Method of forming probability map

Abstract

A method of forming a probability map is disclosed. According to one embodiment, a method may include: (1) obtaining multiple measures of multiple imaging parameters for every stop of a moving window on an image, wherein two neighboring ones of the stops of the moving window are partially overlapped with each other; (2) obtaining first probabilities of an event for the stops of the moving window by matching the measures of the imaging parameters to a classifier; and (3) obtaining second probabilities of the event for multiple voxels of a probability map based on information associated with the first probabilities.

1 - 20 . (canceled) 
     
     
         21 . A method for generating a probability map of an event, comprising:
 generating a moving window for application to a computation region of a medical image;   applying the moving window to the computation region of the medical image;   obtaining measures of imaging parameters for stops of the moving window, wherein at least neighboring two of the stops of the moving window partially overlap;   obtaining a first probability of the event for each of the stops of the moving window; and   obtaining a second probability of the event for each of multiple voxels of the probability map based on information associated with the first probabilities.   
     
     
         22 . The method of  claim 21 , wherein a size of one of the multiple voxels of the probability map is substantially equal to that of one of multiple voxels of the medical image. 
     
     
         23 . The method of  claim 21 , wherein a size of one of the multiple voxels of the probability map is smaller than that of one of multiple voxels of the medical image. 
     
     
         24 . The method of  claim 21 , wherein said obtaining the first probability of the event comprises matching the measures of the imaging parameters to a classifier for the event. 
     
     
         25 . The method of  claim 21 , wherein the probability map comprises the voxels and provides an indication of a likelihood of the event associated with said each of the voxels, and wherein the neighboring two of the stops of the moving window are shifted from each other by a distance substantially equal to a side length of one of the voxels. 
     
     
         26 . The method of  claim 25 , wherein the moving window at each stop overlaps an area of the computation region, wherein the area is associated with multiple of the voxels of the probability map at said each stop. 
     
     
         27 . The method of  claim 21 , wherein the event is occurrence of a cancer. 
     
     
         28 . The method of  claim 21 , wherein said obtaining the second probabilities of the event for the respective voxels comprises calculating multiple assumed probabilities for the respective voxels of the probability map based on the first probabilities of the event for the stops covering the respective voxels. 
     
     
         29 . The method of  claim 21 , wherein the moving window has a circular shape. 
     
     
         30 . The method of  claim 21 ,
 wherein the probability map is a first probability map and the event is a first event,   the method further comprising:
 obtaining a third probability of a second event for said each of the stops of the moving window by matching the measures to a classifier for the second event; 
 obtaining a fourth probability of the second event for each of the voxels of a second probability map of the second event based on information associated with the third probabilities; and 
 creating the first and second probability maps, 
   wherein:
 said obtaining the first probability of the first event for said each of the stops comprises obtaining a first one of the first probabilities for a first one of the stops, and obtaining a second one of the first probabilities for a second one of the stops, 
 said obtaining the second probability of the first event for said each of the multiple voxels of the first probability map comprises calculating a fifth probability of the first event based on the first one and the second one of the first probabilities of the first event, 
 said obtaining the third probability of the second event for said each of the stops comprises obtaining a first one of the third probabilities for a first one of the stops and obtaining a second one of the third probabilities for a second one of the stops, and 
 said obtaining the fourth probability of the second event for said each of the multiple voxels of the second probability map comprises calculating a sixth probability of the second event based on the first one and the second one of the third probabilities of the second event. 
   
     
     
         31 . The method of  claim 30 , further comprising creating a composite probability map combining the first probability map of the first event and the second probability map of the second event. 
     
     
         32 . The method of  claim 30 , wherein the first event is that a cancer occurs, and the second event is associated with a Gleason score or a Gleason score in a given range. 
     
     
         33 . A method for generating a probability map of an event, comprising:
 generating a moving window for application to a computation region of a medical image;   applying the moving window to the computation region of the medical image;   obtaining measures of imaging parameters for stops of the moving window, wherein at least neighboring two of the stops of the moving window partially overlap;   obtaining a first probability of the event for each of the stops of the moving window; and   creating the probability map based on the first probabilities, wherein the probability map comprises multiple voxels and provides an indication of a likelihood of the event associated with each of the voxels, and wherein the neighboring two of the stops of the moving window are shifted from each other by a distance substantially equal to a side length of one of the voxels.   
     
     
         34 . The method of  claim 33 , wherein a size of one of the multiple voxels of the probability map is substantially equal to that of one of multiple voxels of the medical image. 
     
     
         35 . The method of  claim 33 , wherein a size of one of the voxels of the probability map is smaller than that of one of voxels of the medical image. 
     
     
         36 . The method of  claim 33 , wherein said obtaining the first probability of the event comprises matching the measures of the imaging parameters to a classifier for the event. 
     
     
         37 . The method of  claim 33 , wherein the moving window at each stop overlaps an area of the computation region, wherein the area is associated with multiple of the voxels of the probability map at said each stop. 
     
     
         38 . The method of  claim 33 , wherein the event is occurrence of a cancer. 
     
     
         39 . The method of  claim 33 , further comprising obtaining a second probability of the event for said each of the voxels of the probability map based on information associated with the first probabilities, wherein said obtaining the second probabilities of the event for the respective voxels comprises calculating multiple assumed probabilities for the respective voxels of the probability map based on the first probabilities of the event for the stops covering the respective voxels. 
     
     
         40 . The method of  claim 33 , wherein the moving window has a circular shape. 
     
     
         41 . The method of  claim 33 , wherein the probability map is a first probability map, and the event is a first event, further comprising:
 obtaining a third probability of a second event for said each of the stops of the moving window by matching the measures to a classifier for the second event; and   obtaining fourth probabilities of the second event for the voxels of a second probability map based on information associated with the third probabilities.   
     
     
         42 . The method of  claim 41 , further comprising creating a composite probability map combining the first probability map of the first event and the second probability map of the second event. 
     
     
         43 . The method of  claim 41 , wherein the first event is that a cancer occurs, and the second event is associated with a Gleason score or a Gleason score in a given range.