Method, device and computer-readable medium for automatically classifying coronary lesion according to CAD-RADS classification by a deep neural network

1. A computer-implemented method for determining the presence of a coronary lesion for a patient, comprising:

receiving at least one curved or stretched multiplanar medical image of computed tomography (X-scanner) of a coronary artery of said patient; and

determining a value according to the CAD-RADS classification (for Coronary Artery Disease-Reporting and Data System value or System of reports and Data) of a coronary lesion on said image or on a portion of said image by using a first trained deep neural network applied directly to the detected images or portions of detected images.

2. The method according to claim 1 , further comprising predicting a coronary fractal flow reserve interval (FFR) by manual, semi-automated and/or automated measurement of at least two morphological criteria selected from:

the degree of maximum coronary stenosis expressed in percentage (%) of diameter;

the degree of maximum coronary stenosis expressed in percentage (%) of surface;

the minimum diameter of the stenosis in mm;

the minimum surface area of the stenosis in mm 2 ;

the length of the stenosis in mm; or

the myocardial mass and the percentage (%) of myocardial mass downstream of the coronary stenosis.

3. The method according to claim 1 , further comprising predicting a coronary fractal flow reserve interval of coronary stenosis by using a second trained deep neural network applied directly to the detected images or portions of images.

4. The method according to claim 1 , further comprising at least one of the following:

automated determination of the image quality providing a diagnostic confidence index by using a third trained neural network applied directly to the detected images or portions of detected images;

determining a global calcification score on a scale of 0 to 4 predicting the Agatston calcium score, by using a fourth trained neural network applied directly to the detected images or portions of images; and/or

determining a high-risk plaque (HRP) of a cardiac event, by using a fifth trained neural network applied directly to the detected images or portions of detected images.

5. The method according to claim 4 , further comprising:

determining a value according to the CAD-RADS classification by using a first trained deep neural network applied directly to the detected images or portions;

predicting a coronary reserve flow value interval by using a second trained deep neural network applied directly to the detected images or portions;

automated determination of the image quality providing a diagnostic confidence index from a third trained neural network applied directly to the detected images or portions of detected images;

determining a global calcification score on a scale of 0 to 4 predicting the Agatston calcium score, by using a fourth trained neural network applied directly to the detected images or portions of detected images; and

determining a high-risk plaque of a cardiac event, using a fifth trained neural network applied directly to the detected images or portions of detected images.

6. The method according to claim 5 , wherein the detection of images or portions of images corresponding to the lesion of the patient comprises detecting portions of images corresponding to the coronary lesion, a coronary tree, coronary ostia, or coronary vessels.

7. The method according to claim 1 , wherein the images or portions of images are derived from a Coronary angiography (or CCTA: for Coronary Computer Tomograph Angiography).

8. A device adapted to determine the presence of a coronary lesion for a patient, comprising:

at least one input adapted to receiving at least one curved or stretched multiplanar medical image of computed tomography (X-scanner), of a coronary artery of said patient; at least one processor configured for determining a value according to the CAD-RADS classification (for Coronary Artery Disease-Reporting and Data System value or System of reports and Data) of a Coronary lesion on said image or on a portion of said image by using a first trained deep neural network applied directly to the detected images or portions of images.

9. The device according to claim 8 , wherein the at least one processor is further configured for predicting a coronary reserve flow value interval by using a second trained deep neural network applied directly to the detected images or portions of detected images.

10. The device according to claim 8 , wherein the at least one processor is further configured for:

automated determination of the image quality providing a diagnostic confidence index by using a third trained neural network applied directly to the detected images or portions of detected images;

determining a global calcification score on a scale of 0 to 4 predicting the Agatston calcium score, by using a fourth trained neural network applied directly to the detected images or portions of detected images; and/or

determining a high-risk plaque of a cardiac event, by using a fifth trained neural network applied directly to the detected images or portions of detected images.

