US 2026/0017531 A1Published application

Focal learning-based method for intelligent ct angiography imaging

AssigneeThe First Medical Center of Pla General Hospital

InventorsXin LOU, Mingliang YANG, Jinhao LYU

Life of this patent

Estimating the term…

Loading patent…

Abstract

The present invention discloses a focal learning-based method for intelligent CT angiography imaging. (1) Acquiring NCCT images and their corresponding real CTA images; (2) Constructing an adversarial network model comprising a generator, a corrector, and a discriminator; (3) Formulating a joint focal learning loss function for the generator-corrector pair and a separate loss function for the discriminator; (4) Training the adversarial network model using the training set, and validating the trained model using the validation set; (5) Identifying the generator with the best test performance by virtue to the test set. The invention establishes a joint focal learning loss function, which allows the generator to create synthetic CTA images that more effectively emphasize target areas, like vascular tissues. Furthermore, a corrector is incorporated into the invention to facilitate improved registration and alignment between NCCT images and CTA images.

A focal learning-based method for intelligent CT angiography imaging, comprising the following steps:

Step 1:
Acquiring NCCT images and their corresponding real CTA images, followed by normalization processing;
The normalized NCCT images and the corresponding normalized real CTA images constitute sample pairs, which are subsequently partitioned into training, validation, and test sets;
Step 2:
Constructing an adversarial network model comprising a generator, a corrector, and a discriminator;
Step 3:
Formulating a joint focal learning loss function for the generator-corrector pair and a separate loss function for the discriminator;
Step 4:
Training the adversarial network model using the training set, and validating the trained model using the validation set;
Step 5:
Inputting sample pairs from the test set into the generator to produce normalized synthetic CTA images, and testing and evaluating the obtained images to identify the generator with the best test performance;
Step 6:
Loading the best-performing generator produced in Step 5 and inputting the normalized NCCT images to be processed into the generator, which outputs the corresponding normalized synthetic CTA images;
The joint focal learning loss function LGR for the generator-corrector pair, as stated in Step 3, is defined by the following formula:
min
⁢
L
G
⁢
R
=
L
G
⁢
A
⁢
N
(
G
,
D
)
+
∑
i
=
1
m
⁢
b
i
⁢
L
C
⁢
o
⁢
r
⁢
r
i
+
γ
⁢
L
Smooth
L
G
⁢
A
⁢
N
(
G
,
D
)
=
E
x
[
(
1
-
D
⁡
(
G
⁡
(
x
)
)
)
2
]
L
C
⁢
o
⁢
r
⁢
r
i
=
E
x
,
y
[

y
i
-
(
G
⁡
(
x
)
⁢
°
⁢
R
⁡
(
G
⁡
(
x
)
,
y
)
)
i

1
]
L
Smooth
=
E
x
,
y
[

∇
R
⁢
(
G
⁢
(
x
)
,
y
)

1
2
]
Where, LGAN(G, D) denotes the adversarial loss function, where D is the discriminator and G is the generator;
m represents the number of focal scales;
bi is the weighting coefficient for the
i
t
⁢
h
⁢
L
C
⁢
orr
i
;
L
C
⁢
orr
i
represents the correction loss function;
γ is the weighting coefficient of LSmooth;
LSmooth is the smoothing loss function;
E(⋅) is the expectation operator, with the subscript indicating the input variable;
x is the normalized NCCT image input to the generator G;
° represents the resampling operation;
R is the corrector;
∇ represents the gradient operator;
∥⋅∥1 is L1 distance operator;
R(G(x),y) denotes the correction space matrix output by the corrector through training;
G(x) is the output of the generator;
G(x)°R(G(x),y) is the normalized synthetic CTA image after correction;
y is the normalized real CTA image;
i takes values 1 and 2;
when i=1, the full-image loss between y and G(x)°R(G(x),y) is computed;
when i=2, the region-filtered image loss between y and G(x)°R(G(x),y) is computed;
The discriminator's loss function LAdv(G, D) stated in Step 3 is defined by the following formula:
min
⁢
L
A
⁢
d
⁢
v
(
G
,
D
)
=
E
y
[
(
1
-
D
⁡
(
y
)
)
2
]
+
E
x
[
D
⁡
(
G
⁡
(
x
)
)
2
]
.

232 more elements

Abstract

Claims6