US5425368A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Method and apparatus for estimating tissue volumes in magnetic resonance images
Assignee: The University of Texas System
•
Filing: 1993-03-17
•
Granted: 1995-06-20
•
Expires: 2013-03-17
Abstract
Abstract A fuzzy logic approach to the problem of distinguishing cerebrospinal fluid, gray and white matter pixels in magnetic resonance images of the brain. An unsupervised fuzzy clustering procedure based on a variant of the fuzzy c-means algorithm computes automatically, with virtually no operator intervention, the percentage area of each of these three compartments in each image. Each volume element represented in the image can belong to all compartments in varying degrees. The procedure requires input of the number of different compartments in the image, as well as a parameter which determines the amount of overlap of compartment boundaries. Preliminary data processing involves noise removal from images by highpass filtering. The final solution is substantially independent of required initial estimates of the gray scale values that are most representative of the white, gray and cerebrospinal fluid compartments in the image. The method is useful in the diagnosis of hydrocephalus.
Inventors
- 👤 Michael E. Brandt
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 22:18
CPC Classifications
G; G01; G01R; G01R33/00; G01R33/20; G01R33/44; G01R33/48; G01R33/54; G01R33/56; G06; G06F; G06F18/00; G06F18/20; G06F18/23; G06F18/232; G06F18/2321; G06F18/23213; G06T; G06T7/00; G06T7/10; G06T7/11; G06T7/60; G06T7/66; G06V; G06V10/00; G06V10/20; G06V10/28; G01R33/5608; G06T2207/00; G06T2207/10; G06T2207/10072; G06T2207/10088; G06T2207/30; G06T2207/30004; G06T2207/30016; G06V2201/00; G06V2201/03; G06V2201/031; G16; G16H; G16H15/00; G16H30/00; G16H30/20; Y; Y10; Y10S; Y10S128/00; Y10S128/92; Y10S128/925
Claims Analysis
Total Claims: 43
Claim 1
Independent Claim
51 words
A method of analyzing magnetic resonance images of a patient's brain to determine brain compartments, comprising: providing pixelized magnetic resonance image data representative of a patient's brain; and distinguishing at least two brain compartment types for said patient's brain utilizing a fuzzy clustering process and said pixelized magnetic resonance image data.
Claim 2
Independent Claim
51 words
A method of analyzing magnetic resonance images of a patient's brain to determine brain compartments, comprising: providing pixelized magnetic resonance image data representative of a patient's brain; and distinguishing at least two brain compartment types for said patient's brain utilizing a fuzzy clustering process and said pixelized magnetic resonance image data.
Claim 3
Dependent Claim
23 words
The method of claim 1, further comprising: displaying a pixelized magnetic resonance solution image of said at least two distinguished brain compartment types.
Claim 4
Dependent Claim
22 words
The method of claim 1, further comprising: determining brain compartment volumes for each of said at least two distinguished brain compartment types.
Claim 5
Dependent Claim
24 words
The method of claim 3, further comprising: determining a percentage brain compartment volume for each of said at least two determined brain compartment volumes.
Claim 6
Dependent Claim
22 words
The method of claim 3, wherein said determining step comprises determining brain compartment volumes for cerebrospinal fluid, gray matter and white matter.
Claim 7
Dependent Claim
29 words
The method of claim 5, wherein said providing step comprises providing pixelized magnetic resonance image data obtained from a PD-weighted magnetic resonance image and a T2-weighted magnetic resonance image.
Claim 8
Dependent Claim
34 words
The method of claim 5, wherein said providing step comprises providing pixelized magnetic resonance image data obtained from a PD-weighted magnetic resonance image, a T2-weighted magnetic resonance image, and a T1-weighted magnetic resonance image.
Claim 9
Dependent Claim
20 words
The method of claim 5, wherein said fuzzy clustering process has a fuzzification factor (m) of about 1.2 to 1.4.
Claim 10
Dependent Claim
19 words
The method of claim 8, wherein said fuzzification factor (m) is an integer ratio of 4 over 3 (4/3).
Claim 11
Dependent Claim
17 words
The method of claim 5, wherein said fuzzy clustering process has a centroid difference error convergence approach.
Claim 12
Dependent Claim
148 words
The method of claim 10, wherein said fuzzy clustering process has a centroid difference error convergence approach, comprising: selecting a current centroid of a cluster representing each of said at least two distinguished brain compartment types; determining a distance from a plurality of pixel vectors to each current centroid; determining a membership vector for each of said plurality of pixel vectors in each cluster; determining a new centroid for each cluster; determining a difference between each of said new centroid for each cluster and said current centroid for each cluster; substituting said new centroid value for said current centroid value for each cluster if said difference is greater than a desired error convergence threshold; and returning to said step of determining a distance after substituting said new centroid value for said current centroid value for each cluster if said difference is greater than a desired error convergence threshold.
