Patent US2685734A successfully refreshed from Google Patents.
US5657362A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Automated method and system for computerized detection of masses and parenchymal distortions in medical images
Assignee: Arch Development Corp
•
Filing: 1995-02-24
•
Granted: 1997-08-12
•
Expires: 2015-02-24
Abstract
Abstract A method and system for the automated detection of lesions such as masses and/or tissue (parenchymal) distortions in medical images such as mammograms. Dense regions and subcutaneous fat regions within a mammogram are segmented. A background correction may be performed within the dense regions. Hough spectrum within ROIs placed in the breast region of a mammogram are calculated and thresholded using the intensity value η in order to increase sensitivity and reduce the number of false-positive detections. Lesions are detected based on the thresholded Hough spectra. The thresholded Hough spectra are also used to differentiate between benign and malignant masses.
Inventors
- 👤 Maryellen L. Giger
- 👤 Ming Zhang
- 👤 Ping Lu
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-23 17:53
CPC Classifications
G; G06; G06T; G06T7/00; G06T7/0002; G06T7/0012; G06T7/10; G06T7/11; G06T2207/00; G06T2207/10; G06T2207/10116; G06T2207/20; G06T2207/20048; G06T2207/20061; G06T2207/20112; G06T2207/20132; G06T2207/30; G06T2207/30004; G06T2207/30068; G06T2207/30096
Claims Analysis
Total Claims: 51
Claim 1
Independent Claim
36 words
A method for enhancing visualization of a mammographic image, comprising: identifying in said image an anatomically dense portion of said image; and processing said dense portion to produce a processed image having a more uniform density.
Claim 2
Independent Claim
36 words
A method for enhancing visualization of a mammographic image, comprising: identifying in said image an anatomically dense portion of said image; and processing said dense portion to produce a processed image having a more uniform density.
Claim 3
Dependent Claim
43 words
A method as recited in claim 1, wherein identifying said dense portion comprises: identifying subcutaneous fat in said image, said image having a plurality of pixels; and excluding first pixels in said image corresponding to said subcutaneous fat to produce a fat-excluded image.
Claim 4
Dependent Claim
15 words
A method as recited in claim 2, comprising performing morphological filtering on said fat-excluded image.
Claim 5
Dependent Claim
119 words
A method as recited in claim 2, wherein excluding said first pixels comprises: identifying a breast border in said image; identifying a nipple position in said image; selecting a first row of pixels including said nipple position and having a first starting pixel; determining a gray-level threshold value in said image; excluding second pixels in said first row having a gray-level value less than said threshold and being within a selected distance of said first starting pixel; selecting a second row of pixels having a second starting pixel on said breast border; and excluding third pixels in said second row having a gray-level value less than said threshold and being within said selected distance of said second starting pixel.
Claim 6
Dependent Claim
65 words
A method as recited in claim 4, wherein determining said threshold comprises: placing a region on interest on said image proximate to a chest wall in said image; generating a first gray-level histogram of fourth pixels in said region of interest; generating a second gray-level histogram of said pixels in said image; and determining said gray-level threshold based on said first and second gray-level histograms.
Claim 7
Dependent Claim
84 words
A method as recited in claim 1, wherein identifying said dense portion of said image comprises: placing a region on interest on said image proximate to at least one of a chest wall and a breast border in said image, said image having a plurality of pixels; generating a first gray-level histogram of first pixels in said region of interest; generating a second gray-level histogram of said pixels in said image; and determining a gray-level threshold based on said first and second gray-level histograms.
Claim 8
Dependent Claim
28 words
A method as recited in claim 6, comprising: thresholding said image using said gray-level threshold to produce a thresholded image; and performing morphological filtering on said thresholded image.
Claim 9
Dependent Claim
35 words
A method as recited in claim 6, comprising: thresholding said image using said gray-level threshold to produce a thresholded image; and performing at least one of feature analysis and multi-gray-level thresholding on said thresholded image.
Claim 10
Dependent Claim
23 words
A method as recited in claim 6, comprising: thresholding said image using said gray-level threshold; and calculating a percent dense of said image.
Claim 11
Dependent Claim
54 words
A method as recited in claim 9, wherein calculating said percent dense comprises: determining a first number of pixels in said image above said gray-level threshold; determining a second number of pixels within a breast region of said image excluding pixels corresponding to subcutaneous fat; and dividing said first number by said second number.
Claim 12
Dependent Claim
13 words
A method as recited in claim 1, comprising: background-trend correcting said dense portion.
Claim 13
Dependent Claim
41 words
A method as recited in claim 11, wherein background-trend correcting comprises: curve fitting said dense portion to produce a fit to said dense portion; subtracting said fit from said dense portion to produce a subtracted image; and normalizing said subtracted image.
Claim 14
Dependent Claim
39 words
A method according to claim 1, comprising: processing said first image to produce a second image; extracting features from said second image; and detecting a lesion in said image based on the extracted features extracted in said extracting step.
Claim 15
Dependent Claim
18 words
A method as recited in claim 13, wherein processing said dense portion is performed during extracting said features.
