Autonomous segmentation of contrast filled coronary artery vessels on computed tomography images

1. A computer-implemented method for autonomous segmentation of contrast-filled coronary artery vessels, the method comprising:

a) receiving a CT scan volume representing a 3D volume of a region of anatomy that includes a pericardium;

b) preprocessing the CT scan volume to output a preprocessed scan volume;

c) converting the CT scan volume to three sets of two-dimensional slices, wherein the first set is arranged along the axial plane, the second set is arranged along the sagittal plane and the third set is arranged along the coronal plane;

d) extracting a region of interest (ROI) by autonomous segmentation of the heart region as outlined by the pericardium, by means of three individually trained ROI extraction convolutional neural networks (CNN), each trained to process a particular one of the three sets of two-dimensional slices to output a mask denoting a heart region as delineated by the pericardium;

e) combining the preprocessed scan volume with the mask to obtain a masked volume;

f) converting the masked volume to three groups of sets of two-dimensional masked slices, wherein the first group is arranged along the axial plane, the second group is arranged along the sagittal plane and the third group is arranged along the coronal plane and each group includes at least three sets, wherein the first set corresponds to the principal plane of the set and at least two other sets are tilted with respect to the principal plane; and

g) performing autonomous coronary vessel segmentation by autonomous segmentation of the sets of the two-dimensional masked slices by means of three individually trained segmentation convolutional neural networks (CNN), each trained to process a particular one of the sets of the two-dimensional masked slices to output a mask denoting the coronary vessels.

2. The method according to claim 1 , wherein the step of preprocessing the CT scan includes performing at least one of: windowing, filtering and normalization.

3. The method according to claim 1 , wherein the step of preprocessing the CT scan includes computing a 3D Jerman filter response.

4. The method according to claim 3 , further comprising combining the 3D Jerman filter response with the mask to obtain a masked Jerman-filtered volume, converting the masked Jerman-filtered volume to three groups of sets of two-dimensional masked Jerman-filtered slices and providing the two-dimensional masked Jerman-filtered slices as an input to a second channel of the segmentation convolutional neural networks (CNN).

5. The method according to claim 1 , further comprising combining the masks denoting the coronary vessel to a segmented 3D data set representing the shape, location and size of the coronary vessels.

6. A computer-implemented system, comprising:

at least one nontransitory processor-readable storage medium that stores at least one of processor-executable instructions or data; and

at least one processor communicably coupled to the at least one nontransitory processor-readable storage medium, wherein the at least one processor is configured to perform the steps of the method of claim 1 .