US5732121A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Method for detecting abnormal patterns
Assignee: PARAMOUNT CAPITAL Inc
•
Filing: 1996-10-09
•
Granted: 1998-03-24
•
Expires: 2016-10-09
Abstract
Abstract Prospective abnormal patterns in a radiation image of an object are detected in accordance with an image signal representing the radiation image. A probability density function of the image signal, which corresponds to a region, that is inward from a contour of each of the prospective abnormal patterns having been detected, and a neighboring region, is formed. Probability density function information in accordance with the probability density function is obtained. A definite prospective abnormal pattern, which is among the prospective abnormal patterns having been detected and has a high level of probability that it will be the true abnormal pattern, is detected in accordance with the probability density function information.
Inventors
- 👤 Hideya Takeo
- 👤 Nobuyoshi Nakajima
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-31 23:24
CPC Classifications
G; G06; G06T; G06T7/00; G06T7/0002; G06T7/0012; G01; G01N; G01N23/00; G01N23/02; G01N23/04
Claims Analysis
Total Claims: 21
Claim 1
Independent Claim
114 words
A method for detecting an abnormal pattern in a radiation image, wherein prospective abnormal patterns in a radiation image of an object are detected in accordance with an image signal representing the radiation image, the method comprising the steps of: i) forming a probability density function of the image signal, which corresponds to a region, that is inward from a contour of each of the prospective abnormal patterns having been detected, and a neighboring region, ii) obtaining probability density function information in accordance with said probability density function, and iii) detecting a definite prospective abnormal pattern, which is among the prospective abnormal patterns having been detected, in accordance with said probability density function information.
Claim 2
Independent Claim
114 words
A method for detecting an abnormal pattern in a radiation image, wherein prospective abnormal patterns in a radiation image of an object are detected in accordance with an image signal representing the radiation image, the method comprising the steps of: i) forming a probability density function of the image signal, which corresponds to a region, that is inward from a contour of each of the prospective abnormal patterns having been detected, and a neighboring region, ii) obtaining probability density function information in accordance with said probability density function, and iii) detecting a definite prospective abnormal pattern, which is among the prospective abnormal patterns having been detected, in accordance with said probability density function information.
Claim 3
Dependent Claim
22 words
A method as defined in claim 1 wherein the detection of the prospective abnormal patterns is carried out with iris filter processing.
Claim 4
Dependent Claim
88 words
A method as defined in claim 1 wherein said probability density function information is a new rating function value, which is obtained by combining at least two index values selected from the group consisting of a first index value representing a variance of said probability density function, a second index value representing a contrast of said probability density function, and a third index value representing an angular moment of said probability density function, and said definite prospective abnormal pattern is detected in accordance with said rating function value.
Claim 5
Dependent Claim
22 words
A method as defined in claim 3 wherein the detection of the prospective abnormal patterns is carried out with iris filter processing.
Claim 6
Dependent Claim
92 words
A method as defined in claim 1 wherein said probability density function information is at least one index value selected from the group consisting of a first index value representing a variance of said probability density function, a second index value representing a contrast of said probability density function, and a third index value representing an angular moment of said probability density function, and said definite prospective abnormal pattern is detected in accordance with at least one index value selected from the group consisting of said first, second, and third index values.
Claim 7
Dependent Claim
22 words
A method as defined in claim 5 wherein the detection of the prospective abnormal patterns is carried out with iris filter processing.
Claim 8
Independent Claim
135 words
A method for detecting an abnormal pattern in a radiation image, wherein prospective abnormal patterns in a radiation image of an object are detected in accordance with an image signal representing the radiation image, the method comprising the steps of: i) forming a probability density function of the image signal, which corresponds to a region, that is inward from a contour of each of the prospective abnormal patterns having been detected, and a neighboring region, ii) obtaining probability density function information in accordance with said probability density function, iii) obtaining edge information of a contour of each of the prospective abnormal patterns having been detected, and iv) detecting a definite prospective abnormal pattern, which is among the prospective abnormal patterns having been detected, in accordance with said probability density function information and said edge information.
Claim 9
Independent Claim
135 words
A method for detecting an abnormal pattern in a radiation image, wherein prospective abnormal patterns in a radiation image of an object are detected in accordance with an image signal representing the radiation image, the method comprising the steps of: i) forming a probability density function of the image signal, which corresponds to a region, that is inward from a contour of each of the prospective abnormal patterns having been detected, and a neighboring region, ii) obtaining probability density function information in accordance with said probability density function, iii) obtaining edge information of a contour of each of the prospective abnormal patterns having been detected, and iv) detecting a definite prospective abnormal pattern, which is among the prospective abnormal patterns having been detected, in accordance with said probability density function information and said edge information.
Claim 10
Dependent Claim
22 words
A method as defined in claim 7 wherein the detection of the prospective abnormal patterns is carried out with iris filter processing.
