Search

Xiyun Song

from Cupertino, CA
Age ~53

Xiyun Song Phones & Addresses

  • 865 Bette Ave, Cupertino, CA 95014
  • 1000 Kiely Blvd, Santa Clara, CA 95051 (408) 615-9802
  • 234 Escuela Ave, Mountain View, CA 94040 (650) 210-9492
  • San Jose, CA
  • 18 Brookebury Dr, Reisterstown, MD 21136 (410) 526-9518
  • Chapel Hill, NC
  • 890 S Blaney Ave, Cupertino, CA 95014

Work

Position: Professional/Technical

Education

Degree: Graduate or professional degree

Publications

Us Patents

Isotropic Resolution Image Reconstruction

View page
US Patent:
8488850, Jul 16, 2013
Filed:
Mar 26, 2008
Appl. No.:
12/594512
Inventors:
Jinghan Ye - Fremont CA, US
Xiyun Song - Santa Clara CA, US
Assignee:
Koninklijke Philips Electronics N.V. - Eindhoven
International Classification:
G06K 9/00
US Classification:
382128
Abstract:
A nuclear imaging system () includes a radiation detector () having a distance dependent spatial resolution. A reconstructor () reconstructs projections acquired by the detector to generate image data. The reconstructor () applies a distance dependent projection filter () so as to reduce angular dependent resolution variations in the image space data.

Iterative Reconstruction Of Multiple-Peak Isotope Images

View page
US Patent:
20070183642, Aug 9, 2007
Filed:
Jan 25, 2007
Appl. No.:
11/627087
Inventors:
Jinghan Ye - Fremont CA, US
Mary K. Durbin - San Jose CA, US
Xiyun Song - Mountain View CA, US
Lingxiong Shao - Saratoga CA, US
Assignee:
KONINKLIJKE PHILIPS ELECTRONICS N.V. - Eindhoven
International Classification:
G06K 9/00
US Classification:
382131
Abstract:
In an imaging method, estimated data is iteratively projected and backprojected. The iterative projecting and backprojecting includes projecting or backprojecting the estimated data along parallel paths each employing energy-dependent parameters appropriate for a different energy. During each iteration, the estimated data is adjusted based on comparison of the estimated data with measured data.

Multi-Segment Reconstruction

View page
US Patent:
20100278412, Nov 4, 2010
Filed:
Jan 7, 2009
Appl. No.:
12/812040
Inventors:
Xiyun Song - Santa Clara CA, US
Zuo Zhao - Palo Alto CA, US
Jinghan Ye - Fremont CA, US
Lingxiong Shao - Saratoga CA, US
Assignee:
KONINKLIJKE PHILIPS ELECTRONICS N.V. - EINDHOVEN
International Classification:
G06T 7/00
US Classification:
382131
Abstract:
A medical imaging system includes a view transformation component () and a segment combiner (). The transformation component () transforms projection data in each view of a plurality of individual segments, which each includes at least one view. The transformed projection data for substantially similar views across the plurality of individual segments have a common radius of rotation. The segment combiner () combines the transformed projection data to produce a single data set that includes the transformed projection data for each of the views of each of the plurality of individual segments.

Image Registration Alignment Metric

View page
US Patent:
20100284598, Nov 11, 2010
Filed:
Jan 7, 2009
Appl. No.:
12/812045
Inventors:
Zuo Zhao - Palo Alto CA, US
Lingxiong Shao - Saratoga CA, US
Jinghan Ye - Fremont CA, US
Xiyun Song - Santa Clara CA, US
Assignee:
KONINKLIJKE PHILIPS ELECTRONICS N.V. - EINDHOVEN
International Classification:
G06K 9/32
G06K 9/00
US Classification:
382131, 382294, 382128
Abstract:
A method includes obtaining a combined data set that includes first and second imaging data sets. The first and second imaging data sets correspond to different imaging modalities. The method further includes determining a metric indicative of an alignment between the first and second imaging data sets in the combined data set. The method further includes presenting the metric in a human readable format.

