Hong M Shen

US Patent:

6738063, May 18, 2004

Filed:

Feb 7, 2002

Appl. No.:

10/071003

Inventors:

Hong Shen - Plainsboro NJ
Jianzhong Qian - Princeton Junction NJ
Li Fan - Plainsboro NJ

Assignee:

Siemens Corporate Research, Inc. - Princeton NJ

International Classification:

G06T 1700

US Classification:

345424, 345420, 345593, 345594, 382130, 382154

Abstract:

Disclosed is a method for object correspondence identification between two image sets, said method steps comprising roughly aligning the two image sets, receiving a selected point in said one image set, locating a rough matching point in said another image, defining a first volume-of-interest around said selected point, defining a search window around said matching point comprising a plurality of neighboring points, for every point in said search window, defining a second volume-of-interest, computing the similarity between each said second volume-of-interest with said first volume-of-interest, and selecting that second volume-of-interest that is most similar to said first volume-of-interest.

US Patent:

6932611, Aug 23, 2005

Filed:

Jul 31, 2001

Appl. No.:

10/343516

Inventors:

Hong Shen - Plainsboro NJ, US
Michael Shur - Latham NY, US
Tor Fjeldly - Oslo, NO

Assignee:

Rensselaer Polytechnic Institute - Troy NY

International Classification:

G09B023/00

US Classification:

434276, 434118, 434224, 434350, 434362, 709203, 700 65

Abstract:

The invention includes a method for a client to remotely conduct a laboratory experiment using a remote computer communicating with a host computer in a computer network. The experiment is stimulated by a set of input variable and provides a set of dependent output variables. The method includes the steps of an instructor setting up the experiment at a central location, determining a tolerance band for each input variable of the experiment, and restricting a range of each tolerance band. The instructor enters into the host computer a program to run the experiment. The client remotely access the experiment using the remote computer. The instructor enables the client to conduct the experiment and simultaneously limits the client to the range of each tolerance band.

US Patent:

7296239, Nov 13, 2007

Filed:

Mar 4, 2002

Appl. No.:

10/090314

Inventors:

Hong Shen - Plainsboro NJ, US
Jianzhong Qian - Princeton Junction NJ, US
Li Fan - Plainsboro NJ, US

Assignee:

Siemens Corporate Research, Inc. - Princeton NJ

International Classification:

G06F 15/00
G06F 13/00

US Classification:

715764, 715732

Abstract:

Disclosed is a graphical user interface, comprising a plurality of main displays, each for displaying an image set, a user interactive system for receiving from a user a first location of an object-of-interest in one of said image sets, and a correlation system for finding and displaying a second location, corresponding to said first location, of a corresponding second volume-of-interest in at least one of said other image sets.

US Patent:

7301535, Nov 27, 2007

Filed:

Aug 15, 2005

Appl. No.:

11/203725

Inventors:

Hong Shen - Plainsboro NJ, US

Assignee:

Siemens Medical Solutions USA, Inc. - Malvern PA

International Classification:

G06T 17/00

US Classification:

345324, 345419, 382132, 382154, 600407

Abstract:

A computer-implemented method for visualizing a tumor in a volume data includes providing a plurality of tumors, detected and segmented from the volume data, storing locations of a plurality of voxels corresponding to each of the plurality of tumors, and determining a mesh of surface voxels for each of the plurality of tumors from the stored locations. The method further includes rendering the meshes for each of the plurality of tumors in a volume rendering window, selecting a tumor of interest from the plurality of tumors rendered in the volume rendering window, and determining a correspondence of the selected tumor to a slice of the volume data, wherein the slice of the volume data is displayed in a main window.

