Image analysis – Applications – Biomedical applications
Reexamination Certificate
1999-08-20
2003-08-12
Patel, Jayanti K. (Department: 2625)
Image analysis
Applications
Biomedical applications
C128S922000, C600S407000
Reexamination Certificate
active
06606400
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Field of the Invention
This invention relates to an abnormal pattern detection processing method and system. This invention particularly relates to an improvement in processing of an image, on which an abnormal pattern detection processing is to be performed.
2. Description of the Prior Art
In medical fields, various kinds of image forming modalities (i.e., image input apparatuses), such as computed tomography (CT) scanners, magnetic resonance imaging (MRI) apparatuses, and computed radiography (CR) apparatuses, have become popular as apparatuses for forming images to be used in making a diagnosis. Also, with the rapid advances made in network techniques in recent years, there has arisen a tendency toward utilization of networks for connecting image forming modalities, which are located in examination rooms of hospitals, or the like, and terminals or image output devices, such as image display devices (cathode ray tube (CRT) display devices, liquid crystal display devices, and the like), and printers (laser printers (LP), e.g. laser imagers, and the like), which are located in consultation rooms, laboratories, and the like. In such cases, visible images to be used in making a diagnosis can be reproduced in the consultation rooms from image signals, which have been acquired with the image forming modalities located in the examination rooms.
Further, it has been proposed to provide a quality assurance workstation (QAWS) on the medical image network constituted in the manner described above. The QAWS collectively manages image signals, which have been acquired with various kinds of image forming modalities, processed image signals, which have been obtained from image processing performed on the acquired image signals such that image quality may be enhanced, and the like.
Before the acquired image signals are transferred to various kinds of terminals or the image output devices located on the network, the QAWS checks fundamental image quality of the image signals and acts as a server for storing the image signals. Specifically, before the signals are transferred to the terminals or the image output devices, the QAWS simply checks the presence or absence of severe defect of images, which may occur due to a failure in image recording performed by the image forming modalities, a mistake made during readout of the recorded images, inappropriate processing in various kinds of intermediate processing, or the like.
Examples of image signals, which are acquired with the image forming modalities and fed into the QAWS, include image signals representing mamma images. The mamma images are recorded primarily for making a diagnosis of breast cancer. The applicant proposed abnormal pattern detection processing systems (computer aided medical image diagnosing systems) for automatically detecting an abnormal pattern, which suggests the presence of breast cancer, or the like, from a mamma image, or the like, by the utilization of a computer, and reproducing and displaying the abnormal pattern in various display forms. The abnormal pattern detection processing systems are described in, for example, Japanese Unexamined Patent Publication Nos. 8(1996)-294479 and 8(1996)-287230.
As abnormal pattern detecting means for performing processing for detecting an abnormal pattern, the abnormal pattern detection processing systems are provided with abnormal pattern detecting means utilizing an iris filter, wherein image density gradients (or luminance gradients) in an image are represented by image density gradient vectors, and an image area, which is associated with a high degree of centralization of the image density gradient vectors, is detected as an abnormal pattern. Alternatively, the abnormal pattern detection processing systems are provided with abnormal pattern detecting means utilizing a morphology filter, wherein a multi-structure element in accordance with the size of an abnormal pattern to be detected is utilized, and an image area, at which the image density changes in a range spatially narrower than the multi-structure element, is detected as an abnormal pattern. With the abnormal pattern detecting means utilizing the iris filter, a tumor pattern (a form of the abnormal pattern), which is a form of breast cancer, or the like, can be detected automatically. With the abnormal pattern detecting means utilizing the morphology filter, a small calcified pattern (a form of the abnormal pattern), which is a different form of breast cancer, or the like, can be detected automatically.
However, the abnormal pattern detection processing performed by the abnormal pattern detecting means requires a large amounts of operations with respect to each of pixels constituting an image, and a heavy load is required for the operations with respect to the entire area of the image. Therefore, in the medical image network described above, in order for the load to the QAWS to be prevented from becoming heavy, the abnormal pattern detecting means should preferably be provided as special-purpose detection means independent of the QAWS.
In cases where the abnormal pattern detecting means is constituted as a device independent of the QAWS, it is necessary for the operator to perform an operation for transferring only the mamma image signals, which are among a plurality of image signals fed from all image forming modalities into the QAWS, from the QAWS into the abnormal pattern detecting means.
As for the mammography, a single plan image and a single side image are recorded for each of the right and left mammae. Therefore, ordinarily, four mamma images are recorded per patient. When a medical doctor, or the like, finally makes a diagnosis, the four mamma images are seen and compared with one another, and the position of occurrence of an abnormal pattern, the form of occurrence of the abnormal pattern, and the like, are checked. Accordingly, in the abnormal pattern detecting means, four mamma image signals representing the four mamma images of each patient should preferably be processed together. Also, the four mamma image signals representing the four mamma images of each patient should preferably be fed as a single set into the image output device. For such purposes, it is necessary for the operator to perform an operation for grouping the four mamma image signals representing the four mamma images of each patient into a single set during the classifying operation described above.
However, a large number of image signals are fed from a plurality of image forming modalities, which are connected to the network, into the QAWS. Therefore, considerable time and labor are required for the operator to perform the manual operations for extracting only the mamma image signals from the large number of image signals, grouping the image signals corresponding to each patient into a single set, and transferring each set of the image signals into the abnormal pattern detecting means. Also, in cases where the number of the image signals to be processed by the QAWS becomes very large, it is expected that the operator cannot manually cope with the large number of the image signals. Further, it often occurs that the abnormal pattern detection processing should be performed urgently when the operator is absent.
SUMMARY OF THE INVENTION
The primary object of the present invention is to provide an abnormal pattern detection processing method, wherein image signals, which are among a plurality of given image signals and which are to be subjected to abnormal pattern detection processing, such as image signals representing mamma images or chest images, are capable of being automatically grouped into a single set for each patient, and an operator need not perform manual operations for the grouping of the image signals.
Another object of the present invention is to provide a system for carrying out the abnormal pattern detection processing method.
An abnormal pattern detection processing method and system in accordance with the present invention are characterized by selecting image signals, which are among a plurality o
Fuji Photo Film Co. , Ltd.
Patel Jayanti K.
Tabatabai Abolfazl
LandOfFree
Abnormal pattern detection processing method and system does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Abnormal pattern detection processing method and system, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Abnormal pattern detection processing method and system will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3126218