Claim 13
Dependent Claim
19 words
The method of claim 11, wherein said desired error convergence threshold is greater than 0.0 but less than 0.5.
Claim 14
Independent Claim
112 words
A method of analyzing magnetic resonance images of a patient's brain to determine the presence or absence of a predetermined brain compartment level, comprising: providing pixelized magnetic resonance image data representative of a patient's brain; determining a brain compartment level for at least one brain compartment type of said patient's brain utilizing a fuzzy clustering process and said pixelized magnetic resonance image data; and comparing said brain compartment level for at least one of said at least one brain compartment type with a predetermined brain compartment level for said at least one of said at least one brain compartment type to determine the presence or absence of said predetermined brain compartment level.
Claim 15
Independent Claim
112 words
A method of analyzing magnetic resonance images of a patient's brain to determine the presence or absence of a predetermined brain compartment level, comprising: providing pixelized magnetic resonance image data representative of a patient's brain; determining a brain compartment level for at least one brain compartment type of said patient's brain utilizing a fuzzy clustering process and said pixelized magnetic resonance image data; and comparing said brain compartment level for at least one of said at least one brain compartment type with a predetermined brain compartment level for said at least one of said at least one brain compartment type to determine the presence or absence of said predetermined brain compartment level.
Claim 16
Dependent Claim
23 words
The method of claim 13, wherein said determining step comprises determining a brain compartment level of cerebrospinal fluid, gray matter and white matter.
Claim 17
Dependent Claim
20 words
The method of claim 14, wherein said fuzzy clustering process has a fuzzification factor (m) of about 1.2 to 1.4.
Claim 18
Dependent Claim
19 words
The method of claim 15, wherein said fuzzification factor (m) is an integer ratio of 4 over 3 (4/3).
Claim 19
Dependent Claim
17 words
The method of claim 14, wherein said fuzzy clustering process has a centroid difference error convergence approach.
Claim 20
Dependent Claim
148 words
The method of claim 17, wherein said fuzzy clustering process has a centroid difference error convergence approach, comprising: selecting a current centroid of a cluster representing each of said at least two distinguished brain compartment type; determining a distance from a plurality of pixel vectors to each current centroid; determining a membership vector for each of said plurality of pixel vectors in each cluster; determining a new centroid for each cluster; determining a difference between each of said new centroid for each cluster and said current centroid for each cluster; substituting said new centroid value for said current centroid value for each cluster if said difference is greater than a desired error convergence threshold; and returning to said step of determining a distance after substituting said new centroid value for said current centroid value for each cluster if said difference is greater than a desired error convergence threshold.
Claim 21
Dependent Claim
19 words
The method of claim 17, wherein said desired error convergence threshold is greater than 0.0 but less than 0.5.
Claim 22
Dependent Claim
36 words
The method of claim 13, further comprising: indicating a brain condition based upon said presence or absence of said predetermined brain compartment level for said at least one of said at least one brain compartment type.
Claim 23
Dependent Claim
51 words
The method of claim 20, wherein said determining step comprises determining a percentage brain compartment volume for cerebrospinal fluid, gray matter and white matter; and said comparing step comprising, comparing said determined percentage brain compartment volume for said cerebrospinal fluid with a predetermined percentage brain compartment volume for said cerebrospinal fluid.
Claim 24
Dependent Claim
18 words
The method of claim 13, wherein said determining step comprises determining a brain compartment level for cerebrospinal fluid.
Claim 25
Dependent Claim
12 words
The method of claim 21, wherein said indicating step comprises indicating hydrocephalus.
Claim 26
Dependent Claim
20 words
The method of claim 23, wherein said predetermined percentage brain compartment volume for said cerebrospinal fluid is about ten percent.
Claim 27
Independent Claim
87 words
An apparatus for a analyzing magnetic resonance images of a patient's brain to determine brain compartments, comprising: an input means for receiving pixelized magnetic resonance image data representative of a patient's brain; a memory means coupled to said input means for storing said pixelized magnetic resonance image data; and a microprocessor means coupled to said memory means and coupled to said input means for distinguishing at least two brain compartment types for said patient's brain utilizing a fuzzy clustering process and said pixelized magnetic resonance image data.
