Ronald B Summers

US Patent:

7454045, Nov 18, 2008

Filed:

Feb 13, 2004

Appl. No.:

10/779210

Inventors:

Jianhua Yao - Laurel MD, US
Ronald M. Summers - Potomac MD, US

Assignee:

The United States of America as represented by the Department of Health and Human Services - Washington DC

International Classification:

G06K 9/00

US Classification:

382128, 382130, 382131, 382132, 382154, 382224

Abstract:

A virtual anatomical structure can be analyzed to determine enclosing three-dimensional boundaries of features therein. Various techniques can be used to determine tissue types in the virtual anatomical structure. For example, tissue types can be determined via an iso-boundary between lumen and air in the virtual anatomical structure and a fuzzy clustering approach. Based on the tissue type determination, a deformable model approach can be used to determine an enclosing three-dimensional boundary of a feature in the virtual anatomical structure. The enclosing three-dimensional boundary can be used to determine characteristics of the feature and classify it as of interest or not of interest.

US Patent:

20190370965, Dec 5, 2019

Filed:

Feb 22, 2018

Appl. No.:

16/488127

Inventors:

- Bethesda MD, US
Yohannes Tsehay - Silver Spring MD, US
Ronald M. Summers - Potomac MD, US
Baris Turkbey - Rockville MD, US
Matthew Greer - Bethesda MD, US
Ruida Cheng - Bethesda MD, US
Holger Roth - Theilheim, Bavaria, DE
Matthew J. McAuliffe - Bethesda MD, US
Sonia Gaur - Bethesda MD, US
Francesca Mertan - Bethesda MD, US
Peter Choyke - Rockville MD, US

Assignee:

The United States of America, as represented by the Secretary, Department of Health and Human Servic - Bethesda MD

International Classification:

G06T 7/00
G06N 20/00

Abstract:

Disclosed prostate computer aided diagnosis (CAD) systems employ a Random Forest classifier to detect prostate cancer. System classify individual pixels inside the prostate as potential sites of cancer using a combination of spatial, intensity and texture features extracted from three sequences. The Random Forest training considers instance-level weighting for equal treatment of small and large cancerous lesions and small and large prostate backgrounds. Two other approaches are based on an AutoContext pipeline intended to make better use of sequence-specific patterns. Also disclosed are methods and systems for accurate automatic segmentation of the prostate in MRI. Methods can include both patch-based and holistic (image-to-image) deep learning methods for segmentation of the prostate. A patch-based convolutional network aims to refine the prostate contour given an initialization. A method for end- to-end prostate segmentation integrates holistically nested edge detection with fully convolutional networks. HNNs automatically learn a hierarchical representation that improve prostate boundary detection.