Thomas F Rathbun

US Patent:

6389157, May 14, 2002

Filed:

Jan 11, 2001

Appl. No.:

09/758889

Inventors:

Steven K. Rogers - Beavercreek OH
Randy P. Broussard - Huber Heights OH
Edward M. Ochoa - San Antonio TX
Thomas F. Rathbun - Beavercreek OH
John E. Rosenstengel - Huber Heights OH

Assignee:

Qualia Computing, Inc. - Beavercreek OH

International Classification:

G06K 900

US Classification:

382132, 382260, 382270

Abstract:

A method and system for detecting and displaying clustered microcalcifications in a digital mammogram, wherein a single digital mammogram is first automatically cropped to a breast area sub-image which is then processed by means of an optimized Difference of Gaussians filter to enhance the appearance of potential microcalcifications in the sub-image. The potential microcalcifications are thresholded, clusters are detected, features are computed for the detected clusters, and the clusters are classified as either suspicious or not suspicious by means of a neural network. Thresholding is preferably by sloping local thresholding, but may also be performed by global and dual-local thresholding. The locations in the original digital mammogram of the suspicious detected clustered microcalcifications are indicated. Parameters for use in the detection and thresholding portions of the system are computer-optimized by means of a genetic algorithm.

US Patent:

6556699, Apr 29, 2003

Filed:

Aug 24, 2001

Appl. No.:

09/938908

Inventors:

Steven K. Rogers - Beavercreek OH
Philip Amburn - Dayton OH
Telford S. Berkey - London OH
Randy P. Broussard - Huber Heights OH
Martin P. DeSimio - Fairborn OH
Jeffrey W. Hoffmeister - Beavercreek OH
Edward M. Ochoa - San Antonio TX
Thomas P. Rathbun - Beavercreek OH
John E. Rosenstengel - Huber Heights OH

Assignee:

Qualia Computing, Inc. - Beavercreek OH

International Classification:

G06K 900

US Classification:

382132, 128922

Abstract:

A method and system for detecting and displaying clustered microcalcifications in a digital mammogram, wherein a single digital mammogram is first automatically cropped to a breast area sub-image which is then processed by means of an optimized Difference of Gaussians filter to enhance the appearance of potential microcalcifications in the sub-image. The potential microcalcifications are thresholded, clusters are detected, features are computed for the detected clusters, and the clusters are classified as either suspicious or not suspicious by means of a neural network. Thresholding is preferably by sloping local thresholding, but may also be performed by global and dual-local thresholding. The locations in the original digital mammogram of the suspicious detected clustered microcalcifications are indicated. Parameters for use in the detection and thresholding portions of the system are computer-optimized by means of a genetic algorithm.

US Patent:

6650766, Nov 18, 2003

Filed:

Oct 25, 2002

Appl. No.:

10/280237

Inventors:

Steven K. Rogers - Beavercreek OH
Philip Amburn - Dayton OH
Telford S. Berkey - London OH
Randy P. Broussard - West River MD
Martin P. DeSimio - Fairborn OH
Jeffrey W. Hoffmeister - Manhattan Beach CA
Edward M. Ochoa - Franklin OH
Thomas F. Rathbun - Monument CO
John E. Rosenstengel - Beavercreek OH

Assignee:

Qualia Computing, Inc. - Beavercreek OH

International Classification:

G06K 900

US Classification:

382132, 128922

Abstract:

A method and system for detecting and displaying clustered microcalcifications in a digital mammogram, wherein a single digital mammogram is first automatically cropped to a breast area sub-image which is then processed by means of an optimized Difference of Gaussians filter to enhance the appearance of potential microcalcifications in the sub-image. The potential microcalcifications are thresholded, clusters are detected, features are computed for the detected clusters, and the clusters are classified as either suspicious or not suspicious by means of a neural network. Thresholding is preferably by sloping local thresholding, but may also be performed by global and dual-local thresholding. The locations in the original digital mammogram of the suspicious detected clustered microcalcifications are indicated. Parameters for use in the detection and thresholding portions of the system are computer-optimized by means of a genetic algorithm.

US Patent:

61671460, Dec 26, 2000

Filed:

Oct 14, 1999

Appl. No.:

9/418662

Inventors:

Steven K. Rogers - Beavercreek OH
Philip Amburn - Dayton OH
Telford S. Berkey - London OH
Randy P. Broussard - Huber Heights OH
Martin P. Desimio - Fairborn OH
Jeffrey W. Hoffmeister - Beavercreek OH
Edward M. Ochoa - San Antonio TX
Thomas F. Rathbun - Beavercreek OH
John E. Rosenstengel - Huber Heights OH

Assignee:

Qualia Computing, Inc. - Beavercreek OH

International Classification:

G06K 936

US Classification:

382132

Abstract:

A method and system for detecting and displaying clustered microcalcifications in a digital mammogram, wherein a single digital mammogram is first automatically cropped to a breast area sub-image which is then processed by means of an optimized Difference of Gaussians filter to enhance the appearance of potential microcalcifications in the sub-image. The potential microcalcifications are thresholded, clusters are detected, features are computed for the detected clusters, and the clusters are classified as either suspicious or not suspicious by means of a neural network. Thresholding is preferably by sloping local thresholding, but may also be performed by global and dual-local thresholding. The locations in the original digital mammogram of the suspicious detected clustered microcalcifications are indicated. Parameters for use in the detection and thresholding portions of the system are computer-optimized by means of a genetic algorithm.

