System and method for image denoising

Abstract

Systems and methods for image noise reduction are provided. The methods may include obtaining first image data, determining a restriction or a gradient of the first image data, determining a regularization parameter for the first image data based on the restriction or the gradient, generating second image data based on the regularization parameter and the first image data, and generating a regularized image based on the second image data.

1 - 20 . (canceled) 
     
     
         21 . A system, comprising:
 at least one hardware processor to perform operations including:
 determining a gradient of image data; 
 determining reciprocal of an absolute value of the gradient of the image data; 
 determining a regularization parameter based on the reciprocal of the absolute value of the gradient; 
 determining a regularization item that regularizes the image data; and 
 generating a regularized image based on the regularization parameter and the regularization item. 
   
     
     
         22 . The system of  claim 21 , wherein the image data is obtained by reconstructing original projection data with a statistical reconstruction algorithm with edge preserving regularization. 
     
     
         23 . The system of  claim 21 , wherein the regularization item is a matrix including one or more item elements corresponding to one or more pixels or voxels of the image data. 
     
     
         24 . The system of  claim 21 , wherein the gradient of the image data is determined based on the gray values of the image data. 
     
     
         25 . The system of  claim 21 , wherein the reciprocal of the absolute value of the gradient is a matrix including a plurality of reciprocal values, and each of the plurality of reciprocal values corresponds to a pixel or voxel of the image data 
     
     
         26 . The system of  claim 21 , the operations further including:
 determining whether the reciprocal of the absolute value corresponding to a pixel or voxel of the image data is within a range; and   in response to the determination that the reciprocal of the absolute value corresponding to the pixel or voxel of the image data is within the range, boosting a parameter value corresponding to the pixel or voxel.   
     
     
         27 . The system of  claim 26 , the operations further including:
 in response to the determination that the reciprocal of the absolute value corresponding to the pixel or voxel of the image data is out of the range, keeping the parameter value corresponding to the pixel or voxel unchanged.   
     
     
         28 . A method implemented on at least one device each of which has at least one processor and storage, the method comprising:
 determining a gradient of image data;   determining reciprocal of an absolute value of the gradient of the image data;   determining a regularization parameter based on the reciprocal of the absolute value of the gradient;   determining a regularization item that regularizes the image data; and   generating a regularized image based on the regularization parameter and the regularization item.   
     
     
         29 . The method of  claim 28 , wherein the image data is obtained by reconstructing original projection data with a statistical reconstruction algorithm with edge preserving regularization. 
     
     
         30 . The method of  claim 28 , wherein the regularization item is a matrix including one or more item elements corresponding to one or more pixels or voxels of the image data. 
     
     
         31 . The method of  claim 28 , wherein the gradient of the image data is determined based on the gray values of the image data. 
     
     
         32 . The method of  claim 28 , wherein the reciprocal of the absolute value of the gradient is a matrix including a plurality of reciprocal values, and each of the plurality of reciprocal values corresponds to a pixel or voxel of the image data 
     
     
         33 . The method of  claim 28 , further including:
 determining whether the reciprocal of the absolute value corresponding to a pixel or voxel of the image data is within a range;   in response to the determination that the reciprocal of the absolute value corresponding to the pixel or voxel of the image data is within the range, boosting a parameter value corresponding to the pixel or voxel.   
     
     
         34 . The method of  claim 33 , further including:
 in response to the determination that the reciprocal of the absolute value corresponding to the pixel or voxel of the image data is out of the range, keeping the parameter value corresponding to the pixel or voxel unchanged.   
     
     
         35 . A non-transitory computer readable medium, comprising at least one set of instructions, wherein when the at least one set of instructions are executed by a processor, the at least one set of instructions causes the processor to perform one or more operations, the one or more operations comprising:
 determining a gradient of image data;   determining reciprocal of an absolute value of the gradient of the image data;   determining a regularization parameter based on the reciprocal of the absolute value of the gradient;   determining a regularization item that regularizes the image data; and   generating a regularized image based on the regularization parameter and the regularization item.   
     
     
         36 . The non-transitory computer readable medium of  claim 35 , wherein the image data is obtained by reconstructing original projection data with a statistical reconstruction algorithm with edge preserving regularization. 
     
     
         37 . The non-transitory computer readable medium of  claim 35 , wherein the regularization item is a matrix including one or more item elements corresponding to one or more pixels or voxels of the image data. 
     
     
         38 . The non-transitory computer readable medium of  claim 35 , wherein the gradient of the image data is determined based on the gray values of the image data. 
     
     
         39 . The non-transitory computer readable medium of  claim 35 , wherein the reciprocal of the absolute value of the gradient is a matrix including a plurality of reciprocal values, and each of the plurality of reciprocal values corresponds to a pixel or voxel of the image data. 
     
     
         40 . The non-transitory computer readable medium of  claim 35 , further including:
 determining whether the reciprocal of the absolute value corresponding to a pixel or voxel of the image data is within a range;   in response to the determination that the reciprocal of the absolute value corresponding to the pixel or voxel of the image data is within the range, boosting a parameter value corresponding to the pixel or voxel.