System and method for shutter detection

Abstract

Methods, systems, and computer-readable medium for detecting and removing unwanted information in a medical image. One method includes receiving, at a processor, an image, obtained using a shutter including at least a first blade and a second blade. The method also includes processing the image to identify a first plurality of candidate edges in the image for the first blade and a second plurality of candidate edges in the image for the second blade. The method further includes individually evaluating each of the first and second plurality of candidate edges to select one of the first plurality of candidate edges as a true edge for the first blade and one of the second plurality of candidate edges as a true edge for the second blade. In addition, the method includes removing the unwanted information from the image based on a location of each of the identified true edges.

1 . A computer-implemented method for detecting and removing unwanted information in a medical image, the method comprising:
 receiving, at a processor, an image, wherein the image is obtained using a shutter including at least a first blade and a second blade;   processing the image to identify a first plurality of candidate edges in the image for the first blade;   processing the image to identify a second plurality of candidate edges in the image for the second blade;   individually evaluating each of the first plurality of candidate edges to select one of the first plurality of candidate edges as a true edge for the first blade;   individually evaluating each of the second plurality of candidate edges to select one of the second plurality of candidate edges as a true edge for the second blade; and   removing the unwanted information from the image based on a location of the true edge for the first blade and the true edge for the second blade.   
     
     
         2 . The method according to  claim 1 , wherein processing the image to identify the first plurality of candidate edges includes:
 down sampling the image to generate a plurality of image levels having successively decreasing image resolutions,   selecting a first candidate list at a lowest of said plurality of image levels and promoting said first candidate list through subsequent image levels until a highest of said image levels and using candidate edges promoted to said highest of said image levels as the first plurality of candidate edges.   
     
     
         3 . The method according to  claim 1 , wherein processing the image to identify the second plurality of candidate edges includes:
 down sampling the image to generate a plurality of image levels having successively decreasing image resolutions,   selecting a first candidate list at a lowest of said plurality of image levels and promoting said first candidate list through subsequent image levels until a highest of said image levels and using candidate edges promoted to said highest of said image levels as the second plurality of candidate edges.   
     
     
         4 . The method according to  claim 1 , wherein processing the image to identify the first plurality of candidate edges includes obtaining a pre-processed image having had a gradient operator applied thereto and applying a Canny edge mask to the pre-processed image to identify the first plurality of candidate edges. 
     
     
         5 . The method according to  claim 1 , wherein processing the image to identify the second plurality of candidate edges includes obtaining a pre-processed image having had a gradient operator applied thereto and applying a Canny edge mask to the pre-processed image to identify the second plurality of candidate edges. 
     
     
         6 . The method according to  claim 1 , wherein processing the image to identify the first plurality of candidate edges includes detecting a plurality of edges in the image, assigning a score to each of the plurality of edges, and selecting the first plurality of candidate edges based on the score assigned to each of the plurality of edges. 
     
     
         7 . The method according to  claim 1 , wherein processing the image to identify the second plurality of candidate edges includes detecting a plurality of edges in the image, assigning a score to each of the plurality of edges, and selecting the second plurality of candidate edges based on the score assigned to each of the plurality of edges. 
     
     
         8 . The method according to  claim 1 , wherein individually evaluating each of the first plurality of candidate edges includes, for each of the first plurality of candidate edges:
 segmenting each candidate edge into least one segment,   determining a validity of the at least one segment,   when the at least one segment is invalid, discarding the at least one segment.   
     
     
         9 . The method according to  claim 8 , wherein individually evaluating each of the first plurality of candidate edges includes, for each of the first plurality of candidate edges, discarding each candidate edge when the candidate edge includes no valid segments. 
     
     
         10 . The method according to  claim 1 , wherein individually evaluating each of the second plurality of candidate edges includes, for each of the second plurality of candidate edges:
 segmenting each candidate edge into least one segment,   determining a validity of the at least one segment,   when the at least one segment is invalid, discarding the at least one segment.   
     
     
         11 . The method according to  claim 10 , wherein individually evaluating each of the second plurality of candidate edges includes, for each of the second plurality of candidate edges, discarding each candidate edge when the candidate edge includes no valid segments. 
     
     
         12 . A computer-readable medium storing computer-executable instructions for causing an image processing device to execute the method according to  claim 1 . 
     
     
         13 . A system for detecting and removing unwanted information in a medical image, the system comprising;
 an interface comprising a display for viewing the image and enabling a user to interact with the system; and   an image processing program configured to:
 receive, at a processor, an image, wherein the image is obtained using a shutter including at least a first blade and a second blade; 
 process the image to identify a first plurality of candidate edges in the image for the first blade; 
 process the image to identify a second plurality of candidate edges in the image for the second blade; 
 individually evaluate each of the first plurality of candidate edges to select one of the first plurality of candidate edges as a true edge for the first blade; 
 individually evaluate each of the second plurality of candidate edges to select one of the second plurality of candidate edges as a true edge for the second blade; and 
 remove the unwanted information from the image based on a location of the true edge for the first blade and the true edge for the second blade. 
   
