Image analysis for scoring motion of a heart wall

Abstract

The present disclosure relates to a system (100) for scoring motion of a heart wall (214, 218). The system (100) includes an imaging system (102) operable to acquire a first image (230) of the heart wall (214, 218) at a first time and a second image (240) of the heart wall (214, 218) at a second time. A processor (108) is provided to identify a first set of contour data in the first image (230); and a second set of contour data in the second image (240). The processor (108) defines at least one element (Ei) representing a cardiac cyclic change in a section of the heart wall (214, 218) in dependence on the first and second sets of contour data. Each element (Ei) is analysed to generate at least one metric which is compared with a reference data model to score the motion of the corresponding section of the heart wall (214, 218). The disclosure also relates to a method of scoring motion of a heart wall (214, 218); and a non-transitory computer-readable medium.

1 . A system for scoring motion of a heart wall, the system comprising:
 an imaging system operable to acquire a first image of the heart wall at a first time and a second image of the heart wall at a second time;   a processor configured to:
 identify a first set of contour data in the first image; 
 identify a second set of contour data in the second image; 
 in dependence on the first and second sets of contour data, define at least one element representing a cardiac cyclic change in a section of the heart wall; 
 analyse the or each element to generate two or more metrics; and 
 compare the two or more metrics generated for the or each element with a reference data model to score the motion of the corresponding section of the heart wall, the reference data model comprising a first principal component; 
   wherein the scoring comprises calculating a score for the or each element in dependence on bivariate or multivariate analysis of the two or more metrics generated for that element, the score representing a value of the two or more metrics on the first principal component of the reference data model.   
     
     
         2 . A system as claimed in  claim 1 , wherein the processor is configured to identify a plurality of pairs of contour points, each pair of contour points relating to a corresponding feature in the first and second sets of contour data. 
     
     
         3 . A system as claimed in  claim 2 , wherein each element comprises at least first and second pairs of contour points, the contour points in each pair defining vertices of the element. 
     
     
         4 . A system as claimed in  claim 3 , wherein the analysis of each element comprises determining a distance between the contour points in each pair and calculating a mean distance between the contour points for each element. 
     
     
         5 . A system as claimed in  claim 2 , wherein each element comprises opposing first and second sides corresponding to motion trajectories of the contour points. 
     
     
         6 . A system as claimed in  claim 1 , wherein the analysis of each element comprises determining an area of the element. 
     
     
         7 . A system as claimed in  claim 1 , wherein the analysis of each element comprises determining a rectangularity of each element, said rectangularity being calculated as the ratio between the area of each element and the area of its minimum bounding rectangle. 
     
     
         8 . A system as claimed in  claim 1 , wherein the analysis of each element comprises determining a solidity of each element, said solidity being calculated as the ratio between the element's area and the area of its convex hull. 
     
     
         9 . A system as claimed in  claim 1 , wherein the imaging system is configured to generate two-dimensional images; the first and second images comprising two-dimensional images of the heart wall. 
     
     
         10 . A system as claimed in  claim 1 , wherein each element comprises a polygon. 
     
     
         11 . A system as claimed in  claim 1 , wherein the processor is configured to score the motion of the heart wall during a rest condition and during a stress condition. 
     
     
         12 . A system as claimed in  claim 1 , wherein the first image comprises an end systole image and the second image comprises an end diastole image; the first set of contour data comprising end systole contour data and the second set of contour data comprising end diastole data. 
     
     
         13 . A method of scoring motion of a heart wall, the method comprising:
 acquiring a first image of the heart wall at a first time and a second image of the heart wall at a second time;   identifying a first set of contour data in the first image;   identifying a second set of contour data in the second image;   in dependence on the first and second sets of contour data, defining at least one element representing a cardiac cyclic change in a section of the heart wall;   analysing the or each element to generate two or more metrics; and   comparing the two or more metrics generated for the or each element with a reference data model to score the motion of the corresponding section of the heart wall, the reference data model comprising a first principal component;   wherein the scoring comprises calculating a score for the or each element in dependence on bivariate or multivariate analysis of the two or more metrics generated for that element, the score representing a value of the two or more metrics on the first principal component of the reference data model.   
     
     
         14 . A method as claimed in  claim 13  comprising identifying a plurality of pairs of contour points, each pair of contour points relating to corresponding image elements in the first and second sets of contour data, wherein each element comprises opposing first and second sides corresponding to motion trajectories of the contour points. 
     
     
         15 . A method as claimed in  claim 14 , wherein each element comprises at least first and second pairs of contour points, the contour points in each pair defining vertices of the element. 
     
     
         16 . A method as claimed in  claim 15 , wherein the analysis of each element comprises determining a distance between the contour points in each pair and calculating a mean distance between the contour points for each element. 
     
     
         17 . A method as claimed in  claim 13 , wherein the analysis of each element comprises one or more of the following:
 (i) determining an area of the element;   (ii) determining a rectangularity of each element, said rectangularity being calculated as the ratio between the area of each element and the area of its minimum bounding rectangle; and   (iii) determining a solidity of each element, said solidity being calculated as the ratio between the element's area and the area of its convex hull.   
     
     
         18 . A method as claimed in  claim 13  comprising scoring the motion of the heart wall during a rest condition and during a stress condition. 
     
     
         19 . A method as claimed in  claim 13 , wherein the first image comprises an end systole image and the second image comprises an end diastole image; the first set of contour data comprising end systole contour data and the second set of contour data comprising end diastole data. 
     
     
         20 . A non-transitory computer-readable medium having a set of instructions stored therein which, when executed, cause a processor to perform the method claimed in  claim 13 .