Method and system for the automatic analysis of an image of a biological sample

Patent metadata

Field	Value
Publication number	US-9558550-B2
Application number	US-201214344965-A
Country	US
Kind code	B2
Filing date	Sep 14, 2012
Priority date	Sep 16, 2011
Publication date	Jan 31, 2017
Grant date	Jan 31, 2017

Abstract

Method for the automatic analysis of an image of a biological sample with respect to a pathological relevance, wherein a)local features of the image are aggregated to a global feature of the image using a bag of visual word approach, b) step a) is repeated at least two times using different methods resulting in at least two bag of word feature datasets, c) computation of at least two similarity measures using the bag of word features obtained from a training image dataset and bag of word features from the image, d) the image training dataset comprising a set of visual words, classifier parameters, including kernel weights and bag of word features from the training images, e) the computation of the at least two similarity measures is subject to an adaptive computation of kernel normalization parameters and/or kernel width parameters, f) for each image one score is computed depending on the classifier parameters and kernel weights and the at least two similarity measures, the at least one score being a measure of the certainty of one pathological category compared to the image training dataset, g) for each pixel of the image a pixel-wise score is computed using the classifier parameters, the kernel weights, the at least two similarity measures, the bag of word features of the image, all the local features used in the computation of the bag of word features of the image and the pixels used in the computations of the local features, h) the pixel-wise score is stored as a heatmap dataset linking the pixels of the image to the pixel-wise scores.

First claim

The invention claimed is:

1. A method for the automatic analysis of an image of a biological sample with respect to a pathological relevance, wherein
a) local features of the image are aggregated to a global feature of the image using a bag of Visual word approach,
b) step a) is repeated at least two times using different methods resulting in at least two bag of word feature datasets,
c) computation of at least two similarity measures using the bag of word features obtained from a training image dataset and bag of word features from the image, the image training dataset comprising a set of Visual words, classifier parameters, including kernel weights and bag of word features from the training images,
the computation of the least to two similarity measures based on one of the following kernels:
Generalized exponential kernel
k w,p ( x l ,x r )= p exp(− wd (( x l ,x r ))  (3),

Gaussian kernel
k w,p ( x l ,x r )= p exp(− w∥x l −x r ∥ 2 2 )  (4),

Chi2 kernel

k

w
,
p

⁡

(

x
l

,

x
r

)

=

p
⁢

⁢

exp
(

-
w

⁢

∑

d
∈

{

1
,

⁢
…
⁢

,
D

)

❘

x
l

(
d
)

+

x
r

(
d
)

>
0

⁢

(

x
l

(
d
)

-

x
r

(
d
)

)

2

x
l

(
d
)

+

x
r

(
d
)

)

(
5
)

Polynomial kernel
k w,p,t ( x l ,x r )= p ( x l ,x r +w ) t   (6)

d) the computation of the at least two similarity measures is subject to an adaptive computation of kernel normalization parameters and/or kernel width parameters,
e) for each image at least one score is computed depending on the classifier parameters and kernel weights, wherein this computation is performed in two steps:
at first by computing a dimension-wise score for each dimension of each of the bag of word features for a subimage by using first order Taylor expansions of a support vector machine prediction function around a point x 0 which is a root of the prediction function f(x 0 )=0:

f
⁡

(
x
)

=

⁢

b

Assignees

• Klauschen Frederick
• Kawanabe Motoaki
• Mueller Klaus-Robert
• Binder Alexander
• Univ Berlin Tech
• Fraunhofer Ges Forschung

Inventors

• Klauschen Frederick
• Kawanabe Motoaki
• Mueller Klaus-Robert
• Binder Alexander

Classifications

• G06V10/806

  of extracted features · CPC title

• G06V10/809

  of classification results, e.g. where the classifiers operate on the same input data · CPC title

• G16H50/20 Primary

  for computer-aided diagnosis, e.g. based on medical expert systems · CPC title

• G06T7/0012 Primary

  Biomedical image inspection · CPC title

• G06F18/253

  of extracted features · CPC title