Receiver Operating Characteristic-Based Training

View page
US Patent:
20100311034, Dec 9, 2010
Filed:
Aug 26, 2008
Appl. No.:
12/675414
Inventors:
Horace Hines - San Jose CA, US
Lingxiong Shao - Saratoga CA, US
Zuo Zhao - Palo Alto CA, US
Xiyun Song - Santa Clara CA, US
Assignee:
KONINKLIJKE PHILIPS ELECTRONICS N.V. - EINDHOVEN
International Classification:
G09B 7/00
G06F 17/30
G09B 25/00
US Classification:
434362, 434428, 707802, 707E17044
Abstract:
A presentation component () presents information from one or more data source(s) () to an assessor for assessment. A receiver operating characteristic (ROC) analyzer uses an ROC analysis technique to evaluate the performance of the assessor. A feedback component () provides feedback as to the assessor's performance. A data manipulator () facilitates manipulation of the presented data.

Hybrid Dual-Modality Image Processing System And Method

View page
US Patent:
20120002857, Jan 5, 2012
Filed:
Feb 9, 2010
Appl. No.:
13/203507
Inventors:
Xiyun Song - Santa Clara CA, US
Angela Da Silva - Danville CA, US
Jinghan Ye - Fremont CA, US
Alicia Wong - Antioch CA, US
Sudhir K. Mahakali - Cupertino CA, US
Jingkun Hu - Dublin CA, US
International Classification:
G06K 9/00
US Classification:
382131
Abstract:
Hybrid dual-modality image processing systems and methods are disclosed. For example, an image processing system includes a computer for processing SPECT tomographic projection data and a CT volume image. The computer derives a SPECT transverse volume image from the projection data and registers the SPECT transverse volume image with the CT volume image to obtain an attenuation map and registration information. The computer uses the attenuation map and the registration information to derive a SPECT transverse volume image with attenuation correction. The computer uses the registration information to derive a SPECT transverse volume image without attenuation correction. The SPECT transverse volume images, with and without attenuation correction, are derived at or near the same time, using the same registration information. The registration information is stored in, carried by, or otherwise communicated through the attenuation map for subsequent processing of the SPECT transverse volume images.

Image Reconstruction Including Shift-Variant Blur Compensation

View page
US Patent:
20120114212, May 10, 2012
Filed:
Jun 15, 2010
Appl. No.:
13/383584
Inventors:
Michael A. King - Northboro MA, US
Joyeeta Mitra Mukherjee - Worcester MA, US
Lingxiong Shao - Saratoga CA, US
Xiyun Song - Santa Clara CA, US
Jiong Wang - Santa Clara CA, US
Assignee:
KONINKLIJKE PHILIPS ELECTRONICS N.V. - EINDHOVEN
International Classification:
G06K 9/00
US Classification:
382131
Abstract:
An image reconstruction method comprises reconstructing an image using an iterative reconstruction method and computing a projection used in the reconstructing by summing ray increments between neighboring planes (P P P . . . ) parallel with a detector face () with stationary incremental blurring associated with each ray increment computed based on a distance between the neighboring parallel planes. A non-stationary blurring kernel may also be convolved at a plane closest to the detector face to generate a projection incorporating shift-variant blurring.

Heart Location And Verification In Emission Images

View page
US Patent:
20130142410, Jun 6, 2013
Filed:
Jul 18, 2011
Appl. No.:
13/817148
Inventors:
Shekhar Dwivedi - Lucknow, IN
Xiyun Song - Cupertino CA, US
Teimuraz Bandzava - San Jose CA, US
Jinghan Ye - Cupertino CA, US
Satrajit Misra - Cupertino CA, US
Assignee:
KONINKLIJKE PHILIPS ELECTRONICS N.V. - EINDHOVEN
International Classification:
A61B 6/00
A61B 5/0402
G06K 9/46
A61B 6/03
US Classification:
382131, 600427
Abstract:
An apparatus comprises: an imaging system () configured to acquire emission data from a cyclically varying element; a monitoring instrument () configured to measure the cyclical varying of the cyclically varying element; and an electronic device () configured to locate an image feature corresponding to the cyclically varying element in the acquired emission data based on correlation of time variation of the emission data with the cyclical varying of the cyclically varying element measured by the monitoring instrument. The located image feature may be verified by: thresholding a projection image generated from the emission data to generate a mask image; identifying in the mask image one of (i) a hollow circular feature, (ii) a hollow oval feature, (iii) a circular cavity feature, and (iv) an oval cavity feature; and verifying the located image feature based on whether the identifying operation is successful
Xiyun Song from Cupertino, CA, age ~53 Get Report