System for and method of identifying coronary artery disease
A method and corresponding system of identifying coronary artery disease. The method comprises receiving contrast cardiac CT data indicative of a contrast cardiac CT scan carried out on a patient, and analysing the contrast cardiac CT data using machine learning to identify a plurality of seed points in the contrast cardiac CT data expected to correspond to locations in cardiac arteries of the patient. The method also comprises producing data indicative of transverse image slices of the cardiac arteries of the patient using the contrast cardiac CT data and the identified seed points, analysing the transverse image slice data using machine learning to produce inner artery wall data and outer artery wall data indicative of predicted respective inner and outer walls of the coronary arteries of the patient, and identifying presence of coronary artery disease using the predicted inner and/or outer walls of the coronary arteries of the patient.
1 . A method of identifying coronary artery disease comprising:
receiving contrast cardiac CT data indicative of a contrast cardiac CT scan carried out on a patient;
analysing the contrast cardiac CT data using machine learning to identify a plurality of centreline seed points in the contrast cardiac CT data predicted to correspond to locations on centrelines of the cardiac arteries of the patient by:
analysing the contrast cardiac CT data using machine learning to identify a plurality of predicted centreline seed points; and
determining a plurality of centreline seed points corresponding to predicted locations on centrelines of the coronary arteries using machine learning by predicting from an instant determined centreline seed point a probable direction to a further centreline seed point of the coronary artery, and selecting a predicted centreline seed point from the plurality of predicted centreline seed points using the predicted probable direction to a further centreline seed point of the coronary artery;
producing data indicative of transverse image slices of the cardiac arteries of the patient using the contrast cardiac CT data and the identified centreline seed points;
analysing the transverse image slice data using machine learning to produce inner artery wall data and outer artery wall data indicative of predicted respective inner and outer walls of the coronary arteries of the patient; and
identifying presence of coronary artery disease using the predicted inner and/or outer walls of the coronary arteries of the patient.
2 . A method as claimed in claim 1 , wherein the step of identifying a plurality of predicted centreline seed points comprises applying a radiodensity test so as to pass predicted centreline seed points that have an associated radiodensity value within a defined parameter range.
3 . A method as claimed in claim 1 , wherein the step of predicting a probable direction to a further centreline seed point is carried out using the predicted centreline seed points and data cubes.
4 . A method as claimed in claim 1 , comprising using machine learning to detect intersection locations between coronary arteries and the aorta.
5 . A method as claimed in claim 4 , comprising determining whether a coronary artery connects to the aorta based on whether the coronary artery extends to a position within a defined distance from the ascending aorta.
6 . A method as claimed in claim 2 , comprising modifying the parameter range used by the radiodensity test if a determination is made that the identified coronary arteries are incorrect or incomplete.
7 . A method as claimed in claim 1 , comprising using the determined inner wall data to determine a cross-sectional lumen area, and using the determined cross-sectional lumen area to identify stenosis.
8 . A method as claimed in claim 7 , comprising determining a reference cross sectional area after each artery bifurcation, the reference area calculated by fitting a linear regression line to an artery portion after the artery bifurcation, the linear regression line indicative of a linear progressively reducing reference cross sectional area, and identifying stenosis based on a comparison of a determined cross-sectional area with a reference cross sectional area according to the linear regression line.
9 . A method as claimed in claim 1 , comprising enabling a user to edit the inner artery wall data.
10 . A method as claimed in claim 9 , comprising enabling a user to edit the inner artery wall data by facilitating selection of vessel stenosis, the system modifying the inner artery wall data based on the selected stenosis.
11 . A method as claimed in claim 10 , comprising modifying the inner artery wall data based on the selected stenosis by carrying out an iterative process including the steps of modifying the lumen area of a selected slice and subsequently recalculating vessel stenosis.
12 . A system for identifying coronary artery disease comprising:
receiving contrast cardiac CT data indicative of a contrast cardiac CT scan carried out on a patient;
a vessel seed detector that analyses received contrast cardiac CT data indicative of a contrast cardiac CT scan carried out on a patient using machine learning to identify a plurality of centreline seed points in the contrast cardiac CT data predicted to correspond to locations in cardiac arteries of the patient by:
analysing the contrast cardiac CT data using machine learning to identify a plurality of predicted centreline seed points; and
determining a plurality of centreline seed points corresponding to predicted locations on centrelines of the coronary arteries using machine learning by predicting from an instant determined centreline seed point a probable direction to a further centreline seed point of the coronary artery, and selecting a predicted centreline seed point from the plurality of predicted centreline seed points using the predicted probable direction to a further centreline seed point of the coronary artery;
a vessel wall segmenter that produces data indicative of transverse image slices of the cardiac arteries of the patient using the contrast cardiac CT data and the identified centreline seed points, the vessel wall segmenter analysing the transverse image slice data using machine learning to produce inner artery wall data and outer artery wall data indicative of predicted respective inner and outer walls of the coronary arteries of the patient; and
a disease assessment unit that identifies presence of coronary artery disease using the predicted inner and/or outer walls of the coronary arteries of the patient.
13 . A system as claimed in claim 12 , wherein the vessel seed detector is arranged to apply a radiodensity test so as to pass predicted centreline seed points that have an associated radiodensity value within a defined parameter range.
14 . A system as claimed in claim 12 , wherein the vessel tracker is arranged to predict a probable direction to a further centreline seed point using the predicted centreline seed points and data cubes.
15 . A system as claimed in claim 12 , wherein the vessel tracker is arranged to use machine learning to detect intersection locations between coronary arteries and the aorta.
16 . A system as claimed in claim 15 , wherein the vessel tracker is arranged to determine whether a coronary artery connects to the aorta based on whether the coronary artery extends to a position within a defined distance from the ascending aorta.
17 . A system as claimed in claim 13 , wherein the vessel seed detector is arranged to modify the parameter range used by the radiodensity test if a determination is made that the identified coronary arteries are incorrect or incomplete.
18 . A system as claimed in claim 12 , wherein the disease assessment unit is arranged to use the determined inner wall data to determine a cross-sectional lumen area, and using the determined cross-sectional lumen area to identify stenosis.
19 . A system as claimed in claim 12 , wherein the system is arranged to enable a user to edit the inner artery wall data.
20 . A system as claimed in claim 12 , wherein the system is arranged to enable a user to edit the inner artery wall data by facilitating selection of vessel stenosis, the system modifying the inner artery wall data based on the selected stenosis.
21 . A system as claimed in claim 20 , wherein the system is arranged to modify the inner artery wall data based on the selected stenosis by carrying out an iterative process including the steps of modifying the lumen area of a selected slice and subsequently recalculating vessel stenosis.