US6317617B1 — Method, computer program product, and system for …

Claim 1

Independent Claim 150 words

A method for the analysis of a lesion in an anatomy, comprising: obtaining plural image data, representative of plural images of a same portion of the anatomy, derived from at least two imaging modalities selected from the group consisting of magnetic resonance imaging, x-ray imaging, and ultrasound imaging; identifying from the plural image data a possible lesion in said plural images; extracting, for each of said plural images derived from said at least two imaging modalities, at least one feature related to characterization of a lesion from image data corresponding to the identified possible lesion; and merging in a common image classifier a plurality of extracted features, including at least one feature related to characterization of a lesion from each of said plural images derived from said at least two imaging modalities to characterize said possible lesion based on the merged plurality of extracted features and yield a corresponding classification.

Claim 2

Independent Claim 150 words

A method for the analysis of a lesion in an anatomy, comprising: obtaining plural image data, representative of plural images of a same portion of the anatomy, derived from at least two imaging modalities selected from the group consisting of magnetic resonance imaging, x-ray imaging, and ultrasound imaging; identifying from the plural image data a possible lesion in said plural images; extracting, for each of said plural images derived from said at least two imaging modalities, at least one feature related to characterization of a lesion from image data corresponding to the identified possible lesion; and merging in a common image classifier a plurality of extracted features, including at least one feature related to characterization of a lesion from each of said plural images derived from said at least two imaging modalities to characterize said possible lesion based on the merged plurality of extracted features and yield a corresponding classification.

Claim 3

Dependent Claim 26 words

The method according to claim 1 , further comprising: extracting features from at least one of the interior or the surface of the identified possible lesion.

Claim 4

Dependent Claim 18 words

The method according to claim 1 , further comprising: extracting geometric based features of the identified possible lesion.

Claim 5

Dependent Claim 25 words

The method according to claim 3 , further comprising: extracting at least one of circularity and irregularity geometric based features of the identified possible lesion.

Claim 6

Dependent Claim 75 words

The method according to claim 4 , further comprising: extracting the circularity geometric based features of the identified possible lesion based on the following equation: C = E   F   V V where C is a measure of circularity of the identified possible lesion, EFV is an effective volume of the identified possible lesion, and V is a sphere having a same volume as the effective volume of the identified possible lesion.

Claim 7

Dependent Claim 70 words

The method according to claim 4 , further comprising: extracting the irregularity geometric based features of the identified possible lesion based on the following equation: I = 1 - π · ( E   D ) 2 S where I is a measure of irregularity of the lesion, ED is an effective diameter of the identified possible lesion, and S is a surface area of the identified possible lesion.

Claim 8

Dependent Claim 19 words

The method according to claim 1 , further comprising: extracting gray level based features of the identified possible lesion.

Claim 9

Dependent Claim 30 words

The method according to claim 1 , further comprising: extracting from each of said images derived from said at least two modalities gradient based features of the identified possible lesion.

Claim 10

Dependent Claim 119 words

The method according to claim 1 , further comprising: extracting from each of said images derived from said at least two modalities gradient based features of the identified possible lesion based on at least one of the following equations: G   F1 = ∑ i ∈ lesion  R i · G i G i G   F2 = ∑ i ∈ shell  R i · G i G i where GF1 and GF2 are a gradient based features of the identified possible lesion, and a 3-voxel thick shell around the identified possible lesion, respectively, R i is an effective diameter of the lesion, and G i is a surface area of the identified possible lesion.

Claim 11

Dependent Claim 31 words

The method according to claim 1 , further comprising: extracting from each of said images derived from said at least two modalities a texture based feature of the identified possible lesion.

Claim 12

Dependent Claim 56 words

The method according to claim 10 , further comprising: extracting from each of said images derived from said at least two modalities the texture based feature based on the following equation: T=rms {F(lesion)} where T is a texture based feature of the lesion, and F is a Fourier transform of the voxel values within the lesion.

Claim 13

Dependent Claim 44 words

The method according to anyone of claim 1 , further comprising: extracting and comparing features of the identified possible lesion with features of a surrounding area of the identified possible lesion for each of said images derived from said at least two different modalities.

Claim 14

Dependent Claim 86 words

The method according to anyone of claim 1 , wherein said extracting step comprises: extracting from each of said images derived from said at least two different modalities temporal based features including at least one of Gd-DTPA uptake, speed of Gd-DTPA uptake, and inhomogeneity of Gd-DTPA uptake in the lesion calculated in terms of volume, uptake in the center of lesion, uptake in the margin of the lesion, a flow of contrast agent into the lesion, and a flow of contrast agent out of the lesion.

