Image analysis – Applications – Biomedical applications
Reexamination Certificate
2002-08-30
2004-01-27
Johns, Andrew W. (Department: 2621)
Image analysis
Applications
Biomedical applications
C382S218000
Reexamination Certificate
active
06683973
ABSTRACT:
BACKGROUND OF THE INVENTION
Field of the Invention
This invention relates to a process, system and computer readable medium for the automated detection of pulmonary nodules in medical images. The present invention also generally relates to computerized techniques for automated analysis of digital images, for example, as disclosed in one or more of U.S. Pat. Nos. 4,839,807; 4,841,555; 4,851,984; 4,875,165; 4,907,156; 4,918,534; 5,072,384; 5,133,020; 5,150,292; 5,224,177; 5,289,374; 5,319,549; 5,343,390; 5,359,513; 5,452,367; 5,463,548; 5,491,627; 5,537,485; 5,598,481; 5,622,171; 5,638,458; 5,657,362; 5,666,434; 5,673,332; 5,668,888; 5,740,268; 5,790,690; 5,832,103; 5,873,824; 5,881,124; 5,931,780; 5,974,165 (PCT Publication WO 95/15537); 5,982,915; 5,984,870; 5,987,345; 6,011,862; 6,058,322; 6,067,373; 6,075,878; 6,078,680; 6,088,473; 6,112,112; 6,138,045; and 6,141,437, as well as U.S. patent application Ser. Nos. 08/173,935; 08/900,188; 08/900,189; 08/979,639; 08/982,282; 09/027,468; 09/028,518; 09/092,004; 09/121,719; 09/141,535; 09/298,852 and 09/471,088; and U.S. provisional patent application Nos. 60/107,095; 60/160,790; 60/176,297; 60/176,304; 60/180,162; 60/193,072 and 60/207,401, all of which are incorporated herein by reference.
The present invention includes use of various technologies referenced and described in the above-noted U.S. patents and patent applications, as well as described in the references identified in the appended APPENDIX by the author(s) and year of publication and cross-referenced throughout the specification by bold numerals in brackets corresponding to the respective references listed in the APPENDIX, the entire contents of which, including the related patents and applications listed above and references listed in the APPENDIX, are incorporated herein by reference.
DISCUSSION OF THE BACKGROUND
It has been reported that radiologists can fail to detect pulmonary nodules on chest radiographs in as many as 30% of positive cases. [1, 2] Many of the lung cancers missed by radiologists were actually visible in retrospect on previous radiographs. [3] Therefore, the inventors and others at the University of Chicago Department of Radiology have developed a computer-aided diagnostic (CAD) scheme to assist radiologists in the detection of pulmonary nodules on digital chest radiographs. [4-9] One problem with the pre-existing scheme is the relatively large number of false positives produced by the automated scheme, which constitutes a main difficulty in the clinical application of the CAD scheme for nodule detection.
SUMMARY OF THE INVENTION
Accordingly, the object of this invention is to provide CAD process, system and computer program product whereby the number of false positives that are incorrectly reported as nodules is reduced.
This and other objects are achieved according to the present invention by providing a new and improved method to determine whether a candidate abnormality in a medical digital image is an actual abnormality, a system which implements the method, and a computer readable medium which stores program steps to implement the method, wherein the method includes obtaining plural first templates and plural second templates respectively corresponding to predetermined abnormalities and predetermined non-abnormalities; comparing the candidate abnormality with the obtained first and second templates to derive cross-correlation values between the candidate abnormality and each of the obtained first and second templates; determining the largest cross-correlation value derived in the comparing step and whether the largest cross-correlation value is produced by comparing the candidate abnormality with the first templates or with the second templates; and determining the candidate abnormality to be an actual abnormality when the largest cross-correlation value is produced by comparing the candidate abnormality with the first templates and determining the candidate abnormality to be a non-abnormality when the largest cross-correlation value is produced by comparing the candidate abnormality with the second templates. An actual abnormality is similarly determined to be malignant or benign based on further cross-correlation values obtained by comparisons with additional templates corresponding to malignant and benign abnormalities.
The maximum cross-correlation values obtained with nodule templates and with non-nodule templates for each of the candidates nodules are employed for distinguishing non-nodules from nodules because a nodule is generally more similar to nodule templates than to non-nodule templates, and a non-nodule is more similar to non-nodule templates than to nodule templates. Therefore, the maximum cross-correlation value of a nodule with nodule templates is generally greater than that with non-nodule templates, and vice versa. Accordingly, according to the present invention, the greatest cross-correlation value obtained is determined and the candidate nodule is then determined to be an actual nodule when the greatest cross-correlation value is obtained based on a comparison with a nodule template and to be a false positive when the greatest correlation value is obtained based on a comparison with a non-nodule template.
A study implementing the CAD process of the invention was performed, whereby a large number of false positives (44.3%) in chest radiographs were removed with reduction of a very small number of true positives (2.3%) by use of the multiple-templates matching technique. In addition, a similar result on another CAD scheme for detection of nodules on CT images by use of the multiple-templates matching technique was obtained. Thus, the present invention is considered to have applicability to improve the performance of many different CAD schemes for detection of various lesions in medical images, including nodules in chest radiographs, masses and microcalcifications in mammograms, nodules, colon polyps, liver tumors, and aneurysms in CT images as well as breast lesions in ultrasound and magnetic resonance images. Furthermore, the multiple-templates matching technique has application to distinguish benign lesions from malignant lesions, in order to improve the performance of CAD schemes for classification between benign lesions and malignant lesions such as lung cancer, breast cancer, colon cancer and stomach cancer.
REFERENCES:
patent: 4802231 (1989-01-01), Davis
patent: 5233519 (1993-08-01), Ito
patent: 6026174 (2000-02-01), Palcic et al.
patent: 6320976 (2001-11-01), Murthy et al.
Doi Kunio
Katsuragawa Shigehiko
Li Qiang
Arch Development Corporation
Johns Andrew W.
Oblon & Spivak, McClelland, Maier & Neustadt P.C.
LandOfFree
Process, system and computer readable medium for pulmonary... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Process, system and computer readable medium for pulmonary..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Process, system and computer readable medium for pulmonary... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3220131