Methods and systems for image annotation and segmentation

A system, comprising:

• an imaging system configured to acquire three-dimensional (3D) multi-volume imaging data;
• and
• a computing device communicably coupled to the imaging system, the computing device configured with instructions stored in non-transitory memory executable by a processor that, when executed, cause the processor to:
• obtain a 3D multi-volume imaging dataset from an imaging archive, wherein the 3D multi-volume imaging dataset comprises a plurality of registered image volumes each comprising a plurality of image slices;
• display an image slice of a first set of image slices of two or more image volumes of the plurality of registered image volumes within a graphical user interface (GUI) of a display device communicably coupled to the computing device;
• determine two or more positions of a user cursor within a first image slice of a first image volume in response to user input;
• determine contour points within two or more image slices corresponding to two or more of the plurality of registered image volumes based on the two or more positions of the user cursor within the first image slice, wherein positions of the contour points are further determined based on one or more gradients in pixel intensity detected within a geodesic propagation around the two or more positions of the user cursor, wherein the one or more gradients in pixel intensity are correlated with one or more edges of a region of interest (ROI) and the one or more edges are defined based on the one or more gradients in pixel intensity;
• generate two or more segmentation contours, wherein each of the two or more segmentation contours corresponds to one of the two or more image slices and comprise respective pluralities of contour points and the two or more segmentation contours are generated based on determining a closest point of the one or more edges to each given contour point;
• select, in response to user input, a selected segmentation contour of the two or more segmentation contours;
• generate, based on the selected contour, a 3D segmentation mask;
• and
• save the 3D segmentation mask to non-transitory memory.

A method, comprising:

• determining a position of a user cursor within a first image of a first image volume of a plurality of image volumes of a 3D multi-volume imaging dataset;
• generating a geodesic propagation around the position of the user cursor within two or more images of two or more corresponding image volumes of the plurality of image volumes;
• determining pixel intensities within the geodesic propagation of each of the two or more images;
• defining an area that approximates an edge of a region of interest within the geodesic propagation of each of the two or more images based on one or more gradients in pixel intensity, wherein when the one or more gradients in pixel intensity are detected within the geodesic propagation based on the determined pixel intensities, the area is not a circle and when one or more gradients in pixel intensity are not detected within the geodesic propagation based on the determined pixel intensities, the area is a circle;
• determining a point of the edge closest to the position of the user cursor within each of the two or more images;
• and
• saving the point as one of a plurality of points of a segmentation contour for each of the two or more images.