US Patent:

7369693, May 6, 2008

Filed:

Jun 17, 2004

Appl. No.:

10/870305

Inventors:

Hong Shen - Princeton NJ, US

Assignee:

Siemens Medical Solutions USA, Inc. - Malvern PA

International Classification:

G06K 9/00

US Classification:

382128, 382293

Abstract:

We introduce a thoracic cage coordinate system for recording pathology locations in lung CT volume data. The centerlines of each individual rib are extracted and labeled from top to bottom. For each pair of ribs, a three-dimensional (“3D”) orthogonal basis is computed by eigen-analysis of the rib centerline points, which are taken as the x, y, and z axes. The rib pairs form a set of reference planes. Therefore, there are a set of coordinate systems (x, y, z), each of which is locally valid between two adjacent planes. To define a location globally, a fourth parameter, n, is added to identify the serial number of the reference plane. The complete coordinate is recorded as (n, x, y, z). This system is robust against deformations due to bending and twisting, and is relatively stable over inhalation. Further, this system may be readily adapted in other 3D modalities, such as MRI volume data.

US Patent:

7379576, May 27, 2008

Filed:

Oct 27, 2004

Appl. No.:

10/974313

Inventors:

Hong Shen - Princeton NJ, US
Benjamin Odry - West New York NJ, US
Shuping Qing - Princeton NJ, US

Assignee:

Siemens Medical Solutions USA, Inc. - Malvern PA

International Classification:

G06K 9/00

US Classification:

382131, 382128, 378 4, 378 21, 378901

Abstract:

A method of identifying a patient from digital medical images includes providing a first digital image volume of an organ of a patient and a second digital image volume of the same organ, segmenting each slice of the first image volume and calculating a cross-sectional area of the organ in each slice to form a first area profile, segmenting each slice of the second image volume and calculating a cross-sectional area of the organ in each slice to form a second area profile, and comparing the first area profile with the second area profile to determine a correlation value for the two profiles. Based on the correlation value between the first area profile and the second area profile, it is determined whether the first digital image volume of the organ and the second digital image volume of the same organ came from the same patient.

US Patent:

7397475, Jul 8, 2008

Filed:

Aug 15, 2005

Appl. No.:

11/203792

Inventors:

Hong Shen - Plainsboro NJ, US
Shuping Qing - Princeton NJ, US

Assignee:

Siemens Medical Solutions USA, Inc. - Malvern PA

International Classification:

G06T 15/00

US Classification:

345420, 345424, 600407

Abstract:

A computer-implemented method for building an atlas includes providing a volume data for a plurality of bones, segmenting, individually, the plurality of bones from the volume data, storing locations of a plurality of voxels for each of the plurality of bones, wherein each of the plurality of bones is registered with a dedicated list of locations, wherein the locations are locations in a coordinate system of the volume data, selecting one or more of the plurality of bones, forming a selected structure, and rendering the selected structure in the coordinate system of the volume data according to the dedicated list of locations of each of the plurality of bones in the selected structure, wherein a rendering is displayed by a display.

US Patent:

7471815, Dec 30, 2008

Filed:

Jun 29, 2005

Appl. No.:

11/170421

Inventors:

Lin Hong - Monmouth Junction NJ, US
Yonggang Shi - San Diego CA, US
Hong Shen - Princeton NJ, US
Shuping Qing - Princeton NJ, US

Assignee:

Siemens Medical Solutions USA, Inc. - Malvern PA

International Classification:

G06K 9/00
A61B 6/00
G01N 23/00
G21K 1/12
H05G 1/60

US Classification:

382128, 378 4, 378 21

Abstract:

A computer-implemented method for candidate generation in three-dimensional volumetric data comprises forming a binary volumetric image of the three-dimensional volumetric data including labeled foreground voxels, estimating a plurality of shape features of the labeled foreground voxels in the binary volumetric data including, identifying peak voxels and high curvature voxels from the foreground voxels in the binary volumetric image, accumulating a plurality of confidence values for boundary and each peak voxel, and detecting confidence peaks from the plurality of confidence values, wherein the confidence peaks are determined to be the candidate points, and refining the candidate points given detected confidence peaks, wherein refined candidate points are determined to be candidates.