CT image lesion detection method and system based on double-branch network, terminal and storage medium

Abstract

The invention provides a CT image lesion detection method and system based on a double-branch network, a terminal and a storage medium. The method comprises the following steps: segmenting an acquired3D medical image into a plurality of 2D layer images; determining inputs of a 2D branch and a 3D branch in a double-branch network according to the segmented 2D layer images; performing 2D branch and3D branch feature extraction on the double-branch network step by step, and determining spatial structure features and context features of each level; performing feature fusion on the spatial structure features and the context features of each level of the double-branch network to obtain fusion features of each level; performing lesion detection by using a target detection method based on the fusion features of each level. According to the invention, modeling and information extraction are carried out on 2D spatial structure information and 3D context information through the double-branch network, and feature fusion is carried out after each level of the two branches through a cross-level feature fusion method, so that feature expression has spatial and context information at the same time, and the lesion detection performance is improved.

Description

technical field [0001] The present application relates to the technical field of medical image processing, and in particular to a dual-branch network-based CT image lesion detection method, system, terminal and storage medium. Background technique [0002] Computer tomography (Computed Tomography, CT) uses X-rays to scan the human body and obtain high-precision internal tissue imaging. CT scanning is widely used in clinical practice and is of great significance to the diagnosis process of diseases. A CT scan is a continuous, multi-layered image. A typical CT scan often includes more than one hundred slices, requiring doctors to spend a lot of time on careful diagnosis. In recent years, deep learning technology has been widely used in the field of medical images. The use of deep learning technology for lesion detection can greatly shorten the diagnosis time, reduce the workload of doctors, and improve the efficiency of diagnosis. [0003] Lesion detection in CT images requi...

AI Technical Summary

Problems solved by technology

[0006] Aiming at the deficiencies of the prior art, this application provides a CT image lesion detection method, system, terminal and storage medium based on a dual-branch network. By using 2D and 3D branches in the backbone network, it solves the problem that the prior art cannot simultaneously build Modulo 2D spatial structure information and 3D context information, poor lesion detection effect, etc.

Images