Medical image segmentation method based on Boosting-Unet segmentation network

Patent metadata

Field	Value
Publication number	US-12444492-B2
Application number	US-202318183931-A
Country	US
Kind code	B2
Filing date	Mar 14, 2023
Priority date	May 10, 2022
Publication date	Oct 14, 2025
Grant date	Oct 14, 2025

Abstract

The present invention provides a medical image segmentation method based on a Boosting-Unet segmentation network. By dividing training of an overall segmentation network into training of m sub segmentation networks, the method inherits convolution kernel parameters of the (k−1) th sub segmentation network during training of the k th sub segmentation network, thereby greatly decreasing the quantity of the convolution kernel parameters during every training and improving the learning ability of the network and the resistance to noise and image blur. In addition, a plurality of sub segmentation networks are arranged, so that the efficiency of the network is improved, a depth of an image data feature is also extracted, and the image data is segmented precisely, thereby improving the learning ability of the overall segmentation network to the image data feature, enhancing the robustness to noise disturbance information and further improving the performance of image segmentation.

First claim

What is claimed is:

1. A medical image segmentation method based on a Boosting-Unet segmentation network, comprising following steps:
S 1 : acquiring a pancreas cancer-related CT slice image data set, pre-processing the data set, and dividing the data set into a training set and a validation set, wherein the data set includes original medical images and corresponding known medical images with labeled segmentation;
S 2 : planning a number n of layers of an overall segmentation network according to a scale of the data set in S 1 , constructing single-layered segmentation networks, and constructing the overall segmentation network by utilizing the single-layered segmentation networks, wherein the overall segmentation network is an instance of the Boosting-Unet segmentation network;
S 3 : dividing the overall segmentation network obtained in S 2 into m sub segmentation networks, where m is an integer greater than or equal to 1, and training the m sub segmentation networks by utilizing the training set; and
S 4 : inputting an original medical image of the validation set into the trained overall segmentation network obtained in S 3 , outputting image data results with labeled segmentation, and comparatively selecting an optimum of the trained overall segmentation network based on the image data results;
in the S 1 , the pre-processing the data set comprises:
I: truncating and normalizing each of medical image data in the data set, with a specific formula below:

V
_

=

max
⁢

(

b
,

min
⁢

(

a
,
V

)

)

-
a

b
-
a

wherein V is single medical image data in the data set, a is a minimum value in the single medical image data, b is a maximum value in the single medical image data, and V is medical image data re-generated by truncating and normalizing the single medical image data; the data set comprises the original medical image and a medical image with labeled segmentation corresponding the original medical image;
in the S 2 , each of the single-layered segmentation networks is an i th layer of the overall segmentation network, wherein 1≤i≤n, each of the single-layered segmentation networks comprises encoding blocks and decoding blocks, the encoding blocks perform feature data extraction on data inputted in the encoding blocks, the decoding blocks output image data labeled with segmentation, the overall segmentation network is constructed by utilizing the single-layered segmentation networks, the inputted image data is inputted to encoding blocks of a 1 st layer, the encoding blocks of the 1 st layer to an n th layer are unidirectionally connected in series together successively in an output-input order to form an encoding path, outputs of encoding blocks of the n th layer are unidirectionally connected to inputs of the decoding blocks of the n th layer, and the decoding blocks of the n th layer to the 1 st layer unidirectionally connected in series together successively in an output-input order to form a decoding path, and finally, the decoding blocks of the 1 st layer output the medical image data with labeled segmentation, and in addition, the encoding blocks in same layer are to be in skip connection to the decoding blocks;
the constructing encoding blocks of the i th layer, wherein 1≤i≤n, of the overall segmentation network comprises following steps:
I: determining a number of needed convolution kernels, initializing the convolution kernels, and selecting an activation function and a pooling operation, specifically comprising following operations:
selecting two convolution kernels, wherein parameters of each convolution kernel of the two convolution kernels are 3×3×3, i.e., three-dimensional matrix data with a height of 3, a width of 3 and a channel number of 3, and initializing the parameters of the convolution kernel in form of a random decimal matrix; setting the number of layers of the convolution kernel to be n×32, wherein n represents an n th layer of the overall segmentation network, setting a moving step length to be a pixel step length, and the moving step length uses zero-padding for invariable size of the outputted image data; and selecting a rectified linear unit (Relu) function as the activation function and selecting max pooling with a kernel of 2×2 as the pooling operation;
II: establishing a feature extraction flow for the inputted image data;
the feature extraction flow for the inputted image data in the step II specifically comprises following steps:
{circle around (1)} Performing a convolutional operation on the inputted image data of the i th layer and the convolution kernel to extract feature data;
{circle around (2)} Performing nonlinear function fitting activation on the extracted feature data by using the Relu function; and
{circle around (3)} Reducing a size of the feature data by means of max pooling after activation;
repeating the feature extraction flow according to quantity of the encoding layers;
constructing the decoding blocks of the 1 st layer of the overall segmentation network comprises following steps:
I: determining the number of needed convolution kernels, initializing the convolution kernels, and selecting an upsampling method and an activation function, specifically comprising following operations:
selecting four convolution kernels, wherein parameters of each of two convolution kernels of four convolution kernels are 3×3×3, i.e., three-dimensional matrix data with a height of 3, a width of 3 and a channel number of 3, and initializing the parameters of the convolution kernels in form of a random decimal matrix; parameters of each of another two convolution kernels of four convolution kernels are 1×1×1, i.e., three-dimensional matrix data with a height of 1, a width of 1 and a channel number of 1, and initializing the parameters of the convolution kernels in form of a random decimal matrix; setting the number of layers of each of the two 3×3×3 convolution kernels to be n×32, wherein n represents the n th layer of the overall segmentation network, setting the number of layers of each of the two 1×1×1 convolution kernels to be 2, setting a moving step length to be a pixel step length, and the moving step length uses zero-padding for invariable size of the outputted image data; and selecting trilinear interpolation as a method of the upsampling, and selecting a Sigmoid function as the activation function;
II: establishing a processing flow for the inputted encoded feature data;
the processing flow for the inputted encoded feature data in the step II specifically comprises following steps:
{circle around (1)} Splicing the feature data with the feature data extracted by the encoding blocks in the same layer through skip connection to obtain the feature dat

Assignees

• Univ South China Normal

Inventors

• Ye Qi
• Wen Lihui
• Chen Jiawei
• Fang Chihua

Classifications

• G06T2207/20084

  Artificial neural networks [ANN] · CPC title

• G06T3/4007

  based on interpolation, e.g. bilinear interpolation (image demosaicing G06T3/4015; edge-driven or edge-based scaling G06T3/403) · CPC title

• G06T7/10 Primary

  Segmentation; Edge detection (motion-based segmentation G06T7/215) · CPC title

• G06T2207/30004

  Biomedical image processing · CPC title

• G06T2207/20081

  Training; Learning · CPC title