Siemens Healthcare Gmbh

The University of British Columbia

Cortic Technology Corp.

Siemens Medical Solutions USA, Inc.

Zhen Wang

Rui Liao

Shun P Miao

Him Wai Ng

Ye Lu

In various embodiments, software architecture and network topology are provided to implement a decentralized distributed computing environment. In some embodiments, the novel network topology is configured as a mesh network such that individual hub devices are connected directly or indirectly with each other. An individual worker can be added to or removed from this network via connection with the hub devices without affecting the rest of the workers in the network and without user intervention or knowledge. In those embodiments, a software package is deployed on a given hub device to enable the hub device to perform network discovery, communicating with other hub devices in the decentralized distributed computing environment, determine a load balance for the decentralized distributed computing environment, distribute a task to an available worker in the decentralized distributed computing environment, manage one or more functional modules in the decentralized distributed computing environment, and/or any other functionalities.

Decentralized distributed computing environment

A method and apparatus for convolutional neural network (CNN) regression based 2D/3D registration of medical images is disclosed. A parameter space zone is determined based on transformation parameters corresponding to a digitally reconstructed radiograph (DRR) generated from the 3D medical image. Local image residual (LIR) features are calculated from local patches of the DRR and the X-ray image based on a set of 3D points in the 3D medical image extracted for the determined parameter space zone. Updated transformation parameters are calculated based on the LIR features using a hierarchical series of regressors trained for the determined parameter space zone. The hierarchical series of regressors includes a plurality of regressors each of which calculates updates for a respective subset of the transformation parameters.

Method and system for convolutional neural network regression based 2D/3D image registration

Growing community of inventors

Vancouver, Canada

Zhen Wang