Claim 28
Independent Claim
87 words
An apparatus for a analyzing magnetic resonance images of a patient's brain to determine brain compartments, comprising: an input means for receiving pixelized magnetic resonance image data representative of a patient's brain; a memory means coupled to said input means for storing said pixelized magnetic resonance image data; and a microprocessor means coupled to said memory means and coupled to said input means for distinguishing at least two brain compartment types for said patient's brain utilizing a fuzzy clustering process and said pixelized magnetic resonance image data.
Claim 29
Dependent Claim
23 words
The apparatus of claim 25, further comprising: an output means coupled to said microprocessor means for displaying a pixelized magnetic resonance solution image.
Claim 30
Dependent Claim
27 words
The apparatus of claim 25, wherein said microprocessor means is also for determining brain compartment volumes for each of said at least two distinguished brain compartment types.
Claim 31
Dependent Claim
21 words
The apparatus of claim 27, wherein said at least two brain compartment types are cerebrospinal fluid gray matter and white matter.
Claim 32
Dependent Claim
20 words
The apparatus of claim 28, wherein said fuzzy clustering process has a fuzzification factor (m) of about 1.2 to 1.4.
Claim 33
Dependent Claim
17 words
The apparatus of claim 28, wherein said fuzzy clustering process has a centroid difference error convergence approach.
Claim 34
Dependent Claim
22 words
The apparatus of claim 30, wherein said fuzzy clustering process has an error convergence threshold greater than 0.0 but less than 0.5.
Claim 35
Independent Claim
148 words
An apparatus for analyzing magnetic resonance images of a patient's brain to determine the presence or absence of a predetermined brain compartment level, comprising: an input means for receiving pixelized magnetic resonance image data representative of a patient's brain; a memory means coupled to said input means for storing said pixelized magnetic resonance image data; and a microprocessor means coupled to said memory means and coupled to said input means for determining a brain compartment level for at least one brain compartment type in said patient's brain utilizing a fuzzy clustering process and said pixelized magnetic resonance image data, and for comparing said brain compartment level for at least one of said at least one brain compartment type with a predetermined brain compartment level for at least one of said at least gone brain compartment type to determine the presence or absence of said predetermined brain compartment level.
Claim 36
Independent Claim
148 words
An apparatus for analyzing magnetic resonance images of a patient's brain to determine the presence or absence of a predetermined brain compartment level, comprising: an input means for receiving pixelized magnetic resonance image data representative of a patient's brain; a memory means coupled to said input means for storing said pixelized magnetic resonance image data; and a microprocessor means coupled to said memory means and coupled to said input means for determining a brain compartment level for at least one brain compartment type in said patient's brain utilizing a fuzzy clustering process and said pixelized magnetic resonance image data, and for comparing said brain compartment level for at least one of said at least one brain compartment type with a predetermined brain compartment level for at least one of said at least gone brain compartment type to determine the presence or absence of said predetermined brain compartment level.
Claim 37
Dependent Claim
42 words
The apparatus of claim 32, further comprising: an output means coupled to said microprocessor means for displaying an indication of said presence or absence of said predetermined brain compartment level for at least one of said at least one brain compartment type.
Claim 38
Dependent Claim
21 words
The apparatus of claim 32, wherein said at least two brain compartment types are cerebrospinal fluid, gray matter and white matter.
Claim 39
Dependent Claim
20 words
The apparatus of claim 34, wherein said fuzzy clustering process has a fuzzification factor (m) of about 1.2 to 1.4.
Claim 40
Dependent Claim
17 words
The apparatus of claim 34, wherein said fuzzy clustering process has a centroid difference error convergence approach.
Claim 41
Dependent Claim
21 words
The apparatus of claim 36, wherein said fuzzy clustering process has a convergence threshold greater than 0.0 but less than 0.5.
Claim 42
Dependent Claim
40 words
The apparatus of claim 34, wherein said microprocessor means is also for indicating a brain condition based upon said presence or absence of said predetermined brain compartment level for at least one of said at least one brain compartment type.
Claim 43
Dependent Claim
39 words
The apparatus of claim 38, wherein said brain compartment level is a percentage brain compartment volume; wherein said predetermined brain compartment level is a predetermined percentage brain compartment volume of cerebrospinal fluid; and wherein said brain condition is hydrocephalus.
References Cited (Backward Citations)
US4729098A
Cited
US4712560A
Cited
US4856528A
Cited
US4961425A
Cited
US5113357A
Cited
US5187658A
Cited
US5273040A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1998-06-19 | 1998-12-19 | 1999-06-20 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2002-06-19 | 2002-12-19 | 2003-06-20 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2006-06-19 | 2006-12-19 | 2007-06-20 | $7700.00 | Window Closed / Lapsed |