Claim 15

Dependent Claim 36 words

The method according to anyone of claim 13 , wherein said characterizing step comprises: providing at least one of a probability of malignancy, diagnosis, and prognosis of the identified possible lesion based on the extracted features.

Claim 16

Dependent Claim 57 words

The method according to anyone of claim 13 , wherein said characterizing step comprises: using an artificial neural network to provide at least one of a probability of malignancy, diagnosis, and prognosis of the identified possible lesion based on the at least one feature extracted from the plural images derived from said at least two imaging modalities.

Claim 17

Dependent Claim 34 words

The method according to claim 1 , wherein said characterizing step comprises: providing at least one of a probability of malignancy, diagnosis, and prognosis of the identified possible lesion based on the extracted features.

Claim 18

Dependent Claim 55 words

The method according to claim 1 , wherein said characterizing step comprises: using an artificial neural network to provide at least one of a probability of malignancy, diagnosis, and prognosis of the identified possible lesion based on the at least one feature extracted from the plural images derived from said at least two imaging modalities.

Claim 19

Dependent Claim 31 words

The method according to anyone of claim 1 , further comprising: extracting features that characterize a lesion within the image data in at least one of two dimensions and three dimensions.

Claim 20

Independent Claim 130 words

A method for the analysis of a lesion in an anatomy, comprising: obtaining plural image data, representative of plural images of a same portion of the anatomy, derived from at least one imaging modality selected from the group consisting of magnetic resonance imaging, x-ray imaging, and ultrasound imaging, said plural images derived at different times during introduction of a contrast agent into said anatomy; identifying from the image data a possible lesion in said plural images; extracting at least one feature related to inhomogeneity of uptake of a lesion from said plural image data corresponding to the identified possible lesion ; and characterizing said possible lesion based at least in part on the at least one feature extracted from the plural images derived from said at least one imaging modality.

Claim 21

Independent Claim 130 words

A method for the analysis of a lesion in an anatomy, comprising: obtaining plural image data, representative of plural images of a same portion of the anatomy, derived from at least one imaging modality selected from the group consisting of magnetic resonance imaging, x-ray imaging, and ultrasound imaging, said plural images derived at different times during introduction of a contrast agent into said anatomy; identifying from the image data a possible lesion in said plural images; extracting at least one feature related to inhomogeneity of uptake of a lesion from said plural image data corresponding to the identified possible lesion ; and characterizing said possible lesion based at least in part on the at least one feature extracted from the plural images derived from said at least one imaging modality.

Claim 22

Dependent Claim 34 words

The method according to claim 19 , further comprising: extracting geometric based features of the identified possible lesion; and characterizing said possible lesion based at least in part on the extracted geometric based features.

Claim 23

Dependent Claim 25 words

The method according to claim 20 , further comprising: extracting at least one of circularity and irregularity geometric based features from the identified possible lesion.

Claim 24

Dependent Claim 36 words

The method according to claim 19 , further comprising: extracting gray level based features from the identified possible lesion; and characterizing said possible lesion based at least in part on the extracted gray level based features.

Claim 25

Dependent Claim 39 words

The method according to claim 19 , further comprising: extracting from each of said images gradient based features of the identified possible lesion; and characterizing said possible lesion based at least in part on the extracted gradient based features.

Claim 26

Dependent Claim 40 words

The method according to claim 19 , further comprising: extracting from each of said images a texture based feature of the identified possible lesion; and characterizing said possible lesion based at least in part on the extracted texture based features.

Claim 27

Dependent Claim 50 words

The method according to claim 19 , further comprising: extracting and comparing features of the identified possible lesion with features of a surrounding area of the identified possible lesion for each of said images; and characterizing said possible lesion based at least in part on the extracted and compared features.

Claim 28

Dependent Claim 77 words

The method according to claim 19 , wherein said determining step comprises: determining from each of said images a variation over time of at least one of Gd-DTPA uptake, speed of Gd-DTPA uptake, and inhomogeneity of Gd-DTPA uptake in the lesion calculated in terms of volume, uptake in the center of lesion, uptake in the margin of the lesion, a flow of contrast agent into the lesion, and a flow of contrast agent out of the lesion.

