# US 2025/0095828 A1 · Medical image segmentation method based on multi-scale feature fusion

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2025/0095828 A1
- Document ID: US20250095828A1
- Status: Published application
- Kind: A1
- Application number: 18/883,295
- Filed: 2024-09-12
- Published: 2025-03-20
- Earliest claimed: 2023-09-15
- Assignees: Guizhou Provincial People's Hospital; Guizhou University
- Applicants: Guizhou Provincial People's Hospital; Guizhou University
- Inventors: Rongpin WANG; Bangkang FU; Junjie HE; Yunsong PENG; Xinhuan SUN
- Web page: https://patentgrep.com/patent/US20250095828A1

## CPC

- G16H 30/40: for processing medical images, e.g. editing
- G06T 3/40: Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T 7/10: Segmentation; Edge detection (motion-based segmentation G06T7/215)
- G06T 7/11: Region-based segmentation
- G06V 10/25: Determination of region of interest [ROI] or a volume of interest [VOI]
- G06V 10/44: Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V 10/771: Feature selection, e.g. selecting representative features from a multi-dimensional feature space
- G06V 10/82: using neural networks
- G06T 2207/20081: Training; Learning
- G06T 2207/20084: Artificial neural networks [ANN]
- Y02T 10/40: Engine management systems
- G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- Y02T: CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION

## Abstract

Provided is a medical image segmentation method based on multi-scale feature fusion. The method includes acquiring medical image data of a same type, and sketching a region of interest (ROI); preprocessing sketched image data; constructing a multi-scale feature extraction module, a multi-scale feature fusion module, and an encoder-decoder deep learning network model; performing 5-fold cross-validation on the network model; and evaluating a medical image segmentation result output by the model with an evaluation index including a dice, an accuracy, a precision and a recall. This application extracts multi-scale features comprehensively from an encoder, a decoder, and connection between the encoder and the decoder in the network, and effectively learns multi-scale information in the image. The multi-scale features are fused by an interactive module, so this application relieves feature conformity caused by direct multi-scale fusion, thereby improving performance of the medical image segmentation.

## Claims

### Claim 1

A medical image segmentation method based on multi-scale feature fusion, comprising the steps:
S1: acquiring medical image data of a same type, and sketching a region of interest (ROI);
S2: preprocessing the medical image data obtained in S1;
S3: constructing a multi-scale feature extraction module;
S4: constructing a multi-scale feature fusion module;
S5: constructing an encoder-decoder deep learning network model;
S6: performing 5-fold cross-validation on the network model; and
S7: evaluating segmentation performance with an evaluation index.

### Claim 2 (depends on 1)

The medical image segmentation method based on multi-scale feature fusion according to claim 1, wherein the S2 preprocessing the medical image date comprises:
S21: reading the medical image data acquired in S1 into a memory, and seeking a mean and a standard deviation of the data:
μ
=
1
n
⁢
∑
i
=
1
n
x
i
std
=
1
n
⁢
∑
i
=
1
n
(
x
i
-
μ
)
2
S22: performing normalization on an image according to the mean and the standard deviation:
Y
=
X
-
μ
std
wherein, μ represents the mean, std is the standard deviation, n represents a number of samples, xi represents an ith sample, X represents a sample population, and Y represents a sample population obtained after the normalization; and
S23: preprocessing the data by flipping the image and scaling the image to a same size.

### Claim 3 (depends on 1)

The medical image segmentation method based on multi-scale feature fusion according to claim 1, wherein when the multi-scale feature extraction module is constructed in S3, the multi-scale feature extraction module is constructed in an encoder and a decoder first, and then a cross-feature extraction module is constructed between the encoder and the decoder.

### Claim 4 (depends on 3)

The medical image segmentation method based on multi-scale feature fusion according to claim 3, wherein the multi-scale feature extraction module comprises a convolutional neural network (CNN) channel based on local information feature extraction and a transformer channel based on global information feature extraction; the CNN channel comprises a convolutional layer, a normalization layer and an activation function; and the CNN channel has a following computing method:
Y
1
=
Re
⁢
lu
⁡
(
BN
⁡
(
Conv
⁡
(
Y
0
)
)
)
Y
2
=
Re
⁢
lu
⁡
(
X
+
BN
⁡
(
Conv
⁡
(
Y
1
)
)
)
wherein, Y0 represents an input feature map, Conv represents a convolutional operation, BN is a normalization operation, Relu is the activation function, Y1 is a result subjected to convolution, normalization and the activated function once, and Y2 is a feature map output finally through the CNN channel; and a self-attention of the transformer channel is computed by:
Q
,
K
,
V
=
DewConv
⁡
(
Y
0
)
Q
1
=
Conv
S
=
r
(
Q
)
K
1
=
Conv
S
=
r
(
K
)
Light_Atten
⁢
(
Q
,
K
,
V
)
=
Soft
⁢
max
⁡
(
Q
1
⁢
K
1
T
d
k
)
⁢
V
wherein, DewConv represents depthwise separable convolution, Y0 represents the input feature map, Q is a query matrix, K is a key matrix, V is a value matrix, ConvS=r represents convolution at a stride of r, the matrix Q and the matrix K are respectively subjected to the convolution to obtain a matrix Q1 and a matrix K1, Light_Atten represents a lightweight self-attention, dk is a dimension of the key matrix, and Softmax is a mapping function.

