Image analysis – Applications – Biomedical applications
Reexamination Certificate
1999-08-13
2004-08-17
Patel, Jayanti K. (Department: 2625)
Image analysis
Applications
Biomedical applications
C382S171000, C382S177000, C600S443000, C600S450000
Reexamination Certificate
active
06778690
ABSTRACT:
FIELD OF THE INVENTION
This invention relates in general to medical imaging systems, and more specifically to a method of prostate boundary segmentation from 2D and 3D ultrasound images.
BACKGROUND OF THE INVENTION
Prostate cancer is the most commonly diagnosed malignancy in men over the age of 50, and is found at autopsy in 30% of men at the age of 50, 40% at age 60, and almost 90% at age 90. Worldwide, it is the second leading cause of death due to cancer in men, accounting for between 2.1% and 15.2% of all cancer deaths. In Canada, about 20,000 new prostate cancer cases will be diagnosed and about 4,000 men will die from this disease every year.
Symptoms due to carcinoma of the prostate are generally absent until extensive local growth or metastases develop, accounting for the fact that only 65% of patients are diagnosed with locally confined disease. Once the tumour has extended beyond the prostate, the risk of metastasis increases dramatically. Tumours smaller than 1 to 1.5 cm
3
rarely broach the prostatic capsule. When diagnosed at this early stage, the disease is curable, and even at later stages treatment can be effective. Nevertheless, treatment options vary depending on the extent of the cancer, and prognosis worsens when diagnosis occurs at an advanced stage.
The challenges facing physicians managing patients with possible prostate cancer are to: (a) diagnose clinically relevant cancers at a stage when they are curable, (b) stage and grade the disease accurately, (c) apply the appropriate therapy accurately to optimize destruction of cancer cells while preserving adjacent normal tissues, (d) follow patients to assess side effects and the effectiveness of the therapy.
U.S. Pat. Nos. 5,562,095, 5,454,371 and 5,842,473 focused on challenges (a) and (b). These patents describe a 3D ultrasound imaging technique for the diagnosis of prostate cancer. Extension of the e concepts for prostate cryosurgery are described in commonly assigned U.S. patent application Ser. No. 60/321,049, the contents of which are incorporated herein by reference.
An important aspect in the establishment of the appropriate prostate therapy is the accurate segmentation (i.e., extraction) of the prostate boundary and other anatomical structures (rectal wall, urethra, bladder). Assignment of the appropriate therapy or dose to the prostate requires that the prostate volume be accurately measured.
In situations where the image contrast is great (e.g., in fluid filled regions in ultrasound images), the segmentation task is relatively easy and many approaches can be used. However, ultrasound images of the prostate are very difficult to segment because the contrast is low, and the image suffers from speckle, shadowing and other artifacts. In performing ultrasound image segmentation, traditional local image processing operators like edge detectors are inadequate in and of themselves for finding the boundary, due to speckle, shadowing and other image artifacts.
The variability in prostate volume measurements using a conventional 2D technique is high, because current ultrasound volume measurement techniques assume an idealized elliptical shape and use only simple measures of the width in two views (see Tong S, Cardinal H N, McLoughlin R F, Downey D B, Fenster A, “Intra- and inter-observer variability and reliability of prostate volume measurement via 2D and 3D ultrasound imaging”, Ultrasound in Med & Biol 1998; 24:673-681, and Elliot T L, Downey D B, Tong S, Mclean C A, Fenster A, “Accuracy of prostate volume measurements in vitro using three-dimensional ultrasound”, Acad Radiol 1996; 3:401-406).
Manual contouring of sequential cross-sectional 2D CT or TRUS (transrectal ultrasound) prostate images has reduced this variability, but this approach is time-consuming and arduous, making it impractical during an intra-operative procedure.
Region-based neural net approaches require extensive teaching sets, are slow, and make addition of user specified boundary information difficult. Contour-based methods, such as “snakes” implementation of active contours are slow, complex, and sensitive to the initial choice of contour.
SUMMARY OF THE INVENTION
According to the present invention, a fast semi-automatic prostate contouring method is provided using model-based initialization and an efficient Discrete Dynamic Contour (DDC) for boundary refinement. The user initiates the process of the preferred embodiment by identifying four (4) points on the prostate boundary, thereby scaling and shaping a prostate model, and then the final prostate contour is refined with a DDC.
The method of the present invention can encompass a 2D segmentation technique or alternatively extend to the segmentation of objects in 3D
The method of the present invention has particular application during the pre-implant planning phase of a brachytherapy procedure. However, this method also has uses in any phase of dose planning in the brachytherapy procedure or any other therapy approach.
REFERENCES:
patent: 5454371 (1995-10-01), Fenster et al.
patent: 5457754 (1995-10-01), Han et al.
patent: 5559901 (1996-09-01), Loregt
patent: 5562095 (1996-10-01), Downey et al.
patent: 5842473 (1998-12-01), Fenster et al.
patent: 5871019 (1999-02-01), Belohlavek
patent: 6163757 (2000-12-01), Aizawa et al.
patent: 6251072 (2001-06-01), Ladak et al.
patent: 6272233 (2001-08-01), Takeo
patent: 6385332 (2002-05-01), Zahalka et al.
Lobregt, et al.,A Discrete Dynamic Contour Model, IEEE Transactions on Medical Imaging, vol.14, No. 1, pp. 12-24 (Mar. 1995).
Worring, et al.,Parameterized Feasible Boundaries in Gradient Vector Fields, Computer Vision and Image Understanding, vol. 63, No. 1, pp. 135-144 (Jan. 1995).
Elliot, et al.,Accuracy of Prostate Volume Measurements In Vitro Using Three-Dimensional Ultrasound, Academic Radiology, vol. 3, No. 5, pp. 401-406 (May 1996).
Tong, et al.,Intra-and Inter-observer Variability and Reliability of Prostate Volume Measurement Via Two-Dimensional and Three-Dimensional Ultrasound Imaging, Ultrasound in Medicine and Biology, vol. 24, No. 5, pp. 673-681, (1998).
Ku, Joy P., et al.,Construction of Geometric Models From Arbitrarily Oriented 2D Ultrasound Images, Bioengineering Conference, Jun. 16-20, 1999, Big Sky Montana.
Downey Donal B.
Fenster Aaron
Ladak Hanif M.
Steinman David A.
Fulwider Patton Lee & Utecht LLP
Patel Jayanti K.
Tabaitabai Abolfazl
LandOfFree
Prostate boundary segmentation from 2D and 3D ultrasound 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 Prostate boundary segmentation from 2D and 3D ultrasound images, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Prostate boundary segmentation from 2D and 3D ultrasound images will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-3350911