Claim 16
Independent Claim
44 words
A method of detecting a lesion in a mammographic image, comprising: determining a fat value of said image; subtracting said fat value from said image to produce a subtracted image; extracting features from said subtracted image; and inputting said features to a detection scheme.
Claim 17
Independent Claim
44 words
A method of detecting a lesion in a mammographic image, comprising: determining a fat value of said image; subtracting said fat value from said image to produce a subtracted image; extracting features from said subtracted image; and inputting said features to a detection scheme.
Claim 18
Independent Claim
98 words
A method of detecting a lesion in a mammographic image, comprising: obtaining right and left mammograms; identifying in at least one of said right and left mammograms an anatomically dense portion; processing said dense portion identified in said identifying step so that the mammogram in which the dense portion is identified has a more uniform density; processing said right and left mammograms after said step of processing said dense portion to obtain a combined image; performing feature analysis on said combined image to extract features from said combined image; and detecting a lesion based on the extracted features.
Claim 19
Independent Claim
98 words
A method of detecting a lesion in a mammographic image, comprising: obtaining right and left mammograms; identifying in at least one of said right and left mammograms an anatomically dense portion; processing said dense portion identified in said identifying step so that the mammogram in which the dense portion is identified has a more uniform density; processing said right and left mammograms after said step of processing said dense portion to obtain a combined image; performing feature analysis on said combined image to extract features from said combined image; and detecting a lesion based on the extracted features.
Claim 20
Dependent Claim
21 words
A method as recited in claim 16, wherein said step of processing said dense portion comprises: background-trend correcting said dense portion.
Claim 21
Independent Claim
58 words
A method of analyzing a mammographic image, comprising: selecting a plurality of regions of interest in said image; calculating a Hough spectrum for each of said regions of interest; determining a threshold using said Hough spectra; thresholding said Hough spectra using said threshold; identifying a region suspected of being a lesion in said image; and analyzing said region.
Claim 22
Independent Claim
58 words
A method of analyzing a mammographic image, comprising: selecting a plurality of regions of interest in said image; calculating a Hough spectrum for each of said regions of interest; determining a threshold using said Hough spectra; thresholding said Hough spectra using said threshold; identifying a region suspected of being a lesion in said image; and analyzing said region.
Claim 23
Dependent Claim
95 words
A method as recited in claim 18, wherein determining said threshold comprises: determining a mean and a first standard deviation of each of said Hough spectra; determining an average mean and a second standard deviation over all of said regions of interest; selecting a starting threshold; determining if each of said Hough spectra are below said starting threshold; varying said starting threshold to a next threshold and determining if each of said Hough spectra are below said next threshold; and determining said threshold where a predetermined percentage of said Hough spectra are below said threshold.
Claim 24
Dependent Claim
38 words
A method as recited in claim 19, wherein selecting said starting threshold comprises: selecting a starting value of η; determining said starting threshold as τ=μ+ησ where μ is said average mean and σ is said second standard deviation.
Claim 25
Dependent Claim
48 words
A method as recited in claim 20, comprising: incrementing η to vary said starting threshold; determining if η is in an effective range; and determining said threshold where said predetermined percentage of said Hough spectra are below said threshold when η is no longer in said effective range.
Claim 26
Dependent Claim
26 words
A method as recited in claim 19, comprising: detecting said lesion in an ROI having at least part of one of Hough spectra above said threshold.
Claim 27
Dependent Claim
49 words
A method as recited in claim 22, comprising: determining a second threshold at which a second predetermined number of said Hough spectra are below said second threshold; and detecting a parenchymal distortion in an ROI having at least part of one of said Hough spectra above said second threshold.
Claim 28
Dependent Claim
29 words
A method as recited in claim 22, comprising: determining whether said lesion is malignant based on said accumulations; and determining whether said lesion is benign based on said accumulations.
Claim 29
Dependent Claim
28 words
A method as recited in claim 19, comprising: determining an accumulation for each of said Hough spectra thresholded at said threshold; detecting said lesion based on said accumulation.
Claim 30
Dependent Claim
16 words
A method as recited in claim 25, comprising: detecting a parenchymal distortion based on said accumulation.
Claim 31
Dependent Claim
58 words
A method as recited in claim 18, wherein said analyzing comprises: measuring an accumulation for said region; extracting at least one feature of said region using a feature analysis technique; inputting said accumulation and said at least one feature into a lesion detection scheme; and determining a likelihood of malignancy of said region using said lesion detection scheme.
Claim 32
Dependent Claim
31 words
A method as recited in claim 27, wherein inputting said accumulation comprises inputting said accumulation into an artificial neural network trained to determine malignancy of a suspect region in a mammogram.
Claim 33
Dependent Claim
22 words
A method as recited in claim 18, comprising: performing preprocessing on said image prior to selecting said plurality of regions of interest.
Claim 34
Dependent Claim
26 words
A method as recited in claim 29, wherein said performing preprocessing comprises performing at least one dense portion processing, histogram equalization, peripheral enhancing and edge enhancing.
