Intelligent medical image landmark detection

A method for intelligent landmark identification in an image, the method comprising:

• receiving, by a processor, image data representing the image;
• automatically parsing, by the processor using a learned artificial agent, the received image data to identify a landmark location in the image, wherein the learned artificial agent is configured to:
• parameterize a patch of the image data in a trained hierarchical data representation, the hierarchical data representation trained optimizing an action-value function by maximizing a future reward of a reward system for each a plurality of available actions to reposition the patch of the image;
• determine an action from the plurality of available actions to reposition the patch based on the parameterized patch of the image data;
• and
• identify the landmark location in a repositioned patch of the image;
• and
• displaying the identified landmark location in the image.

A system for training an artificial agent for intelligent image parsing, the system comprising:

• at least one processor;
• and
• at least one memory including computer program code for one or more programs, the at least one memory and the computer program code configured to, with the at least one processor, cause the system to:
• receive a plurality of a plurality of training images;
• train, based on the plurality of training images, the artificial agent to parse a test image to identify a landmark position in the test image, to train, the system caused to:
• encode, iteratively using a deep neural network of the artificial agent, a plurality of discrete portions of each of the plurality of training images;
• and
• optimize, with each encoding iteration, parameters of the deep neural network, the parameters comprising image search strategy parameters and landmark appearance parameters;
• and
• store, in the at least one memory, the trained artificial agent for parsing the test image to identify a landmark position in the test image.