Claim 11
Dependent Claim
230 words
A method as defined in claim 7 wherein said probability density function information is at least one index value selected from the group consisting of a first index value representing a variance of said probability density function, a second index value representing a contrast of said probability density function, and a third index value representing an angular moment of said probability density function, said edge information is at least one index value selected from the group consisting of a fourth index value representing a variance with respect to a simultaneous formation matrix having been obtained by the utilization of iris filter processing, a fifth index value representing a difference entropy with respect to said simultaneous formation matrix, a sixth index value representing a correlation with respect to said simultaneous formation matrix, a seventh index value representing an inverse difference moment with respect to said simultaneous formation matrix, and an eighth index value representing a sum entropy with respect to said simultaneous formation matrix, a new rating function value is obtained by combining at least one index value, which is selected from the group consisting of said first, second, and third index values, and at least one index value, which is selected from the group consisting of said fourth, fifth, sixth, seventh, and eighth index values, and said definite prospective abnormal pattern is detected in accordance with said rating function value.
Claim 12
Dependent Claim
22 words
A method as defined in claim 9 wherein the detection of the prospective abnormal patterns is carried out with iris filter processing.
Claim 13
Dependent Claim
217 words
A method as defined in claim 7 wherein said probability density function information is at least one index value selected from the group consisting of a first index value representing a variance of said probability density function, a second index value representing a contrast of said probability density function, and a third index value representing an angular moment of said probability density function, said edge information is at least one index value selected from the group consisting of a fourth index value representing a variance with respect to a simultaneous formation matrix having been obtained by the utilization of iris filter processing, a fifth index value representing a difference entropy with respect to said simultaneous formation matrix, a sixth index value representing a correlation with respect to said simultaneous formation matrix, a seventh index value representing an inverse difference moment with respect to said simultaneous formation matrix, and an eighth index value representing a sum entropy with respect to said simultaneous formation matrix, and said definite prospective abnormal pattern is detected in accordance with at least one index value, which is selected from the group consisting of said first, second, and third index values, and at least one index value, which is selected from the group consisting of said fourth, fifth, sixth, seventh, and eighth index values.
Claim 14
Dependent Claim
22 words
A method as defined in claim 11 wherein the detection of the prospective abnormal patterns is carried out with iris filter processing.
Claim 15
Independent Claim
81 words
A method for detecting an abnormal pattern in a radiation image, wherein prospective abnormal patterns in a radiation image of an object are detected in accordance with an image signal representing the radiation image, the method comprising the steps of: i) obtaining edge information of a contour of each of the prospective abnormal patterns having been detected, and ii) detecting a definite prospective abnormal pattern, which is among the prospective abnormal patterns having been detected, in accordance with said edge information.
Claim 16
Independent Claim
81 words
A method for detecting an abnormal pattern in a radiation image, wherein prospective abnormal patterns in a radiation image of an object are detected in accordance with an image signal representing the radiation image, the method comprising the steps of: i) obtaining edge information of a contour of each of the prospective abnormal patterns having been detected, and ii) detecting a definite prospective abnormal pattern, which is among the prospective abnormal patterns having been detected, in accordance with said edge information.
Claim 17
Dependent Claim
22 words
A method as defined in claim 13 wherein the detection of the prospective abnormal patterns is carried out with iris filter processing.
Claim 18
Dependent Claim
139 words
A method as defined in claim 13 wherein said edge information is at least one index value selected from the group consisting of a first index value representing a variance with respect to a simultaneous formation matrix having been obtained by the utilization of iris filter processing, a second index value representing a difference entropy with respect to said simultaneous formation matrix, a third index value representing a correlation with respect to said simultaneous formation matrix, a fourth index value representing an inverse difference moment with respect to said simultaneous formation matrix, and a fifth index value representing a sum entropy with respect to said simultaneous formation matrix, and said definite prospective abnormal pattern is detected in accordance with at least one index value selected from the group consisting of said first, second, third, fourth, and fifth index values.
Claim 19
Dependent Claim
22 words
A method as defined in claim 15 wherein the detection of the prospective abnormal patterns is carried out with iris filter processing.
Claim 20
Dependent Claim
133 words
A method as defined in claim 13 wherein said edge information is a new rating function value, which is obtained by combining at least two index values selected from the group consisting of a first index value representing a variance with respect to a simultaneous formation matrix having been obtained by the utilization of iris filter processing, a second index value representing a difference entropy with respect to said simultaneous formation matrix, a third index value representing a correlation with respect to said simultaneous formation matrix, a fourth index value representing an inverse difference moment with respect to said simultaneous formation matrix, and a fifth index value representing a sum entropy with respect to said simultaneous formation matrix, and said definite prospective abnormal pattern is detected in accordance with said rating function value.
Claim 21
Dependent Claim
22 words
A method as defined in claim 17 wherein the detection of the prospective abnormal patterns is carried out with iris filter processing.
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) | 2001-03-23 | 2001-09-22 | 2002-03-24 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2005-03-23 | 2005-09-22 | 2006-03-24 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2009-03-23 | 2009-09-22 | 2010-03-24 | $7700.00 | Window Closed / Lapsed |