Image analysis – Applications – Biomedical applications
Reexamination Certificate
1999-03-17
2004-02-24
Patel, Jayanti K. (Department: 2625)
Image analysis
Applications
Biomedical applications
C382S260000, C600S410000, C600S427000
Reexamination Certificate
active
06697506
ABSTRACT:
BACKGROUND
1. Technical Field
The present invention relates generally to computer-assisted diagnosis (CAD) and, in particular, to a mark-free CAD method and system for assisting diagnosis of abnormalities in digital medical images using diagnosis based image enhancement.
2. Background Description
Computer-assisted diagnosis is an important technology in many different clinical applications. However, one of the more prevalent clinical applications for computer-assisted diagnosis is in the detection of breast cancer in women. According to the American Cancer Society, breast cancer is the most common cancer among women, other than skin cancer. It is the leading cause of death among women aged 40 to 55. There are approximately 179,000 new cases of breast cancer in the United States each year and about 43,500 deaths from the disease.
While there are presently no means for preventing breast cancer, early detection of the disease prolongs life expectancy and decreases the likelihood of the need for a total mastectomy. Accordingly, the American Cancer Society recommends that all women aged 40 and older should have a mammogram every year.
A typical mammogram is performed using x-rays and may contain a lot of background structures corresponding to breast tissue. Accordingly, a trained, focused eye of a radiologist is needed to detect small lesions among these structures. However, a typical radiologist may be required to examine hundreds of mammograms on a daily basis, leading to the possibility of a missed diagnosis due to human error.
To assist in the detection of abnormal lesions in x-ray mammograms, computer-assisted diagnosis (CAD) systems have been developed. The CAD systems digitize x-ray mammograms to produce a digital mammogram, and perform image processing on the digital mammogram. The output of such CAD systems is a highlighted or “marked” display, the marks directing the attention of the radiologist to suspicious regions in the mammogram.
Examples of prior art systems will now be given. U.S. Pat. No. 5,815,591, entitled “Method and Apparatus for Fast Detection of Spiculated Lesions in Digital Mammograms”, issued on Sep. 29, 1998, and incorporated by reference herein, describes a technique to identify a specific type of abnormality in x-ray mammograms, namely spiculated masses. Such masses are indicated by line structures emanating from a location in the breast in different directions. Identification is made by inferring the shape and type of the mass from the line structures and their intersections.
U.S. Pat. No. 5,491,627, entitled “Method and System for the Detection of Microcalcifications in Digital Mammograms”, issued on Feb. 13, 1996, and incorporated by reference herein, describes a technique for detecting a specific type of abnormality in mammograms, namely, microcalcifications.
U.S. Pat. No. 4,907,156, entitled “Method and System for Enhancement and Detection of Abnormal Anatomic Regions in a Digital Image”, issued on Mar. 6, 1990, and incorporated by reference herein, describes a technique for global enhancement and detection of lung nodules and mammographic lesions. Enhancement is done by subtracting two processed versions of the x-ray image from each other. In one processed version the signal-to-noise ratio is increased, and in the other processed version the signal-to-noise ratio is suppressed. The detection is performed on the subtracted image, which has fewer low frequency background structures.
U.S. Pat. No. 5,579,360, entitled “Mass Detection by Computer Using Digital Mammograms of the Same breast Taken from Different Viewing Directions”, issued on Nov. 26, 1996, and incorporated by reference herein, describes a method for detecting a specific type of abnormality, namely, masses, by comparing two views of the same breast. Each view is analyzed individually to detect suspicious regions. False positives are reduced via comparisons of the characteristics of the lesions in both views. The remaining lesions are either marked or generically enhanced.
U.S. Pat. No. 5,768,406, entitled “Mass Detection in Digital X-Ray images Using Multiple Threshold Levels to Discriminate Spots”, issued on Jun. 16, 1998, and incorporated by reference herein, describes a technique for detecting masses from single mammographs. Detected lesions are either marked or generically enhanced.
U.S. Pat. No. 5,838,815, entitled “Method and System to Enhance Robust Identification of Abnormal Regions in Radiographs”, issued on Nov. 17, 1998; describes a technique of applying multiple global detection schemes for the same abnormality on multiple probabilistic variations of a radiograph. Detection of abnormalities using the technique is claimed to be made more robust. No image enhancement is disclosed.
However, such CAD systems are not without deficiency. For example, lesions such as cancers are sometimes missed on the softcopy reading in part because the optical density and contrast of the cancerous area in the image is not optimal for human detection. It is very difficult to optimize the display of the entire image with a single set of display parameters, since image characteristics (e.g., contrast) vary over the different parts of the image. It is also difficult to optimize the display for different types of lesions by using a single set of display parameters.
Moreover, with respect to the systems which provide a “marked output”, some physicians would likely feel more comfortable with a diagnosis when they are in control of the entire diagnostic process (i.e., when marks are not provided). Further, the marks may be distracting for some physicians who do not rely on the marks in making a diagnosis. On the other hand, the marks may limit the physicians' review of other areas of the softcopy which may contain an “unmarked” but nonetheless abnormal region.
Further, such systems suffer from the problem of false positives, that is, the marking of normal regions. False positives result in time lost by the radiologist, increased healthcare costs, trauma to the patient, and lack of trust in computer-assisted diagnosis.
Thus, it would be desirable and highly advantageous to have a CAD method and system that uses different sets of display parameters for different lesions in different local areas of the image. Moreover, it would be desirable and highly advantageous to have a CAD method and system that does not introduce marks onto the soft-copy which may be distracting to the physician or may result in other adverse affects (such as limiting the physician's review of other areas of the image).
SUMMARY OF THE INVENTION
The present invention is directed to a mark-free computer-assisted diagnosis method and system for assisting diagnosis of abnormalities in digital medical images using diagnosis based image enhancement. The invention integrates a physician's knowledge into the computer-assisted diagnosis process seamlessly, performs diagnostic computation accordingly, and then uses different sets of display parameters for different lesions at different parts of the image.
In one aspect of the present invention, a computer-assisted method for assisting diagnosis of abnormalities in digital medical images comprises the steps of: receiving indicia identifying one or more regions of interest in a digital medical image; and displaying one or more enhanced views of the regions of interest, the enhanced views being based on diagnostic parameters for the regions of interest and diagnostic parameters corresponding to a particular abnormality.
In another aspect of the present invention, a computer-assisted diagnosis system for assisting diagnosis of abnormalities in digital medical images comprises: a memory unit; a plurality of enhancement filters stored in the memory unit, each of the plurality of filters being pre-optimized for a specific type of abnormality and adaptable for further optimization based on diagnostic parameters of a selected region in the digital medical image; a processor operatively coupled to the memory unit for performing calculations with respect to the diagnostic parameters of the
Murthy Sreerama K. V.
Novak Carol L.
Qian Jianzhong
F. Chau & Associates LLP
Paschburg Donald B.
Patel Jayanti K.
Siemens Corporate Research Inc.
Tabatabai Abolfazl
LandOfFree
Mark-free computer-assisted diagnosis method and system for... does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Mark-free computer-assisted diagnosis method and system for..., we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Mark-free computer-assisted diagnosis method and system for... will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3337423