Li I Fan

Author:

Li Fan

ISBN #:

3443510302

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:

6993174, Jan 31, 2006

Filed:

Sep 7, 2001

Appl. No.:

09/947629

Inventors:

Li Fan - Plainsboro NJ, US
Benjamin Odry - Princeton NJ, US
Jianzhong Qian - Princeton Junction NJ, US

Assignee:

Siemens Corporate Research, Inc - Princeton NJ

International Classification:

G06K 9/00

US Classification:

382131, 382173, 382256

Abstract:

Segmentation of pulmonary nodules from digital volumetric image includes segmenting, automatically, the pulmonary nodule from attached anatomical structures by analyzing a structure of interest, and providing a template according to an analyzed structure of interest, wherein the template displays a segmentation of a volume of interest including an object of interest. The template can be adjusted according to a one or more adjustable parameters. The method stores values of the parameters according to the object of interest, and stores a segmentation of the object of interest according to the values of the parameters. The segmentation is refined by extracting and labeling surrounding anatomical structures, defining each structure touching a boundary of a volume of interest as an elongated object, determining a size and shape for each structure, and determining a distance of a current structure to the segmentation result, upon determining the distance to be small compared to a threshold.

US Patent:

7020316, Mar 28, 2006

Filed:

Dec 5, 2001

Appl. No.:

10/008119

Inventors:

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

Assignee:

Siemens Corporate Research, Inc. - Princeton NJ

International Classification:

G06K 9/00

US Classification:

382131

Abstract:

A system and method for automatically detecting nodules from images include a seed point generation unit for generating a seed point from a plurality of images that define a volume, a volume of interest generation unit for defining a volume of interest comprising the seed point and optionally smoothing the volume of interest with a set of pre-selected scales, a volume projection unit for choosing principal viewing axes within the volume of interest, re-slicing the volume of interest along one of the principal viewing axes and computing volume projection curves of the re-sliced volumes along the principal viewing axes, and a volume projection analysis unit for analyzing the shapes of the volume projection curves, and detecting a nodule in accordance with the analyzed shapes.

US Patent:

7088850, Aug 8, 2006

Filed:

Apr 14, 2005

Appl. No.:

11/106271

Inventors:

Jian-Zhong Qian - Princeton Junction NJ, US
Li Fan - Belle Mead NJ, US
Cheng-Chung Liang - West Windsor NJ, US

Assignee:

Edda Technology, Inc. - Princeton Junction NJ

International Classification:

G06K 9/00
G06K 9/32

US Classification:

382128, 382294

Abstract:

Method and system for lesion detection is disclosed. A lesion is detected from each data set in the spatial domain based on an organ intensity subtracted (OIST) image. In the temporal domain, the lesion is detected based on a maximum frequency-magnitude difference (MFMD) map across a plurality of data sets. The detection result from the spatial domain and the detection result from the temporal domain are integrated to produce an integrated lesion detection result.

US Patent:

7203349, Apr 10, 2007

Filed:

Jan 29, 2002

Appl. No.:

10/059848

Inventors:

Li Zhang - Plainsboro NJ, US
Li Fan - Plainsboro NJ, US
Jianzhong Qian - Princeton Junction NJ, US

Assignee:

Siemens Corporate Research, Inc. - Princeton NJ

International Classification:

G06K 9/00

US Classification:

382128, 128922, 378 4

Abstract:

A system and method for automatically reducing false-positive nodule candidates associated with airways includes receiving a nodule candidate, testing for airway cavities connected to the candidate, and recognizing the candidate as a false-positive nodule candidate if it is connected to an airway cavity; where the testing may include perpendicular testing for airways that are relatively perpendicular to an examination plane and parallel testing for airways that are relatively parallel to an examination plane.

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:

7315304, Jan 1, 2008

Filed:

Apr 14, 2005

Appl. No.:

11/105638

Inventors:

Cheng-Chung Liang - West Windsor NJ, US
Jian-Zhong Qian - Princeton Junction NJ, US
Li Fan - Belle Mead NJ, US
Xiaolan Zeng - Princeton NJ, US

Assignee:

Edda Technology, Inc. - Princeton Junction NJ

International Classification:

G06T 15/50

US Classification:

345426, 345419, 345424, 600437

Abstract:

Method and system for multiple volume exploration is disclosed. A first 3D volume is rendered in a first region. One or representations are displayed in a second region, where each representation signifies a stack of 2D images. A first stack represents one or more 2D images of cross sections of a certain orientation from the first 3D volume. Each of the other stacks includes one or more 2D images of cross sections of the same orientation from a 3D volume related to the first 3D volume.

US Patent:

7639848, Dec 29, 2009

Filed:

Apr 14, 2005

Appl. No.:

11/105957

Inventors:

Jian-Zhong Qian - Princeton Junction NJ, US
Li Fan - Belle Mead NJ, US

Assignee:

Edda Technology, Inc. - Princeton Junction NJ

International Classification:

G06K 9/00
G01N 35/00

US Classification:

382128, 436 43

Abstract:

Method and system for quality assurance in lesion marking is disclosed. A marking is created based on a patient study on display in a manner in accordance with an electronically enforced protocol. One or more features are generated based on the marking. Quality of the marking is assessed based on such computed one or features.