Canon U.s.a., Inc.

The Brigham and Women's Hospital, Inc.

Santosh Ganesan

Barret Daniels

Zhuo Wang

Nobuhiko Hata

Brian Ninni

Franklin H King

Junichi Tokuda

Kemal Tuncali

Antonio Bonillas Vaca

Laurent Chauvin

One or more devices, systems, methods and storage mediums for performing medical procedure (e.g., needle guidance, ablation, biopsy, etc.) planning and/or performance, and/or for performing registration using at least one mask, are provided. Examples of applications for such devices, systems, methods and storage mediums include imaging, evaluating and diagnosing biological objects, such as, but not limited to, lesions and tumors, and such devices, systems, methods and storage mediums may be used for radiotherapy applications (e.g., to determine whether to place seed(s) for radiotherapy). The devices, systems, methods and storage mediums provide improved registration results by utilizing at least one mask to suppress one or more artifacts or objects (which may or may not include, but is not limited to, at least one medical instrument or tool) in an image including a portion of the medical guidance device and/or to enhance a region or target of interest in the image.

Structure masking or unmasking for optimized device-to-image registration

A device to image registration method includes obtaining image data of a device, the device including a plurality of fiducials arranged as a fiducial frame on the device; detecting fiducial objects within the image data; cropping the image data to generate cropped image data; applying a feature enhancement to the cropped image data to enhance the fiducial objects; generating a candidate list of candidate objects based on the feature enhancement, and determining a common plane based on at least three points in the candidate list; determining a representative point for each candidate object; determining outlier candidate objects based on the common plane; determining resultant objects by extracting the outlier candidate objects from the candidate list; and registering the resultant objects to the device by matching the representative points of the resultant objects with a model of the fiducial frame.

Device-to-image registration method, apparatus, and storage medium

Exemplary methods, apparatus, and systems are disclosed for automated registration and motion compensation of patient-mounted needle guide medical devices using fiducial markers, and processing algorithms where a re-registration step is provided. These methods, apparati, and systems adaptively compensate for the displacement of the medical device and/or target location due to the patient movement or internal organ motion.

Registration and motion compensation for patient-mounted needle guide

An image processing apparatus is provided and includes one or more processors and a memory storing instructions. The one or more processors are controlled to receive image stream data captured by an image capturing apparatus and store, in memory, a current image frame from the received image stream data and store, in memory, a previously received image frame from the received image stream data. The previously received image frame having been received at a time earlier than the current image data frame. Using the previously received image frame data stored in memory, a compensation value representing an illumination spectrum of the previously stored image frame data is calculated and image correction is performed on the current image frame data using the calculated compensation value. The corrected current image frame for display on a display device.

Apparatus, system and method for dynamic in-line spectrum compensation of an image

Growing community of inventors

Cambridge, MA, United States of America

Santosh Ganesan