     
     
         14 . The system according to  claim 13 , wherein the image processing program is configured to process the image to identify the first plurality of candidate edges by:
 down sampling the image to generate a plurality of image levels having successively decreasing image resolutions,   selecting a first candidate list at a lowest of said plurality of image levels and promoting said first candidate list through subsequent image levels until a highest of said image levels and using candidate edges promoted to said highest of said image levels as the first plurality of candidate edges.   
     
     
         15 . The system according to  claim 13 , wherein the image processing program is configured to process the image to identify the second plurality of candidate edges by:
 down sampling the image to generate a plurality of image levels having successively decreasing image resolutions,   selecting a first candidate list at a lowest of said plurality of image levels and promoting said first candidate list through subsequent image levels until a highest of said image levels and using candidate edges promoted to said highest of said image levels as the second plurality of candidate edges.   
     
     
         16 . The system according to  claim 13 , wherein the image processing program is configured to process the image to identify the first plurality of candidate edges by obtaining a pre-processed image having had a gradient operator applied thereto and applying a Canny edge mask to the pre-processed image to identify the first plurality of candidate edges. 
     
     
         17 . The system according to  claim 13 , wherein the image processing program is configured to process the image to identify the second plurality of candidate edges by obtaining a pre-processed image having had a gradient operator applied thereto and applying a Canny edge mask to the pre-processed image to identify the second plurality of candidate edges. 
     
     
         18 . The system according to  claim 13 , wherein the image processing program is configured to process the image to identify the first plurality of candidate edges by detecting a plurality of edges in the image, assigning a score to each of the plurality of edges, and selecting the first plurality of candidate edges based on the score assigned to each of the plurality of edges. 
     
     
         19 . The system according to  claim 13 , wherein the image processing program is configured to process the image to identify the second plurality of candidate edges by detecting a plurality of edges in the image, assigning a score to each of the plurality of edges, and selecting the second plurality of candidate edges based on the score assigned to each of the plurality of edges. 
     
     
         20 . The system according to  claim 13 , wherein the image processing program is configured to individually evaluate each of the first plurality of candidate edges by, for each of the first plurality of candidate edges:
 segmenting each candidate edge into least one segment,   determining a validity of the at least one segment,   when the at least one segment is invalid, discarding the at least one segment.   
     
     
         21 . The system according to  claim 20 , wherein the image processing program is configured to individually evaluate each of the first plurality of candidate edges by, for each of the first plurality of candidate edges, discarding each candidate edge when the candidate edge includes no valid segments. 
     
     
         22 . The system according to  claim 13 , wherein the image processing program is configured to individually evaluate each of the second plurality of candidate edges by, for each of the second plurality of candidate edges:
 segmenting each candidate edge into least one segment,   determining a validity of the at least one segment,   when the at least one segment is invalid, discarding the at least one segment.   
     
     
         23 . The system according to  claim 20 , wherein the image processing program is configured to individually evaluate each of the second plurality of candidate edges by, for each of the second plurality of candidate edges, discarding each candidate edge when the candidate edge includes no valid segments. 
     
     
         24 . A computer-implemented method for detecting and removing unwanted information in a medical image, the method comprising:
 receiving, at a processor, an image, wherein the image is obtained using a shutter including at least a first blade and a second blade;   processing the image to identify a first plurality of candidate edges in the image for the first blade;   processing the image to identify a second plurality of candidate edges in the image for the second blade;   assigning a score to each of the first plurality of candidate edges;   assigning a score to each of the second plurality of candidate edges;   selecting one or more of the first plurality of candidate edges based on the score assigned to each of the first plurality of candidate edges; and   selecting one or more of the second plurality of candidate edges based on the score assigned to each of the second plurality of candidate edges; and   removing the unwanted information from the image based on at least one of the first plurality of candidate edges and at least one of the second plurality of candidate edges.   
     
     
         25 . The method according to  claim 24 , wherein assigning the score to each of the first plurality of candidate edges includes assigning a score to each of the first plurality of candidate edges indicating a likelihood that each of the first plurality of candidate edges corresponds one of the plurality of blades. 
     
     
         26 . The method according to  claim 24 , wherein assigning the score to each of the second plurality of candidate edges includes assigning a score to each of the second plurality of candidate edges indicating a likelihood that each of the second plurality of candidate edges corresponds one of the plurality of blades.