Patent US2509670A successfully refreshed from Google Patents.
US5576548A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Nuclear imaging enhancer
Assignee: University of South Florida St. Petersburg
•
Filing: 1995-06-05
•
Granted: 1996-11-19
•
Expires: 2015-06-05
Abstract
Abstract A wavelet based neural network (WNN) is proposed for image restoration using a nuclear gamma camera. The WNN first segments the image noise from the detected signal using a wavelet or multi-resolution method and then restores the detector resolution using the neural network. An example of methods is described for detecting beta particles (bremsstrahlung radiation) but the proposed WNN can be applied to either the detection of positrons or gamma rays using the gamma camera.
Inventors
- 👤 Laurence P. Clarke
- 👤 Wei Qian
- 👤 Maria Kallergi
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-05 03:35
CPC Classifications
G; G06; G06T; G06T5/00; G06T5/70; A; A61; A61B; A61B6/00; A61B6/42; A61B6/4208; A61B6/4258; A61B6/52; A61B6/5205; A61B6/5258; G06T5/60; G06T2207/00; G06T2207/20; G06T2207/20048; G06T2207/20064; G06T2207/20084
Claims Analysis
Total Claims: 10
Claim 1
Independent Claim
117 words
A method of detecting a nuclear image and filtering noise from the detected image, the method including the steps of: detecting a nuclear image and producing an image signal; storing the image signal; decomposing the image signal based on wavelet transform into a plurality of subimages of different resolution to concentrate image noise in at least one of the subimages and to concentrate the image signal in another of the subimages; selecting dominant subimages based on resolution representative of the nuclear image to eliminate the concentrated noise subimage; restoring the selected dominant subimages to a restored image of improved resolution by a neural network; and reconstructing the selected dominant subimages to a single high resolution image signal.
Claim 2
Independent Claim
117 words
A method of detecting a nuclear image and filtering noise from the detected image, the method including the steps of: detecting a nuclear image and producing an image signal; storing the image signal; decomposing the image signal based on wavelet transform into a plurality of subimages of different resolution to concentrate image noise in at least one of the subimages and to concentrate the image signal in another of the subimages; selecting dominant subimages based on resolution representative of the nuclear image to eliminate the concentrated noise subimage; restoring the selected dominant subimages to a restored image of improved resolution by a neural network; and reconstructing the selected dominant subimages to a single high resolution image signal.
Claim 3
Dependent Claim
16 words
A method as set forth in claim 1 wherein the decomposing is based on wavelet expansion.
Claim 4
Dependent Claim
40 words
A method as set forth in claim 2 wherein the selection of dominant subimages occurs by selecting low frequencies and resolutions of the subimages as the dominant images while eliminating high frequencies and resolutions containing a concentrated amount of noise.
Claim 5
Dependent Claim
137 words
A filter assembly for use with a nuclear detector to received nuclear image signals and to increase resolution thereof while decreasing the amount of noise, said assembly comprising: storing device for detecting and storing a nuclear image signal; decomposition means for decomposing the nuclear image based on wavelet transform into a plurality of subimages of different resolution to concentrate noise in at least one of the subimages and to concentrate the image signals in another of the subimages; selection means for selecting dominant subimages based on resolution representative of the nuclear image signal to eliminate the concentrate noise subimage; restoration means for restoring the selected dominant subimages to a restored image of improved resolution, said restoration means including a neural network; and reconstruction means for reconstructing the selected dominant subimages to a single high resolution image signal.
Claim 6
Dependent Claim
137 words
A filter assembly for use with a nuclear detector to received nuclear image signals and to increase resolution thereof while decreasing the amount of noise, said assembly comprising: storing device for detecting and storing a nuclear image signal; decomposition means for decomposing the nuclear image based on wavelet transform into a plurality of subimages of different resolution to concentrate noise in at least one of the subimages and to concentrate the image signals in another of the subimages; selection means for selecting dominant subimages based on resolution representative of the nuclear image signal to eliminate the concentrate noise subimage; restoration means for restoring the selected dominant subimages to a restored image of improved resolution, said restoration means including a neural network; and reconstruction means for reconstructing the selected dominant subimages to a single high resolution image signal.
Claim 7
Dependent Claim
20 words
An assembly as set forth in claim 4 further characterized by said decomposition means including decomposing based on wavelet expansion.
Claim 8
Dependent Claim
21 words
An assembly as set forth in claim 5 further characterized by said storing means including a nuclear detector and image matrix.
Claim 9
Dependent Claim
18 words
An assembly as set forth in claim 6 further characterized by said nuclear detector including a gamma camera.
Claim 10
Dependent Claim
35 words
An assembly as set forth in claim 6 further characterized by selecting low frequencies and resolutions of the subimages as the dominant images while eliminating high frequencies and resolutions containing a concentrated amount of noise.
References Cited (Backward Citations)
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1999-11-19 | 2000-05-20 | 2000-11-19 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2003-11-19 | 2004-05-20 | 2004-11-19 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2007-11-19 | 2008-05-20 | 2008-11-19 | $7700.00 | Window Closed / Lapsed |