US5365429A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Computer detection of microcalcifications in mammograms
Assignee: Philips North America LLC
•
Filing: 1993-01-11
•
Granted: 1994-11-15
•
Expires: 2013-01-11
Abstract
Abstract A method of aiding detection of breast cancer by computer analysis of a mammogram image includes computing filtered second spatial derivative of intensity values at the pixels of the image, in the form of a Laplacian. The filtering is iterative adaptive smoothing of the first spatial derivative, which smoothing is applied to achieve relatively great smoothing effect where there is relatively little local variation in derivative value and a relatively small or no smoothing effect where there is relatively great local variation in derivative value. This has the effect of preserving locations of zero crossings in the Laplacian which correspond to edges or boundaries in the image. Regions of negative Laplacian value are labelled and connected. These labelled regions are locally bright spots in the image. From the preserved boundary locations of these locally bright spots, a plurality of feature measures are computed, indicative of their respective brightnesses, shapes and edge contrasts. Those locally bright spots having a weighted combination of logarithms of these feature measures exceeding a predetermined value are identified as microcalcifications of a type associated with cancer, and it is detected where such identified microcalcifications are grouped in clusters.
Inventors
- 👤 Charles S. Carman
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-04 07:54
CPC Classifications
G; G06; G06T; G06T7/00; G06T7/0002; G06T7/0012; G16; G16H; G16H15/00; G06T2207/00; G06T2207/30; G06T2207/30004; G06T2207/30068; G16H30/00; G16H30/20
Claims Analysis
Total Claims: 5
Claim 1
Independent Claim
185 words
A method for aiding detection of cancer, comprising: generating a radiologic image of a region of internal human anatomy by detecting radiation exiting from said region, said image comprising a two dimensional array of pixel positions having respective digitized intensity values; storing said image in a digital storage device; and automatically performing the following steps with a computer having access to the storage device: computing filtered second spatial derivative of intensity values for pixel positions of the radiologic image, in a manner which preserves the locations of edges of any spots in said image different in intensity from their surrounds as zero crossings in values of said second derivative; identifying one or more spots at pixel positions of the radiologic image as a function of the filtered second spatial derivative; computing a plurality of measures of features of the identified one or more spots, said plurality of measures being indicative of at least shape and edge gradient of said spots; and based on a determination from said measures of features computed, identifying which of said spots correspond to objects of a type associated with malignancy.
Claim 2
Independent Claim
185 words
A method for aiding detection of cancer, comprising: generating a radiologic image of a region of internal human anatomy by detecting radiation exiting from said region, said image comprising a two dimensional array of pixel positions having respective digitized intensity values; storing said image in a digital storage device; and automatically performing the following steps with a computer having access to the storage device: computing filtered second spatial derivative of intensity values for pixel positions of the radiologic image, in a manner which preserves the locations of edges of any spots in said image different in intensity from their surrounds as zero crossings in values of said second derivative; identifying one or more spots at pixel positions of the radiologic image as a function of the filtered second spatial derivative; computing a plurality of measures of features of the identified one or more spots, said plurality of measures being indicative of at least shape and edge gradient of said spots; and based on a determination from said measures of features computed, identifying which of said spots correspond to objects of a type associated with malignancy.
Claim 3
Dependent Claim
64 words
The cancer detection aiding method as claimed in claim 1, wherein said radiologic image is a mammogram and said objects are microcalcifications, said method further comprising: identifying one or more clusters of said spots identified as corresponding to microcalcifications of a type associated with malignancy; and providing a human intelligible indication of location in the radiologic image of said identified one or more clusters.
Claim 4
Dependent Claim
157 words
The cancer detection aiding method as claimed in claim 1, wherein said filtered second derivative is computed as follows: computing first spatial derivative of intensity values at pixel positions in said radiologic image; iteratively adaptive smoothing the first spatial derivative values in a manner that an adaptive smoothed first derivative value for a considered pixel position is arrived at by adaptive weighting first derivative values at adjoining pixel positions to achieve a relatively great smoothing effect when such adjoining pixel positions have first spatial derivative values which are relatively similar to the first spatial derivative value of the considered pixel position and to achieve relatively little or no smoothing effect when such adjoining pixel positions have first spatial derivative values which are relatively different from the first spatial derivative value at the considered pixel position; and computing spatial derivative values of the adaptive smoothed first spatial derivative values to form filtered second spatial derivative of intensity values.
Claim 5
Dependent Claim
157 words
The cancer detection aiding method as claimed in claim 2, wherein said filtered second derivative is computed as follows: computing first spatial derivative of intensity values at pixel positions in said radiologic image; iteratively adaptive smoothing the first spatial derivative values in a manner that an adaptive smoothed first derivative value for a considered pixel position is arrived at by adaptive weighting first derivative values at adjoining pixel positions to achieve a relatively great smoothing effect when such adjoining pixel positions have first spatial derivative values which are relatively similar to the first spatial derivative value of the considered pixel position and to achieve relatively little or no smoothing effect when such adjoining pixel positions have first spatial derivative values which are relatively different from the first spatial derivative value at the considered pixel position; and computing spatial derivative values of the adaptive smoothed first spatial derivative values to form filtered second spatial derivative of intensity values.
References Cited (Backward Citations)
US4515165A
Cited
US4618990A
Cited
US4907156A
Cited
US4851984A
Cited
FR2622714A1
Cited
US5003979A
Cited
WO1991007135A1
Cited
US5212637A
Cited
US5142557A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1997-11-14 | 1998-05-16 | 1998-11-15 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2001-11-14 | 2002-05-16 | 2002-11-15 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2005-11-14 | 2006-05-16 | 2006-11-15 | $7700.00 | Window Closed / Lapsed |