US 11,776,120 B2 · Method for predicting morphological changes of liver tumor after ablation based on deep learning

Abstract

A method for predicting the morphological changes of liver tumor after ablation based on deep learning includes: obtaining a medical image of liver tumor before ablation and a medical image of liver tumor after ablation; preprocessing the medical image of liver tumor before ablation and the medical image of liver tumor after ablation; obtaining a preoperative liver region map, postoperative liver region map, and postoperative liver tumor residual image map; obtaining a transformation matrix by a Coherent Point Drift (CPD) algorithm and obtaining a registration result map according to the transformation matrix; training the network by a random gradient descent method to obtain a liver tumor prediction model; using the liver tumor prediction model to predict the morphological changes of liver tumor after ablation. The method provides the basis for quantitatively evaluating whether the ablation area completely covers the tumor and facilitates the postoperative treatment plan for the patient.

A method for predicting morphological changes of liver tumor after ablation based on deep learning, comprising:

1) Obtaining a data set comprising a medical image of the liver tumor before the ablation and a medical image of the liver tumor after the ablation;
2) Pre-processing the medical image of the liver tumor before the ablation and the medical image of the liver tumor after the ablation;
3) Obtaining a preoperative liver region map and a preoperative liver tumor region map from a medical image map before the ablation, and obtaining a postoperative liver region map, a postoperative ablation region map, and a postoperative liver tumor residual image map from a medical image map after the ablation;
4) Registering the preoperative liver region map and the postoperative liver region map by a Coherent Point Drift (CPD) algorithm, and obtaining a transformation matrix;
obtaining a registration result map of the medical image map after the ablation corresponding to the preoperative liver region map and the preoperative liver tumor region map according to the transformation matrix;
5) using the medical image map before the ablation, the preoperative liver region map, the preoperative liver tumor region map and the registration result map as an input of U-net network, and using the postoperative liver tumor residual image map as a real training label;
training the U-net network by a random gradient descent method to obtain a liver tumor prediction model;
and
6) using the liver tumor prediction model to predict the morphological changes of the liver tumor after the ablation;
wherein step 3 comprises:
marking the preoperative liver region map, the preoperative liver tumor region map, and the postoperative liver region map by a maximum flow/minimum cut algorithm;
introducing a potential energy field function based on a global and local region representation as a constraint in a segmentation process, and establishing an adaptive hybrid variational model;
using the maximum flow/minimum cut algorithm to solve an energy equation minimization;
determining a target region selectively according to gray information, boundary gradient, texture information and local context information in different image regions;
wherein step 4 comprises:
obtaining liver data point set of the preoperative liver region map and the postoperative liver region map, making the liver data point set of the preoperative liver region map Xi=(x1, . . . , xN)T as a target point set, and making the liver data point set of the postoperative liver region map Yi=(y1, . . . , yM)T as a model point set, wherein the target point set is a data set of Gaussian mixture model, and the model point set is a kernel point set of the Gaussian mixture model;
N and M respectively represent a number of points in the target point set and a number of the model point set;
a probability density function of the Gaussian mixture model is:
p
⁡
(
x
⁢
❘
"\[LeftBracketingBar]"
m
)
=
1
(
2
⁢
∏
σ
2
)
D
/
2
⁢
exp

x
-
y
m

2
2
2
⁢
σ
2
p
⁡
(
x
)
=
ω
⁢
1
N
+
(
1
-
ω
)
⁢
∑
m
=
1
M
1
M
⁢
p
⁡
(
x
⁢
❘
"\[LeftBracketingBar]"
m
)
;
wherein p(x|m) is a probability density basis function of the Gaussian mixture model, σ represents a standard deviation of the probability density function, ω represents a weight value of overflow points, and a value range is 0-1, x is a translation variable;
calculating a minimum negative logarithm likelihood function:
E(θ,σ2)=−Σn=1N log Σm=1M+1P(m)p(x|m),
θ represents transformation parameters, and σ represents the standard deviation of the probability density function;
obtaining a derivative according to a gradient descent method:
Q
⁡
(
θ
,
σ
2
)
=
1
2
⁢
σ
2
⁢
∑
n
=
1
N
∑
m
=
1
M
P
old
(
m
⁢
❘
"\[LeftBracketingBar]"
x
n
)
⁢

x
n
-
τ
⁡
(
y
m
,
θ
)

2
+
N
p
⁢
D
2
⁢
log
⁢
σ
2
,
wherein
P
⁡
(
m
)
=
1
M
,
N
P
=
∑
n
=
1
N
∑
m
=
1
M
P
old
(
m
⁢
❘
"\[LeftBracketingBar]"
x
n
)
≤
N
,
P
old
(
m
⁢
❘
"\[LeftBracketingBar]"
x
n
)
=
exp
-
1
2
⁢

x
n
-
τ
⁡
(
y
m
,
θ
old
)
σ
old

2
∑
k
=
1
M
exp
-
1
2
⁢

x
n
-
τ
⁡
(
y
k
,
θ
old
)
σ
old

2
+
c
,
τ represents one of rigid, affine and non-rigid transformations, and
c
=
(
2
⁢
∏
σ
2
)
D
/
2
⁢
ω
1
-
ω
⁢
M
N
;
solving optimal parameters for the transformation parameters of the minimum negative logarithm likelihood function by iteration with an Expectation-Maximization algorithm;
and
calculating a location of the preoperative liver region map corresponding to the medical image map after the ablation according to selected point cloud data and the optimal parameters for the transformation parameters, wherein the selected point cloud data comprise the liver data point set of the preoperative liver region map Xi=(x1, . . . , XN)T and the liver data point set of the postoperative liver region map Yi=(y1, . . . , yM)T.

276 more elements

Method for predicting morphological changes of liver tumor after ablation based on deep learning

Life of this patent

Method for predicting morphological changes of liver tumor after ablation based on deep learning

Life of this patent

Abstract

Claims8