Image analysis – Applications – Biomedical applications
Reexamination Certificate
2000-06-23
2004-10-05
Boudreau, Leo (Department: 2621)
Image analysis
Applications
Biomedical applications
C382S132000, C378S037000
Reexamination Certificate
active
06801645
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Field of the Invention
The present invention relates to a method and system for computer aided analysis of detections on digital images and, more particularly, to a method and system for assisting radiologists in reading medical images.
2. Related Prior Art
Computer aided detection (CAD) systems for mammography have been advocated for several decades. The objective of any medical CAD system is to indicate tissue regions that need a physician's attention while leaving normal tissue unmarked. Current systems use one or possibly two image inputs to detectors. If two images are input to a detector, the methods fall into one of two approaches.
The first approach is known as bilateral subtraction. In this method, the left and right breast images are subtracted to produce a difference image. Since cancer is typically unilateral and since bodies are relatively symmetric, in many cases the difference image emphasizes cancerous regions. The second approach is similar to bilateral subtraction. However, in this case, a temporal subtraction is performed wherein the same view of a body part taken at an earlier time is subtracted from the current image. This temporal subtraction is intended to highlight regions that have changed during the time interval between imaging sessions.
Both approaches can increase sensitivity of a detector, but suffer from two problems. First, the number of false indications is increased by the subtraction. Second, the images involved in the subtraction process must first be aligned. Alignment is not trivial since tissue is elastic. Therefore, the alignment method must compensate for translation, rotation, scale, and spatially dependent stretching.
The approach in this invention provides significant improvement relative to single image based detection methods. Furthermore, the CAD system described in this application exploits the information available from the entire set of images associated with a patient's screening mammography session, without requiring image subtraction or alignment.
SUMMARY OF THE INVENTION
The present invention provides a computer aided detection method and system to assist radiologists in the reading of medical images.
In a first step, a set of digital mammogram images is obtained, such as from mammograms obtained from a patient's screening visit. A rectangular analysis region containing breast tissue is segmented from each digital mammogram image, and a binary mask corresponding to the breast tissue is created.
Clustered microcalcifications are detected in a microcalcification detection step. Point features from each microcalcification are applied to a classifier trained to pass microcalcifications representative of malignant clusters. Those microcalcifications remaining after the classifier are represented by their centroid location and subsequently grouped into clusters. Features are computed from the clusters and each is subsequently assigned a class label and a quality score.
Densities are detected in a density detection step. In this step, a subsampled image is applied to a bank of DoG filters to produce an image with enhanced local bright spots. This image is then thresholded and the thresholded image is input to a screening classifier. Detections passing the screening classifier as suspicious are input to a region growing step and density features are computed from the region grown area. Detections are input to a density classification step, the output of which includes computed features, a class label, and two quality scores for each detection.
Detections, including both microcalcifications and densities, are further analyzed in a post processing stage. In a first post processing step, the detections across all the images in the case are considered collectively by case based ranking. In a second post processing step, within each image, the collection of detections across detection category are assigned to one of 29 image context categories based on associated quality scores. When certain image context categories of detections are observed on an image, all the detections on that image are removed. In the third post processing step, the remaining detections across all the images in the case are considered within microcalcification and density detection categories. Within each detection category, “normalcy” features are computed using the quality scores from all the detections in the case from that category. These normalcy features are applied to a classification stage designed to assign the entire case as “Normal” or “Not Normal”. When the classifier assigns the case as “Normal”, all detections of the corresponding category, microcalcification or density, are removed from the images in that case. The final output of the system is a set of indications which is displayed overlaid on the set of digital images.
It should be noted that the present method and system is in contrast to subtraction-based methods proposed by the prior art in that such prior art methods are inherently limited to two input images, whereas the present invention performs analysis of detections extending across a set of images for a patient, such as a set of four images forming a case for the patient. By exploiting the information available from the entire set of images associated with a patient's screening mammography session, the approach of the present invention provides significant improvement in accomplishing the objectives of obtaining both increased system sensitivity and reduction of false positive detections.