Claim 29

Dependent Claim 34 words

The method according to claim 26 , wherein said characterizing step comprises: providing at least one of a probability of malignancy, diagnosis, and prognosis of the identified possible lesion based on the extracted features.

Claim 30

Dependent Claim 47 words

The method according to claim 26 , wherein said characterizing step comprises: using an artificial neural network to provide at least one of a probability of malignancy, diagnosis, and prognosis of the identified possible lesion based on the at least one feature extracted from the plural images.

Claim 31

Dependent Claim 34 words

The method according to claim 19 , wherein said characterizing step comprises: providing at least one of a probability of malignancy, diagnosis, and prognosis of the identified possible lesion based on the extracted features.

Claim 32

Dependent Claim 47 words

The method according to claim 19 , wherein said characterizing step comprises: using an artificial neural network to provide at least one of a probability of malignancy, diagnosis, and prognosis of the identified possible lesion based on the at least one feature extracted from the plural images.

Claim 33

Dependent Claim 29 words

The method according to claim 19 , further comprising: extracting features that characterize a lesion within the image data in at least one of two dimensions and three dimensions.

Claim 34

Dependent Claim 19 words

A storage medium storing a program for performing the steps recited in one of claims 1 - 31 .

Claim 35

Dependent Claim 27 words

The method according to claim 19 , wherein said extracting step comprises extracting a feature related to a time variation in a voxel value of the lesion.

Claim 36

Dependent Claim 31 words

The method according to claim 19 , wherein said extracting step comprises extracting a feature related to a time variation in a standard deviation of a voxel value in the lesion.

Claim 37

Dependent Claim 25 words

The method according to claim 19 , wherein said extracting step comprises extracting a feature related to a radial gradient frequency variation in the lesion.

Claim 38

Dependent Claim 62 words

The method according to claim 19 , wherein: said extracting step comprises extracting from said plural image data corresponding to the identified possible lesion at least one further feature related to an uptake of a lesion; and said characterizing step comprises characterizing said possible lesion based at least in part on the one further feature related to the uptake of the lesion.

Claim 39

Dependent Claim 24 words

The method according to claim 36 , wherein said extracting step comprises extracting a feature related to uptake in a margin of the lesion.

Claim 40

Dependent Claim 24 words

The method according to claim 36 , wherein said extracting step comprises extracting a feature related to uptake in a center of the lesion.

Claim 41

Dependent Claim 24 words

The method according to claim 36 , wherein said extracting step comprises extracting a feature related to a speed of uptake in the lesion.

Claim 42

Dependent Claim 63 words

The method according to claim 19 , wherein: said extracting step comprises extracting at least one further feature related to a spatial characteristic of a lesion from said plural image data corresponding to the identified possible lesion; said characterizing step comprises characterizing said possible lesion based at least in part on the one further feature related to the spatial characteristic of the lesion.

Claim 43

Dependent Claim 23 words

The method according to claim 40 , wherein said extracting step comprises extracting a feature related to a textural characteristic of the lesion.

Claim 44

Dependent Claim 26 words

The method according to claim 40 , wherein said extracting step comprises extracting a feature related to a power spectrum of voxel values in the lesion.

Claim 45

Dependent Claim 26 words

The method according to claim 40 , wherein said extracting step comprises extracting a feature related to a variation in a margin characteristic of the lesion.

Claim 46

Dependent Claim 24 words

The method according to claim 40 , wherein said extracting step comprises extracting a feature related to a radial gradient index of the lesion.

Claim 47

Dependent Claim 23 words

The method according to claim 40 , wherein said extracting step comprises extracting a feature related to a margin gradient of the lesion.

Claim 48

Dependent Claim 23 words

The method according to claim 40 , wherein said extracting step comprises extracting a feature related to a shape feature of the lesion.

Claim 49

Dependent Claim 22 words

The method according to claim 46 , wherein said extracting step comprises extracting a feature related to an irregularity of the lesion.

Claim 50

Dependent Claim 22 words

The method according to claim 46 , wherein said extracting step comprises extracting a feature related to a circularity of the lesion.

