Heat map based medical image diagnostic mechanism

Abstract

A device to provide a heat map based medical image diagnostic mechanism is described. An image analysis application executed by the device receives a medical image from a medical image provider. A region of interest (ROI) is determined or provided by a user. A disease state score including a malignancy score is calculated for the ROI. Next, the ROI is partitioned into sub-regions. Impact values associated with the sub-regions are also determined. The impact values indicate the influence of a sub-region on the disease state score. Furthermore, annotations are determined based on pixel values associated with the sub-region. A heat map of the sub-regions is also generated based on the impact values. The heat map is labeled with the annotations. Next, the heat map is overlaid on the ROI. The medical image is provided with the heat map to the user.

What is claimed is: 
     
         1 . A device to provide a heat map based medical image diagnostic mechanism, the device comprising:
 a memory configured to store instructions associated with an image analysis application,   a processor coupled to the memory, the processor executing the instructions associated with the image analysis application, wherein the processor is configured to:
 receive a region of interest (ROI) within a medical image; 
 determine a disease state score including a malignancy score associated with the ROI; 
 partition the ROI into sub-regions; 
 determine a variation in the disease state score upon alterations to each sub-region; 
 determine impact values associated with the sub-regions based on the variation in the disease state score; 
 generate a heat map of the sub-regions based on the impact values; 
 overlay the heat map on the ROI; and 
 provide the medical image with the heat map to a user. 
   
     
     
         2 . The device of  claim 1 , wherein the processor is further configured to:
 modify the ROI by replacing the sub-regions with a pattern of pixels, wherein the pattern of pixels simulates background tissue within the sub-regions;   determine a modified malignancy score associated with the modified ROI; and   designate the modified malignancy score as one or more of the impact values associated with one or more of the sub-regions.   
     
     
         3 . The device of  claim 2 , wherein the impact value of each sub-region is computed as a normalized change in the disease state score, wherein a highest probability of a disease state associated with the ROI includes the disease state score equal a value of approximately 1 and a lowest probability of the disease state associated with the ROI includes the disease state score equal a value of approximately 0. 
     
     
         4 . The device of  claim 1 , wherein the processor is further configured to:
 determine an annotation for each sub-region based on the impact values associated with the sub-regions;   wherein each of the annotations include a label describing a malignant lesion associated with the ROI, and wherein the label includes spiculated, micro-lobulated, rounded, indistinct, or angular.   
     
     
         5 . The device of  claim 1 , wherein the processor is further configured to:
 determine an annotation for each sub-region based on the impact values associated with the sub-regions;   wherein each of the annotations include a label describing a benign lesion associated with the ROI, and wherein the label includes oval, circumscribed, and abrupt interface.   
     
     
         6 . The device of  claim 1 , wherein the heat map includes sections correlated to the sub-regions. 
     
     
         7 . The device of  claim 6 , wherein each of the sections are assigned a color, and wherein the color represents one of the impact values associated with one of the sub-regions. 
     
     
         8 . The device of  claim 6 , wherein the processor is further configured to:
 provide a user interface to allow the user to change a color associated with a selected section of the heat map or a selected annotation associated with one of the sub-regions.   
     
     
         9 . The device of  claim 1 , wherein the processor is further configured to:
 provide a user interface to allow the user to select the ROI.   
     
     
         10 . The device of  claim 1 , wherein the processor is further configured to:
 sample an area of the medical image outside the ROI to obtain a background texture, wherein the texture is used to replace the sub-regions in the modified ROIs to obtain the impact value of the sub-region.   
     
     
         11 . The device of  claim 1 , wherein the processor is further configured to:
 sample one or more areas of the medical image outside the ROI with textures, wherein the sample of the textures are used individually and in combination to replace the sub-region of the ROI to calculate the impact value of the sub-region.   
     
     
         12 . A method of providing a heat map based medical image diagnostic mechanism, the method comprising:
 receiving a region of interest (ROI) within a medical image;   determining a disease state score including a malignancy score associated with the ROI;   partitioning the ROI into sub-regions;   determining a variation in the disease state score upon alterations to each sub-region;   determining impact values associated with the sub-regions based on the variation in the disease state score;   generating a heat map of the sub-regions based on the impact values;   overlaying the heat map on the ROI; and   providing the medical image with the heat map to a user.   
     
     
         13 . The method of  claim 1 , further comprising:
 modifying the ROI by replacing the sub-regions with a pattern of pixels, wherein the pattern of pixels simulates background tissue within the sub-regions;   determining a modified malignancy score associated with the modified ROI; and   designating the modified malignancy score as one or more of the impact values associated with one or more of the sub-regions.   
     
     
         14 . The method of  claim 2 , wherein the impact value of each sub-region is computed as a normalized change in the disease state score, wherein a highest probability of a disease state associated with the ROI includes the disease state score equal a value of approximately 1 and a lowest probability of the disease state associated with the ROI includes the disease state score equal a value of approximately 0. 
     
     
         15 . The method of  claim 1 , further comprising:
 determining an annotation for each sub-region based on the impact values associated with the sub-regions;   wherein each of the annotations include a label describing a malignant lesion associated with the ROI, and wherein the label includes spiculated, micro-lobulated, rounded, indistinct, or angular.   
     
     
         16 . The method of  claim 1 , further comprising:
 determining an annotation for each sub-region based on the impact values associated with the sub-regions;   wherein each of the annotations include a label describing a benign lesion associated with the ROI, and wherein the label includes oval, circumscribed, and abrupt interface.   
     
     
         17 . The method of  claim 6 , further comprising:
 providing a user interface to allow the user to change a color associated with a selected section of the heat map or a selected annotation associated with one of the sub-regions.   
     
     
         18 . The method of  claim 1 , further comprising:
 providing a user interface to allow the user to select the ROI.   
     
     
         19 . The method of  claim 1 , further comprising:
 sampling an area of the medical image outside the ROI to obtain a background texture, wherein the texture is used to replace the sub-regions in the modified ROIs to obtain the impact value of the sub-region.   
     
     
         20 . The method of  claim 1 , wherein the processor is further configured to:
 sample one or more areas of the medical image outside the ROI with textures, wherein the sample of the textures are used individually and in combination to replace the sub-region of the ROI to calculate the impact value of the sub-region.