Construction method and device of automatic liver segmentation model based on deep learning, computer equipment and storage medium

Abstract

The invention provides a construction method of an automatic liver segmentation model based on deep learning, and the method comprises the steps: obtaining a three-dimensional image of a sample liver, and obtaining a liver segmentation label of the three-dimensional image of the sample liver; taking the three-dimensional image of the sample liver and the liver segmentation label as a training set, iterating the liver segmentation model for deep learning training to acquire the trained liver segmentation model, wherein a deep learning network adopted by the liver segmentation model is a segmentation network based on combination of UNet / VNet and a channel attention mechanism. The invention further provides a construction device of automatic liver segmentation model based on deep learning, computer equipment and a readable storage medium. Due to the fact that the UNet / VNet and the channel attention mechanism are combined, more image information of the sample liver three-dimensional image is mined through the UNet / VNet, important channel information is endowed with higher weight through the channel attention mechanism, a more accurate prediction result is obtained, and an accurate and efficient liver segmentation result can be provided for doctors.

Description

technical field [0001] The present invention relates to the technical field of medical image processing, in particular to the technical field of liver segmentation, and specifically refers to a method, device, computer equipment and storage medium for constructing an automatic liver segmentation model based on deep learning. Background technique [0002] Liver cancer is one of the most common cancer diseases in the world. Currently, liver cancer surpasses gastric cancer and ranks among the top three cancer deaths. The liver is a common site for primary or secondary tumor growth, and their heterogeneity and diffuse shape make segmental dissection difficult. Therefore, the ability to accurately infer and measure each segment in the liver is a prerequisite for modern liver surgery. [0003] In clinical diagnosis, it is very time-consuming to explore spatial information along the Z-axis for liver segmentation, and thus requires an automated method to solve it efficiently. Rece...

AI Technical Summary

Problems solved by technology

[0005] However, there are few studies on automatic liver segmentation based on MRI at present, and the traditional algorithm is still used to implement it step by step (Lebre M A, Vacavant A, Grand-Brochier M, et al. Automatic segmentation methods for liver and hepatic vessels from CT and MRI volumes, applied to the Couinaudscheme[J].Computers in Biology and Medicine,2019,110(7):42-51), that is, liver segmentation, vessel centerline extraction and reconstruction of liver segmentation

Images