Claim 51

Independent Claim 152 words

A system for the analysis of a lesion in an anatomy, comprising: means for obtaining plural image data, representative of plural images of a same portion of the anatomy, derived from at least two imaging modalities selected from the group consisting of magnetic resonance imaging, x-ray imaging, and ultrasound imaging; means for identifying from the image data a possible lesion in said plural images; means for extracting, for each of said plural images derived from said at least two imaging modalities, at least one feature related to characterization of a lesion from said plural image data corresponding to the identified possible lesion; and means for merging in a common image classifier a plurality of extracted features, including at least one feature extracted from each of the plural images derived from said at least two imaging modalities to characterize said possible lesion based on the merged extracted features and yield a corresponding classification.

Claim 52

Independent Claim 152 words

A system for the analysis of a lesion in an anatomy, comprising: means for obtaining plural image data, representative of plural images of a same portion of the anatomy, derived from at least two imaging modalities selected from the group consisting of magnetic resonance imaging, x-ray imaging, and ultrasound imaging; means for identifying from the image data a possible lesion in said plural images; means for extracting, for each of said plural images derived from said at least two imaging modalities, at least one feature related to characterization of a lesion from said plural image data corresponding to the identified possible lesion; and means for merging in a common image classifier a plurality of extracted features, including at least one feature extracted from each of the plural images derived from said at least two imaging modalities to characterize said possible lesion based on the merged extracted features and yield a corresponding classification.

Claim 53

Independent Claim 136 words

A system for the analysis of a lesion in an anatomy, comprising: means for obtaining plural image data, representative of plural images of a same portion of the anatomy, derived from at least one imaging modality selected from the group consisting of magnetic resonance imaging, x-ray imaging and ultrasound imaging, said plural images derived at different times during introduction of a contrast agent into said anatomy; means for identifying from the image data a possible lesion in said plural images; means for extracting at least one feature related to inhomogeneity of uptake of a lesion from said image data corresponding to the identified possible lesion; and means for characterizing said possible lesion based at least in part on the at least one feature extracted from the plural images derived from said at least one imaging modality.

Claim 54

Independent Claim 136 words

A system for the analysis of a lesion in an anatomy, comprising: means for obtaining plural image data, representative of plural images of a same portion of the anatomy, derived from at least one imaging modality selected from the group consisting of magnetic resonance imaging, x-ray imaging and ultrasound imaging, said plural images derived at different times during introduction of a contrast agent into said anatomy; means for identifying from the image data a possible lesion in said plural images; means for extracting at least one feature related to inhomogeneity of uptake of a lesion from said image data corresponding to the identified possible lesion; and means for characterizing said possible lesion based at least in part on the at least one feature extracted from the plural images derived from said at least one imaging modality.

Claim 55

Independent Claim 117 words

A method for the analysis of a lesion in an anatomy, comprising: obtaining plural image data, representative of plural images of a same portion of the anatomy, derived from at least one imaging modality selected from the group consisting of magnetic resonance imaging, x-ray imaging, and ultrasound imaging; identifying from the image data a possible lesion in said plural images; extracting a radial gradient peak distinction and a variance of a gradient along a margin of said possible lesion; and characterizing said possible lesion based at least in part on said radial gradient peak distinction and said variance of a gradient along a margin extracted from the plural images derived from said at least one imaging modality.

Claim 56

Independent Claim 117 words

A method for the analysis of a lesion in an anatomy, comprising: obtaining plural image data, representative of plural images of a same portion of the anatomy, derived from at least one imaging modality selected from the group consisting of magnetic resonance imaging, x-ray imaging, and ultrasound imaging; identifying from the image data a possible lesion in said plural images; extracting a radial gradient peak distinction and a variance of a gradient along a margin of said possible lesion; and characterizing said possible lesion based at least in part on said radial gradient peak distinction and said variance of a gradient along a margin extracted from the plural images derived from said at least one imaging modality.

Annuity Stage	Window Opens	Payment Deadline	Surcharge Period Until	Estimated Fee	Status
3.5 Years (Year 4)	2004-11-12	2005-05-14	2005-11-13	$2000.00	Window Closed / Lapsed
7.5 Years (Year 8)	2008-11-12	2009-05-14	2009-11-13	$3760.00	Window Closed / Lapsed
11.5 Years (Year 12)	2012-11-12	2013-05-14	2013-11-13	$7700.00	Window Closed / Lapsed

Method, computer program product, and system for the automated analysis of lesions in magnetic resonance, mammogram and ultrasound images

Abstract

Inventors

Bibliographic Details

Claims Analysis

References Cited (Backward Citations)

USPTO Annuity & Maintenance Windows

Assigned Categories & Tags

Assign Category Tag