Richard Mitchell

US Patent:

6757415, Jun 29, 2004

Filed:

Jun 13, 2003

Appl. No.:

10/461301

Inventors:

Steven K. Rogers - Beavercreek OH
Kenneth W. Bauer - Fairborn OH
Michael J. Collins - Beavercreek OH
Martin P. DeSimio - Fairborn OH
Richard A. Mitchell - Springboro OH

Assignee:

Qualia Computing, Inc. - Beavercreek OH

International Classification:

G06K 900

US Classification:

382130, 382132

Abstract:

A computer aided detection method and system to assist radiologists in the reading of medical images. The method and system has particular application to the area of mammography including detection of clustered microcalcifications and densities. A microcalcification detector is provided wherein individual detections are rank ordered and classified, and one of the features for classification is derived using a multilayer perceptron. A density detector is provided including an iterative, dynamic region growing module with embedded subsystem for rank ordering and classification of a best subset of candidate masks. Features are computed from a detection on an input image by providing first and second regions on the input image corresponding to areas inside and outside the detection, measurements are computed based on values derived from the two regions, a standard deviation is computed for the measurements in each region, and a feature for the detection is computed using a Bauer-Fisher ratio. A post processing stage is provided where detections are analyzed in the context of a set of images for a patient. The final output of the system is a set of indications overlaid on the input medical images.

US Patent:

6763128, Jul 13, 2004

Filed:

Jun 13, 2003

Appl. No.:

10/461316

Inventors:

Steven K. Rogers - Beavercreek OH
Michael J. Collins - Beavercreek OH
Richard A. Mitchell - Springboro OH

Assignee:

Qualia Computing, Inc. - Beavercreek OH

International Classification:

B06K 900

US Classification:

382130, 378 37

Abstract:

A computer aided detection method and system to assist radiologists in the reading of medical images. The method and system has particular application to the area of mammography including detection of clustered microcalcifications and densities. A microcalcification detector is provided wherein individual detections are rank ordered and classified, and one of the features for classification is derived using a multilayer perceptron. A density detector is provided including an iterative, dynamic region growing module with embedded subsystem for rank ordering and classification of a best subset of candidate masks. A post processing stage is provided where detections are analyzed in the context of a set of images for a patient. The post processing includes a normalcy classification including providing computed values corresponding to each detection from a category of detections on an image set, computing a normalcy value using the computed values, and removing all detections from an image set when the normalcy value does not meet a predetermined condition. The final output of the system is a set of indications overlaid on the input medical images.

US Patent:

6801645, Oct 5, 2004

Filed:

Jun 23, 2000

Appl. No.:

09/602762

Inventors:

Michael J. Collins - Beavercreek OH
Steven K. Rogers - Beavercreek OH
Richard A. Mitchell - Springboro OH

Assignee:

iCad, Inc. - Nashua NH

International Classification:

G06K 900

US Classification:

382130, 382132, 378 37

Abstract:

A computer aided detection method and system to assist radiologists in the reading of medical images. The method and system has particular application to the area of mammography including detection of clustered microcalcifications and densities. A microcalcification detector is provided wherein individual detections are rank ordered and classified, and one of the features for classification is derived using a multilayer perceptron. A density detector is provided including an iterative, dynamic region growing module with embedded subsystem for rank ordering and classification of a best subset of candidate masks. A post processing stage is provided where detections are analyzed in the context of a set of images for a patient. Three analysis methods are used to distribute a limited number of detections across the image set and further within each image, and additionally to perform a normalcy classification. The normalcy classification is used to remove all detections from an image set when predetermined normalcy conditions are met.

US Patent:

7298877, Nov 20, 2007

Filed:

Nov 6, 2002

Appl. No.:

10/288766

Inventors:

Michael J. Collins - Beavercreek OH, US
Richard A. Mitchell - Springboro OH, US
Steven W. Worrell - Beavercreek OH, US

Assignee:

ICad, Inc. - Nashua NH

International Classification:

G06K 9/00
G06K 9/62
G06K 9/34
G01N 23/00
A61B 6/00

US Classification:

382128, 382155, 382173, 382181, 378 1, 378 4

Abstract:

This invention provides an information fusion method for multiple indicators of cancers detected with multiple channels. Each channel consists of specifically tuned detectors, features, classifiers and Bayes networks. The outputs of the Bayes networks are probabilities of malignancy for the detections passing the corresponding classifier.

US Patent:

7333645, Feb 19, 2008

Filed:

Oct 26, 2004

Appl. No.:

10/973837

Inventors:

Richard A. Mitchell - Springboro OH, US
Michael J. Collins - Beavercreek OH, US

Assignee:

iCAD, Inc. - Beavercreek OH

International Classification:

G06K 9/00

US Classification:

382128, 382132, 128920, 128922

Abstract:

The method and system for exploiting information from multiple images in a mammographic computer-aided detection application is disclosed. A pair of images is obtained by a CAD system. The images are processed to produce a set of regions of interest (ROIs) to be associated with each image. A ROI is selected from the first image of the pair. This ROI is identified and matched to a ROI in the second image. The single image feature values are obtained by the two ROIs of the image pair. Transforming the image feature value to an integer value produces a pair of integers for each image feature value. The pair of integers defines the element of the pre-determined co-occurrence matrix. An element of a predetermined co-occurrence matrix is selected to provide evidence value for the ROI of the first image.