US Patent:

61154881, Sep 5, 2000

Filed:

Oct 14, 1999

Appl. No.:

9/418382

Inventors:

Steven K. Rogers - Beavercreek OH
Philip Amburn - Dayton OH
Telford S. Berkey - London OH
Randy P. Broussard - Huber Heights OH
Martin P. Desimio - Fairborn OH
Jeffrey W. Hoffmeister - Beavercreek OH
Edward M. Ochoa - San Antonio TX
Thomas P. Rathbun - Beavercreek OH
John E. Rosenstengel - Huber Heights OH

Assignee:

Qualia Computing, Inc. - Beavercreek OH

International Classification:

G06K 900

US Classification:

382132

Abstract:

A method and system for detecting and displaying clustered microcalcifications in a digital mammogram, wherein a single digital mammogram is first automatically cropped to a breast area sub-image which is then processed by means of an optimized Difference of Gaussians filter to enhance the appearance of potential microcalcifications in the sub-image. The potential microcalcifications are thresholded, clusters are detected, features are computed for the detected clusters, and the clusters are classified as either suspicious or not suspicious by means of a neural network. Thresholding is preferably by sloping local thresholding, but may also be performed by global and dual-local thresholding. The locations in the original digital mammogram of the suspicious detected clustered microcalcifications are indicated. Parameters for use in the detection and thresholding portions of the system are computer-optimized by means of a genetic algorithm.

US Patent:

59996390, Dec 7, 1999

Filed:

Aug 28, 1998

Appl. No.:

9/141802

Inventors:

Steven K. Rogers - Beavercreek OH
Philip Amburn - Dayton OH
Telford S. Berkey - London OH
Randy P. Broussard - Huber Heights OH
Martin P. DeSimio - Fairborn OH
Jeffrey W. Hoffmeister - Beavercreek OH
Edward M. Ochoa - San Antonio TX
Thomas P. Rathbun - Beavercreek OH
John E. Rosenstengel - Huber Heights OH

Assignee:

Qualia Computing, Inc. - Beavercreek OH

International Classification:

G06K 900

US Classification:

382132

Abstract:

A method and system for detecting and displaying clustered microcalcifications in a digital mammogram, wherein a single digital mammogram is first automatically cropped to a breast area sub-image which is then processed by means of an optimized Difference of Gaussians filter to enhance the appearance of potential microcalcifications in the sub-image. The potential microcalcifications are thresholded, clusters are detected, features are computed for the detected clusters, and the clusters are classified as either suspicious or not suspicious by means of a neural network. Thresholding is preferably by sloping local thresholding, but may also be performed by global and dual-local thresholding. The locations in the original digital mammogram of the suspicious detected clustered microcalcifications are indicated. Parameters for use in the detection and thresholding portions of the system are computer-optimized by means of a genetic algorithm.

US Patent:

61378984, Oct 24, 2000

Filed:

Nov 25, 1998

Appl. No.:

9/200128

Inventors:

Randy P. Broussard - Huber Heights OH
Thomas F. Rathbun - Beavercreek OH
Steven K. Rogers - Beavercreek OH

Assignee:

Qualia Computing, Inc. - Beavercreek OH

International Classification:

G06K 900

US Classification:

382132

Abstract:

A method and system for detecting and displaying clustered microcalcifications in a digital mammogram, wherein a single digital mammogram is first automatically cropped to a breast area sub-image which is then processed by means of an optimized Difference of Gaussians filter to enhance the appearance of potential microcalcifications in the sub-image. The potential microcalcifications are thresholded, clusters are detected, features are computed for the detected clusters, and the clusters are classified as either suspicious or not suspicious by means of a neural network. Thresholding is preferably by sloping local thresholding, but may also be performed by global and dual-local thresholding. The locations in the original digital mammogram of the suspicious detected clustered microcalcifications are indicated. Parameters for use in the detection and thresholding portions of the system are computer-optimized by means of a genetic algorithm.

US Patent:

62052365, Mar 20, 2001

Filed:

Oct 12, 1999

Appl. No.:

9/416437

Inventors:

Steven K. Rogers - Beavercreek OH
Philip Amburn - Dayton OH
Telford S. Berkey - London OH
Randy P. Broussard - Huber Heights OH
Martin P. DeSimio - Fairborn OH
Jeffrey W. Hoffmeister - Beavercreek OH
Edward M. Ochoa - San Antonio TX
Thomas F. Rathbun - Beavercreek OH
John E. Rosenstengel - Huber Heights OH

Assignee:

Qualia Computing, Inc. - Beavercreek OH

International Classification:

G06K 900

US Classification:

382132

Abstract:

A method and system for detecting and displaying clustered microcalcifications in a digital mammogram, wherein a single digital mammogram is first automatically cropped to a breast area sub-image which is then processed by means of an optimized Difference of Gaussians filter to enhance the appearance of potential microcalcifications in the sub-image. The potential microcalcifications are thresholded clusters are detected, features are computed for the detected clusters, and the clusters are classified as either suspicious or not suspicious by means of a neural network. Thresholding is preferably by sloping local thresholding but may also be performed by global and dual-local thresholding. The locations in the original digital mammogram of the suspicious detected clustered microcalcifications are indicated. Parameters for use in the detection and thresholding portions of the system are computer-optimized by means of a genetic algorithm.