Smart editing of image-processing results

A computer-implemented method for processing an image, the method comprising:

• receiving one or more images acquired from an image scanner device;
• automatically generating an initial segmentation of an anatomical feature of interest by applying a segmentation algorithm to the one or more images;
• presenting the initial segmentation to a user on a display;
• in response to receiving a rejection of the initial segmentation from the user, performing an iterative segmentation process until receiving a user exit request comprising:
• generating a plurality of alternative segmentations of the anatomical feature of interest by applying a first machine learning model to the one or more images using a plurality of first model parameters,
• presenting the plurality of alternative segmentations to the user on the display,
• receiving a user response comprising (i) an indication of acceptance of one or more of the alternative segmentations, (ii) an indication of rejection of all of the alternative segmentations, or (iii) the user exit request,
• updating the plurality of first model parameters based on the user response, and
• using the plurality of alternative segmentations and the user response to train a second machine learning model to learn one or more user segmentation preferences.

A system for processing images comprising:

• a display;
• one or more processors;
• and
• a non-transitory, tangible computer-readable medium holding instructions executable by the one or more processors for performing a method comprising:
• performing one or more image processing tasks on an input image using an iterative editing process, wherein the iterative editing process is executed until receiving a user exit request and each iteration of the iterative editing process comprises:
• using a first machine learning model to generate a plurality of processed images, wherein each processed image corresponds to a distinct set of processing parameters;
• presenting the plurality of processed images to a user on the display;
• receiving a user response comprising (i) an indication of acceptance of one or more of the processed images, (ii) an indication of rejection of all of the processed images, or (iii) the user exit request;
• using the plurality of processed images and the user response to train a second machine learning model to generate first model input parameters to the first machine learning model;
• and
• following the iterative editing process, performing at least one clinical task using at least one of the processed images generated immediately prior to receiving the user exit request.