of basic information of the object, a physiological condition of the ROI, medical history of the object, a goal to scan the object, or a treatment plan of the object, the thresholds of at least two of the two or more sub-regions being different;   identifying target elements in the image based on the thresholds of the two or more sub-regions; and   generating a presentation of the target elements.   
     
     
         40 . A non-transitory computer readable medium, comprising at least one set of instructions, wherein when executed by one or more processors of a computing device, the at least one set of instructions causes the computing device to perform a method, the method comprising:
 obtaining an image representing a region of interest (ROI) of an object, the ROI including two or more sub-regions, the image being generated based on imaging signals corresponding to the ROI;   for each of the two or more sub-regions of the ROI, determining a threshold using a threshold model based on at least one of basic information of the object, a physiological condition of the ROI, medical history of the object, a goal to scan the object, or a treatment plan of the object, the thresholds of at least two of the two or more sub-regions being different;   identifying target elements in the image based on the thresholds of the two or more sub-regions; and   generating a presentation of the target elements.