Method and System for Image Registration Using an Intelligent Artificial Agent

Abstract

Methods and systems for image registration using an intelligent artificial agent are disclosed. In an intelligent artificial agent based registration method, a current state observation of an artificial agent is determined based on the medical images to be registered and current transformation parameters. Action-values are calculated for a plurality of actions available to the artificial agent based on the current state observation using a machine learning based model, such as a trained deep neural network (DNN). The actions correspond to predetermined adjustments of the transformation parameters. An action having a highest action-value is selected from the plurality of actions and the transformation parameters are adjusted by the predetermined adjustment corresponding to the selected action. The determining, calculating, and selecting steps are repeated for a plurality of iterations, and the medical images are registered using final transformation parameters resulting from the plurality of iterations.

Description

[0001]This application claims the benefit of U.S. Provisional Application No. 62 / 338,059, filed May 18, 2016, U.S. Provisional Application No. 62 / 344,125, filed Jun. 1, 2016, and U.S. Provisional Application No. 62 / 401,977, filed Sep. 30, 2016, the disclosures of which are herein incorporated by reference in its entirety.BACKGROUND OF THE INVENTION[0002]The present invention relates to registration of medical images, and more particularly to computer-based automated medical image registration using an intelligent artificial agent.[0003]Medical image registration is an important technology that enables image guided therapy, automated diagnosis imaging, and machine-driven image understanding. The goal of image registration is to recover correspondences between two or more medical images, which can be acquired from different patients / objects, the same patient at different time points, different medical imaging modalities, etc., in order to align or fuse the images. The aligned images c...

AI Technical Summary

Problems solved by technology

Due to the vast range of applications to which image registration can be applied, it is challenging to develop a general image registration method that works robustly for all uses.

One reason for this is that a generic matching metric does not guarantee a good representation of the accuracy of the alignment of the data at hand for all use cases, in all circumstances.

In addition, a generic matching metric is often non-convex for a given registration task and generic optimizers typically perform poorly on non-convex optimization problems.

Images