### Claim 5 (depends on 3)

The medical image segmentation method based on multi-scale feature fusion according to claim 3, wherein when the cross-feature extraction module is constructed, an input of the cross-feature extraction module is a feature map output by the encoder; the encoder comprises three layers of multi-scale feature extraction modules and multi-scale feature fusion modules; for the input feature map, a feature map output by a first layer of multi-scale feature extraction modules and multi-scale feature fusion modules is α1, and a feature map output by a second layer and a feature map output by a third layer are respectively α2, and α3; and the cross-feature extraction module is constructed as follows:
performing matrix multiplication on the feature map α1 and the feature map α2, performing normalization on a result of the matrix multiplication;
performing matrix multiplication on a processed result and the feature map α3; and
performing residual connection on a result of the matrix multiplication and the feature map α3.

### Claim 6 (depends on 1)

The medical image segmentation method based on multi-scale feature fusion according to claim 1, wherein the multi-scale feature fusion module in S4 comprises two inputs, a local information feature f1 extracted by a CNN and a global information feature f2 extracted by a transformer;
for the multi-scale feature fusion module, the f1 and the f2 and the/are concatenated into a feature map matrix, the feature map matrix is split into v different portions in a first dimension, a shift operation is performed on h portions along a y-axis direction, and spatial position information is learned with convolution to obtain a feature map ZV a shift operation is performed in an x-axis direction, and spatial information is learned with the convolution; and residual connection is performed on an obtained feature map ZH, and the input feature map matrix:
Z
V
=
Conv
⁡
(
Roll
(
Chunk
(
Z
,
v
)
,
Vertical
)
)
Z
H
=
Conv
⁡
(
Roll
(
Chunk
(
Z
V
,
h
)
,
Horizontal
)
)
wherein, Z is the concatenated feature map matrix, v is a portion to be split, Chunk represents a split operation, Roll represents the shift operation, Conv represents a convolutional operation, Vertical represents the shift operation along the y-axis direction, and Horizontal represents the shift operation along the x-axis direction.

### Claim 7 (depends on 1)

The medical image segmentation method based on multi-scale feature fusion according to claim 1, wherein the encoder-decoder deep learning network model in S5 consists of an encoder and a decoder;
the encoder-decoder deep learning network model comprises four layers, and each of the four layers comprises the multi-scale feature extraction module and the multi-scale feature fusion module;
a preprocessed medical image is input, a local feature is generalized through a convolutional module having a stride, and a feature map is downsampled;
an obtained feature map enters a CNN local feature extraction channel and a transformer global feature extraction channel to obtain two feature matrices having a same size;
the two feature matrices are concatenated and input to the multi-scale feature fusion module; and
the multi-scale feature fusion module is configured to perform interaction on features of different scales through a split operation and a shift operation.

### Claim 8 (depends on 7)

The medical image segmentation method based on multi-scale feature fusion according to claim 7, wherein for the features of the different scales obtained by the encoder, attentions of the features are fused through a cross-feature extraction module between the encoder and the decoder;
an obtained feature is connected to the decoder; and
through extraction, fusion and upsampling on multi-scale features, a segmented mask image is obtained.

### Claim 9 (depends on 1)

The medical image segmentation method based on multi-scale feature fusion according to claim 1, wherein S6 comprises: uniformly splitting a dataset into five subsets having a similar size, comprising four subsets used in training, and one subset used as a validation set;
performing validation cyclically five times; and
averaging validation results in the five times to obtain a final result.

### Claim 10 (depends on 9)

The medical image segmentation method based on multi-scale feature fusion according to claim 9, wherein a model parameter is optimally trained with a weighted cross-entropy loss function and a dice loss function by:
L
Dice
=
1
-
2
⁢
❘
"\[LeftBracketingBar]"
P
⋂
G
❘
"\[RightBracketingBar]"
❘
"\[LeftBracketingBar]"
P
❘
"\[RightBracketingBar]"
+
❘
"\[LeftBracketingBar]"
G
❘
"\[RightBracketingBar]"
L
CE
=
-
1
N
⁢
∑
i
=
1
C
∑
j
=
1
N
g
ij
⁢
log
⁢
p
ij
L
total
=
α
⁢
L
Dice
+
(
1
-
α
)
⁢
L
CE
wherein, LDice represents the dice loss function; LCE represents the cross-entropy loss function; Ltotal represents a total loss function, G represents a real label; P represents a segmented region predicted by the network model; N represents a total number of pixels in an input image; in gij, i represents a category of a label, and j represents a pixel, and the gij has a value of 1 when a predicted label of the pixel is the same as the real label, and a value of 0 when the predicted label of the pixel is different from the real label; pij is a probability that the model outputs the pixel j; and α is an artificially set parameter, and is in an interval from 0 to 1.