Other objects and advantages of the invention will be apparent from the following description, accompanying drawings and the appended claims.
REFERENCES:
patent: 4453266 (1984-06-01), Bacus
patent: 4723553 (1988-02-01), Miwa et al.
patent: 4736439 (1988-04-01), May
patent: 4747156 (1988-05-01), Wahl
patent: 4907156 (1990-03-01), Doi et al.
patent: 5133020 (1992-07-01), Giger et al.
patent: 5212637 (1993-05-01), Saxena
patent: 5260871 (1993-11-01), Goldberg
patent: 5268967 (1993-12-01), Jang et al.
patent: 5289374 (1994-02-01), Doi et al.
patent: 5291560 (1994-03-01), Daugman
patent: 5331550 (1994-07-01), Stafford et al.
patent: 5343390 (1994-08-01), Doi et al.
patent: 5359513 (1994-10-01), Kano et al.
patent: 5365429 (1994-11-01), Carman
patent: 5388143 (1995-02-01), MacMahon
patent: 5452367 (1995-09-01), Bick et al.
patent: 5463548 (1995-10-01), Asada et al.
patent: 5491627 (1996-02-01), Zhang et al.
patent: 5537485 (1996-07-01), Nishikawa et al.
patent: 5572565 (1996-11-01), Abdel-Mottaleb
patent: 5574799 (1996-11-01), Bankman et al.
patent: 5579360 (1996-11-01), Abdel-Mottaleb
patent: 5586160 (1996-12-01), Mascio
patent: 5598481 (1997-01-01), Nishikawa et al.
patent: 5615243 (1997-03-01), Chang et al.
patent: 5622171 (1997-04-01), Asada et al.
patent: 5625717 (1997-04-01), Hashimoto et al.
patent: 5627907 (1997-05-01), Gur et al.
patent: 5633948 (1997-05-01), Kegelmeyer, Jr.
patent: 5638458 (1997-06-01), Giger et al.
patent: 5657362 (1997-08-01), Giger et al.
patent: 5661820 (1997-08-01), Kegelmeyer, Jr.
patent: 5666434 (1997-09-01), Nishikawa et al.
patent: 5668888 (1997-09-01), Doi et al.
patent: 5673332 (1997-09-01), Nishikawa et al.
patent: 5729620 (1998-03-01), Wang
patent: 5729662 (1998-03-01), Rozmus
patent: 5732697 (1998-03-01), Zhang et al.
patent: 5740266 (1998-04-01), Weiss et al.
patent: 5740267 (1998-04-01), Echerer et al.
patent: 5740268 (1998-04-01), Nishikawa et al.
patent: 5757953 (1998-05-01), Jang
patent: 5761334 (1998-06-01), Nakajima et al.
patent: 5768333 (1998-06-01), Abdel-Mottaleb
patent: 5768406 (1998-06-01), Abdel-Mottaleb
patent: 5769074 (1998-06-01), Barnhill et al.
patent: 5799100 (1998-08-01), Clarke et al.
patent: 5815591 (1998-09-01), Roehrig et al.
patent: 5825910 (1998-10-01), Vafai
patent: 5825936 (1998-10-01), Clarke et al.
patent: 5857030 (1999-01-01), Gaborski et al.
patent: 5872859 (1999-02-01), Gur et al.
patent: 5917929 (1999-06-01), Marshall et al.
patent: 5999639 (1999-12-01), Rogers et al.
patent: 6014452 (2000-01-01), Zhang et al.
patent: 6035056 (200
Collins Michael J.
Mitchell Richard A.
Rogers Steven K.
Akhavannik Hussein
Boudreau Leo
Dinsmore & Shohl LLP
iCad, Inc.
LandOfFree
Computer aided detection of masses and clustered... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Computer aided detection of masses and clustered..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Computer aided detection of masses and clustered... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3287257