11. The device according to claim 10 , wherein the at least one processor is further configured for:

determining a value according to the CAD-RADS classification by using a first trained deep neural network applied directly to the detected images or portions;

predicting a coronary reserve flow value interval by using a second trained deep neural network applied directly to the detected images or portions;

automated determination of the image quality providing a diagnostic confidence index by using a third trained neural network applied directly to the detected images or portions of images;

determining a global calcification score on a scale of 0 to 4 predicting the Agatston calcium score, by using a fourth trained neural network applied directly to the detected images or portions of detected images; and

determining a high-risk plaque of a cardiac event, by using a fifth trained neural network applied directly to the detected images or portions of detected images.

12. A non-transitory computer-readable medium storing computer-readable program instructions for determining the presence of a coronary lesion for a patient, comprising executing by a computer-readable program instruction processor having the effect of performing the following operations:

receiving at least one curved or stretched multiplanar medical image of computed tomography (X-scanner) of the coronary artery of said patient;

wherein it further generates by said processor an operation of determining a value according to the CAD-RADS classification (for Coronary Artery Disease-Reporting and Data System value or System of reports and Data) of a Coronary lesion on said image or on a portion of said image by using a first trained deep neural network applied directly to the detected images or portions of detected images.

13. The non-transitory computer-readable medium according to claim 12 , wherein it further generates by said processor a prediction operation of a coronary reserve flow value interval by using a second trained deep neural network applied directly to the detected images or portions of detected images.

14. The non-transitory computer-readable medium according to one of claim 13 , wherein it further generates, by said processor, at least one of the following operations:

automated determination of an image quality providing a diagnostic confidence index by using a third trained neural network applied directly to the detected images or portions;

determination of a global calcification score on a scale of 0 to 4 predicting the Agatston calcium score, by using a fourth trained neural network applied directly to the detected images or portions of detected images; and/or

determination of a high-risk plaque of a cardiac event, by using a fifth trained neural network applied directly to the detected images or portions of images.

15. The non-transitory computer-readable medium according to claim 14 , wherein it generates the execution by said processor of the following five operations:

determining a value according to the CAD-RADS classification by using a first trained deep neural network applied directly to the detected images or portions or detected images;

predicting a coronary reserve flow value interval by using a second trained deep neural network applied directly to the detected images or portions of detected images;

automatically determining the image quality providing a diagnostic confidence index by using a third trained neural network applied directly to the detected images or portions of detected images;

determining a global calcification score on a scale of 0 to 4 predicting the Agatston calcium score, by using a fourth trained neural network applied directly to the detected images or portions of detected images; and

determining a high-risk plaque of a cardiac event, by using a fifth trained neural network applied directly to the detected images or portions of detected images.

16. The non-transitory computer-readable medium according to one of claim 12 , wherein it further generates, by said processor, at least one of the following operations:

automated determination of an image quality providing a diagnostic confidence index by using a third trained neural network applied directly to the detected images or portions;

determination of a global calcification score on a scale of 0 to 4 predicting the Agatston calcium score, by using a fourth trained neural network applied directly to the detected images or portions of detected images; and/or

determination of a high-risk plaque of a cardiac event, by using a fifth trained neural network applied directly to the detected images or portions of images.

17. The non-transitory computer-readable medium according to claim 16 , wherein it generates the execution by said processor of the following five operations:

determining a value according to the CAD-RADS classification by using a first trained deep neural network applied directly to the detected images or portions or detected images;

predicting a coronary reserve flow value interval by using a second trained deep neural network applied directly to the detected images or portions of detected images;

automatically determining the image quality providing a diagnostic confidence index by using a third trained neural network applied directly to the detected images or portions of detected images;

determining a global calcification score on a scale of 0 to 4 predicting the Agatston calcium score, by using a fourth trained neural network applied directly to the detected images or portions of detected images; and

determining a high-risk plaque of a cardiac event, by using a fifth trained neural network applied directly to the detected images or portions of detected images.