Claim 35
Independent Claim
92 words
A method of analyzing an image, comprising: locating a region suspected of containing a lesion; selecting a plurality of regions of interest including said region; calculating a Hough spectrum for each of said regions of interest; determining a threshold using said Hough spectra; thresholding said Hough spectra using said threshold to produce a thresholded Hough spectra; determining an accumulation for each of said thresholded Hough spectra; extracting at least one feature of said region using a feature analysis technique; and analyzing said region using said accumulation and said at least one feature.
Claim 36
Independent Claim
92 words
A method of analyzing an image, comprising: locating a region suspected of containing a lesion; selecting a plurality of regions of interest including said region; calculating a Hough spectrum for each of said regions of interest; determining a threshold using said Hough spectra; thresholding said Hough spectra using said threshold to produce a thresholded Hough spectra; determining an accumulation for each of said thresholded Hough spectra; extracting at least one feature of said region using a feature analysis technique; and analyzing said region using said accumulation and said at least one feature.
Claim 37
Dependent Claim
35 words
A method as recited in claim 31, wherein analyzing said region comprises: inputting said accumulation and said at least one feature to a detection scheme; and determining a likelihood of malignancy using said detection scheme.
Claim 38
Dependent Claim
27 words
A method as recited in claim 31, comprising: obtaining a mammographic image; detecting at least one of a mass and a parenchymal distortion in said mammographic image.
Claim 39
Dependent Claim
61 words
A method as recited in claim 31, comprising: selecting a single region of interest containing said region; calculating a single Hough spectrum for said single region of interest; determining a threshold using said single Hough spectrum; thresholding said single Hough spectrum using said threshold to produce a single thresholded Hough spectrum; and determining an accumulation for said single thresholded Hough spectrum.
Claim 40
Dependent Claim
35 words
A method as recited in claim 34, wherein analyzing said region comprises: inputting said accumulation and said at least one feature to a detection scheme; and determining a likelihood of malignancy using said detection scheme.
Claim 41
Dependent Claim
25 words
A method as recited in claim 31, comprising: detecting whether said region contains a malignant mass; and detecting whether said region contains a benign mass.
Claim 42
Dependent Claim
17 words
A method as recited in claim 36, comprising differentiating between said malignant mass and said benign mass.
Claim 43
Independent Claim
54 words
A system for visualization in an image, comprising: an image acquisition device configured to acquire said image; and a dense portion processing circuit connected to said image acquisition device and configured to identify an anatomically dense portion of said image and process said dense portion to produce a processed image having more uniform density.
Claim 44
Independent Claim
54 words
A system for visualization in an image, comprising: an image acquisition device configured to acquire said image; and a dense portion processing circuit connected to said image acquisition device and configured to identify an anatomically dense portion of said image and process said dense portion to produce a processed image having more uniform density.
Claim 45
Dependent Claim
17 words
A system as recited in claim 38, wherein said image acquisition device is a mammogram acquisition device.
Claim 46
Dependent Claim
49 words
The system of claim 38, comprising: an image processing circuit connected to said dense portion processing circuit and configured to process said processed image having more uniform density; a feature extraction circuit connected to said image processing circuit; and a lesion detection circuit connected to said feature analysis circuit.
Claim 47
Dependent Claim
30 words
A system as recited in claim 40, comprising: a lesion location superimposing circuit connected to said lesion detection circuit; and an image display connected to said lesion location superimposing circuit.
Claim 48
Independent Claim
82 words
A system for detecting lesions in an image; an image acquisition device; a lesion location circuit connected to said image acquisition device; a dense portion processing circuit connected to said lesion location circuit; a Hough spectrum analysis circuit connected to said lesion location circuit and said dense portion processing circuit; a lesion extraction circuit connected to said Hough spectrum analysis circuit; a feature extraction circuit connected to said lesion extraction circuit; and a lesion detection circuit connected to said feature analysis circuit.
Claim 49
Independent Claim
82 words
A system for detecting lesions in an image; an image acquisition device; a lesion location circuit connected to said image acquisition device; a dense portion processing circuit connected to said lesion location circuit; a Hough spectrum analysis circuit connected to said lesion location circuit and said dense portion processing circuit; a lesion extraction circuit connected to said Hough spectrum analysis circuit; a feature extraction circuit connected to said lesion extraction circuit; and a lesion detection circuit connected to said feature analysis circuit.
Claim 50
Dependent Claim
30 words
A system as recited in claim 42, comprising: a lesion location superimposing circuit connected to said lesion detection circuit; and an image display connected to said lesion location superimposing circuit.
Claim 51
Dependent Claim
17 words
A system as recited in claim 42, wherein said image acquisition device is a mammogram acquisition device.
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) | 2000-08-11 | 2001-02-10 | 2001-08-12 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2004-08-11 | 2005-02-10 | 2005-08-12 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2008-08-11 | 2009-02-10 | 2009-08-12 | $7700.00 | Window Closed / Lapsed |