Li Zhang

US Patent:

7512519, Mar 31, 2009

Filed:

Nov 24, 2006

Appl. No.:

11/563048

Inventors:

Curtis E. Hrischuk - Holly Springs NC, US
Edward Emil Huth - Royal Palm Beach FL, US
Dazhi Wang - Durham NC, US
Li Zhang - Yorktown Heights NY, US

Assignee:

International Business Machines Corporation - Armonk NY

International Classification:

G06F 3/00

US Classification:

702179, 702182, 702183, 702186

Abstract:

A method of determining accuracy of predicted system behavior can include creating a plurality of noise adjusted analytical models, wherein each noise adjusted analytical model is associated with a set of predefined analytical model parameters. A set of inferred analytical model parameters for each noise adjusted analytical model can be derived. Each set of inferred analytical model parameters can depend upon a current noise adjusted analytical model and each prior noise adjusted analytical model. For each set of inferred analytical model parameters, a measure of error between the set of inferred analytical model parameters and the set of predefined analytical model parameters associated with the noise adjusted analytical model from which the set of inferred analytical model parameters was derived can be determined.

US Patent:

7986823, Jul 26, 2011

Filed:

May 7, 2008

Appl. No.:

12/116461

Inventors:

Yiwen Wang - Gainesville FL, US
Li Zhang - Skillman NJ, US

Assignee:

Siemens Aktiengesellschaft - Munich

International Classification:

G06K 9/00

US Classification:

382131, 378 4

Abstract:

A method for finding consistent mid-sagittal planes (MSPs) in a pair of 3D image head scans of a same patient includes, for each image, selecting a 2D transverse localizer image from a middle slice along a transverse view of the 3D image, fitting an ellipse to the transverse localizer image to locate a head position (x, y), where the y-coordinate is indicative of a position of a 2D coronal localizer image in the 3D image, fitting an ellipse to the coronal localizer image to locate a head position (x, y) in the coronal localizer image, calculating a middle line in the transverse localizer image and a middle line in the coronal localizer image, calculating an MSP from the middle lines, and determining a new set of slope and intercept parameters for one MSP that maximizes a similarity measure between the one MSP and the other MSP.

US Patent:

20090138237, May 28, 2009

Filed:

Dec 24, 2008

Appl. No.:

12/344052

Inventors:

Curtis E. Hrischuk - Holly Springs NC, US
Ed Emil Huth - Royal Palm Beach FL, US
Dazhi Wang - Durham NC, US
Li Zhang - Yorktown Heights NY, US

Assignee:

INTERNATIONAL BUSINESS MACHINES CORPORATION - Armonk NY

International Classification:

G06F 17/18

US Classification:

702179

Abstract:

A method of determining accuracy of predicted system behavior can include creating a plurality of noise adjusted analytical models, wherein each noise adjusted analytical model is associated with a set of predefined analytical model parameters. A set of inferred analytical model parameters for each noise adjusted analytical model can be derived. Each set of inferred analytical model parameters can depend upon a current noise adjusted analytical model and each prior noise adjusted analytical model. For each set of inferred analytical model parameters, a measure of error between the set of inferred analytical model parameters and the set of predefined analytical model parameters associated with the noise adjusted analytical model from which the set of inferred analytical model parameters was derived can be determined.