Surgery – Diagnostic testing – Detecting nuclear – electromagnetic – or ultrasonic radiation
Reexamination Certificate
2001-04-16
2003-02-04
Manuel, George (Department: 3737)
Surgery
Diagnostic testing
Detecting nuclear, electromagnetic, or ultrasonic radiation
Reexamination Certificate
active
06514207
ABSTRACT:
BACKGROUND OF THE INVENTION
1. Field of the Invention
This invention relates to video indexing and summarization, and more particularly, to methods and systems for indexing and summarizing echocardiogram images.
2. Background of the Related Art
An echocardiogram is a common and useful ultrasound imaging technique used for viewing a patient's cardiac function. To administer an echocardiogram, a technician holds a transducer on the patient's chest above the body organs that the physician, e.g., the cardiologist, wants to visualize. The transducer generates high frequency sound waves, which are reflected back to the transducer by the different structures of the heart. This reflection of the waves or “echoes” is used to form an image by the machine.
The echocardiogram is useful to measure the size of the heart structures and the thickness of the heart muscle. It can be used to observe how the heart is working, e.g., to observe blood flow through the heart chambers (when combined with a Doppler technique), or how the heart wall is moving (when combined with stress test). The echocardiogram can identify tumors or emboli in the heart. In addition, it can detect structural abnormalities of the heart wall, the valves, and the blood vessels transporting blood to and from the heart. This technique is useful for diagnosing congenital heart disease (i.e., ventricular septal defect), cardiomyopathies, and aneurysms.
Echocardiogram videos (hereinafter “echo videos” ) are typically captured and stored on analog videotapes, and a particular echo study may have a duration of several minutes. Although an echocardiogram is capable of providing a significant amount of information to the physician, it consequently may be a challenge for the physician to examine this amount of information and provide a diagnosis for large number of patients. The cardiology department of a typical hospital has an archive of thousands of echocardiograms captured each year. To derive useful information from this analog archive, the physician or other specialist must watch each echo study using a video cassette player (VCR) with such limited functionalities as rewind and fast forward. In order to find a particular view corresponding to a certain probe location, the physician must search through the entire videotape record of a patient's study manually, by using the rewind and fast forwards controls. This process introduces a number of inefficiencies, including the excessive amount of time spent by the physician to review irrelevant video information, and the resources of the hospital or medical facility that must be used to archive a large number of videotapes.
Typical techniques for improving the process have largely been directed towards more efficient storage of the videotape record. For example, the analog videotape may be digitized and stored on a hard drive rather than on analog video tapes. In addition, various compression techniques such as MPEG-1, MPEG-2, or full motion JPEG for video have been used to store the video sequences. However, none of these techniques significantly relieves the user of the need to view the entire videotape record to perform a diagnosis.
SUMMARY OF THE INVENTION
The invention provides a method and a system for indexing and summarizing the echo videos, which provide the user with the necessary tools for efficient access and browsing. In accordance with the invention, the user is able to view a summary of the echo study of a patient in the form of a table of representative frames, instead of the full length of the video. The physician may make a diagnosis based on these representative frames, or alternatively, the representative frames provide a link for the user to view the full length video that may show any abnormality or a specific structure of interest.
A method for processing an echocardiogram video of a patient's heart is disclosed. The echocardiogram video comprises a first sequence of consecutive video frames corresponding to a first view of the patient's heart concatenated with a second sequence of consecutive video frames corresponding to a second view of the patient's heart. The method comprises receiving the first sequence of consecutive video frames and the second sequence of consecutive video frames. A first feature is observed in each video frame. A transition is detected between the first sequence of consecutive video frames and the second sequence of consecutive video frames by observing a discontinuity in the first feature between adjacent video frames. The method further comprises observing a second feature in the first sequence of consecutive video frames and the second sequence of consecutive video frames. A video frame in each of the first plurality of video frames and the second plurality of video frames is selected, corresponding to an occurrence of the second feature in each of the first sequence of consecutive video frames and the second sequence of consecutive video frames. The method further comprises generating a summary comprising video frames corresponding to the occurrences of the second feature.
Accordingly, it is an object of the invention to provide a method and system that makes more efficient use of the user's time in providing a diagnosis by presenting only relevant representative frames to the user.
It is another object of the invention to provide the capability of making a diagnosis from a remote location by reducing the amount of video that must be transferred from the location where the echocardiograms are acquired and the location of the specialist.
It is a further object of the invention to provide the capability to compare a patient's current study with the patient's previous studies on record, or to compare the patient's study with a “normal” echocardiogram by reviewing the summaries of echocardiogram videos rather than the entire video.
REFERENCES:
patent: 5385725 (1995-01-01), Lin et al.
patent: 5419328 (1995-05-01), Goh et al.
patent: 5570430 (1996-10-01), Sheehan et al.
patent: 5797396 (1998-08-01), Geiser et al.
patent: 5873830 (1999-02-01), Hossack et al.
patent: 5910111 (1999-06-01), Hunziker
Yihong Gong et al., “Automatic Parsing of TV Soccer Programs,” Proceedings of the International Conference on Multimedia Computing and Systems, 1995, pp. 167-174.
Wayne Wolf, “Key Frame Selection by Motion Analysis,” Proceedings of ICASSP '96, 1996, pp. 1228-1231.
John S. Boreczky et al., “Comparison of Video Shot Boundary Detection Techniques,” Storage and Retrieval for Image and Video Databases IV, Proceedings of IS&T/SPIE 1996 International Symposium on Electrical Imaging: Science and Technology, Feb. 1996, San Jose, CA.
Michael G. Christel et al., “Multimedia Abstractions for a Digital Video Library,” Proceedings of the 2nd ACM International Conference on Digital Libraries, Jul. 1997, pp. 21-29.
Anita Komlodi et al., “Key Frame Preview Techniques for Video Browsing,” Proceedings of ACM International Conference on Digital Libraries, 1998, pp. 118-125, Pittsburgh, PA.
Chang Shih-Fu
Ebadollahi Shahram
Wu Henry
Baker & Botts L.L.P.
Imam Ali M.
Manuel George
The Trustees of Columbia University in the City of New York
LandOfFree
Method and apparatus for processing echocardiogram video images 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 and apparatus for processing echocardiogram video images, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus for processing echocardiogram video images will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3180439