Surgery – Diagnostic testing – Detecting nuclear – electromagnetic – or ultrasonic radiation
Reexamination Certificate
1997-07-25
2001-11-13
Smith, Ruth S. (Department: 3737)
Surgery
Diagnostic testing
Detecting nuclear, electromagnetic, or ultrasonic radiation
C600S411000, C600S420000, C600S427000, C600S431000, C600S443000, C600S458000, C128S922000, C382S131000, C706S020000
Reexamination Certificate
active
06317617
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Field of the Invention
The invention relates generally to a method and system for the computerized automatic analysis of lesions in magnetic resonance images. Specifically the system includes the computerized analysis of lesions in the breast using both two-dimensional and three-dimensional analyses. Techniques of the present invention include novel developments and implementations of spatial, temporal, and hybrid features to assess the characteristics of the lesions and in some cases give an estimate of the likelihood of malignancy or of prognosis, and also allow for the enhanced visualization of the breast and its pathological states. The system of the present invention also includes an option to merge the extracted features with those from x-ray and/or ultrasound images in order to further characterize the lesion and/or make a diagnosis and/or a prognosis.
2. Discussion of Background
Breast cancer is a leading cause of death in women, causing an estimated 46,000 deaths per year. (See Reference (1)). Mammography is the most effective method for the early detection of breast cancer, and it has been shown that periodic screening of asymptomatic women does reduce mortality. (See References (2)-(4)). Many breast cancers are detected and referred for surgical biopsy on the basis of a radiographically detected mass lesion or cluster of microcalcifications. Although general rules for the differentiation between benign and malignant mammographically identified breast lesions exist (see references (5)-(6)), considerable misclassification of lesions occurs with the current methods. On average, less than 30% of masses referred for surgical breast biopsy are actually malignant. (See reference (7)).
Breast MR imaging as an adjunct to mammography and sonography reveals breast cancer with a higher sensitivity than do mammography and sonography only. (See reference (13)). However, using all three methods in the human interpretation process yielded a lower specificity. It also has been shown that temporal analysis from dynamic MR correlates with intensity of fibrosis in fibroadenomas (see reference (14)). Some computerized analyses of spatial features are being performed. Adams et al. achieved a separation between malignant and benign lesions using a statistical analysis, however, their database consisted of only 16 cases. (See Reference (15)).
Computerized image analysis techniques that can objectively and reliably classify lesions based upon reported MR characteristics of benign and malignant masses, especially if combined with their mammographic features, could significantly improve the specificity of breast imaging and the evaluation of breast masses. Computer-aided techniques have been applied to the color Doppler evaluation of breast masses with promising results. (See reference (16)). However, color Doppler imaging is a technique which focuses only upon the vascularity of lesions. Since not all sonographically visible cancers have demonstrable neovascularity, this technique is inherently somewhat limited. On the other hand, computer-aided diagnosis techniques applied to gray-scale sonographic images has not yet been reported. In addition, computerized analysis of MR images of the breast has mainly been limited to only temporal analysis using contrast media.
Comprehensive summaries of investigations in the field of mammography CAD have been published. (See references (17)-(18)). In the 1960s and 70s, several investigators attempted to analyze mammographic abnormalities with computers. These previous studies demonstrated the potential capability of using a computer in the detection of mammographic abnormalities. Gale et al. (see reference (19)) and Getty et al. (see reference (20)) are both developing computer-based classifiers, which take as input diagnostically-relevant features obtained from radiologists' readings of breast images. Getty et al. found that with the aid of the classifier, community radiologists performed as well as unaided expert mammographers in making benign-malignant decisions. Swett et al. (see reference (21)) are developing an expert system to provide visual and cognitive feedback to the radiologist using a critiquing approach combined with an expert system. At the University of Chicago, we have shown that the computerized analysis of mass lesions (see reference (22)) and clustered microcalcifications (see reference (23)) on digitized mammograms yields performances similar to an expert mammographer and significantly better than average radiologists in the task of distinguishing between malignant and benign lesions.
SUMMARY OF THE INVENTION
Accordingly, an object of this invention is to provide a method and system for the analysis of lesions in magnetic resonance (MR) images.
Another object of this invention is to provide an automated method and system for the characterization of lesions using computer-extracted features from MR images of the breast.
Another object of this invention is to provide an automated method and system for determination of spatial features to assess the characteristics of the lesions in MR images.
A further object of this invention is to provide an automated method and system for determination of temporal features to assess the characteristics of the lesions in MR images.
A still further object of this invention is to provide an automated method and system for determination of hybrid features to assess the characteristics of the lesions in MR images.
An additional object of this invention is to provide an automated method and system for merging computer-extracted information from mammographic, ultrasound, and/or MR images and making a diagnosis and/or prognosis.
A further object of the invention is to provide an automated method and system for determining an estimate of the likelihood of malignancy or of prognosis of a lesion on an MR image.
Yet another object of the invention is to provide a method and system for presenting an enhanced visualization of the breast from a medical image.
The above and other objects are achieved according to the present invention by providing a new and improved method for the analysis of lesions in magnetic resonance (MR) images, including generating MR image data from the MR images; and extracting features that characterize a lesion within the MR image data, including extracting at least one of temporal, spatial, and hybrid features of the lesion.
REFERENCES:
patent: 4907156 (1990-03-01), Doi et al.
patent: 5059415 (1991-10-01), Neuwelt
patent: 5133020 (1992-07-01), Giger et al.
patent: 5235510 (1993-08-01), Yamada et al.
patent: 5279301 (1994-01-01), Tsukaya et al.
patent: 5415163 (1995-05-01), Harms et al.
patent: 5452367 (1995-09-01), Bick et al.
patent: 5463548 (1995-10-01), Asada et al.
patent: 5537485 (1996-07-01), Nishikawa et al.
patent: 5638458 (1997-06-01), Giger et al.
patent: 5657362 (1997-08-01), Giger et al.
Bick Ulrich
Giger Maryellen L.
Gilhuijs Kenneth
ARCH Development Corporation
Oblon & Spivak, McClelland, Maier & Neustadt P.C.
Smith Ruth S.
LandOfFree
Method, computer program product, and system for the... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method, computer program product, and system for the..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method, computer program product, and system for the... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2603798