Ear CT (Computed Tomography) image vestibular segmentation method for mixing 2D (Two Dimensional) and 3D (Three Dimensional) convolutional neural networks

Abstract

The invention discloses an ear CT image vestibule segmentation method mixing 2D and 3D convolutional neural networks. The method comprises three steps of constructing a data set, designing a 2DCNN segmentation network based on a plurality of depth feature fusion strategies, and designing a 3D DDenseUNet segmentation network. The 2D network adopts an encoder-decoder structure as a backbone network to extract vestibular features of the ear CT image; the method comprises the following steps: firstly, constructing a vestibule, then integrating DenseNet-BC and U-Net network architectures, constructing a 3DDenseUNet network, fusing low-level spatial information and high-level semantic information, and finally realizing precise segmentation of the vestibule. The segmentation network designed for the vestibular structure can obtain segmentation performance better than that of a general segmentation method, and the working efficiency and quality of medical staff in the radiology department are improved. The ear key structure can be accurately and automatically segmented, a doctor is helped to complete a large amount of repeated work, and the burden of the doctor is effectively relieved.

Description

technical field [0001] The invention belongs to the field of computer vision and medical image processing, and specifically relates to computer image processing, deep learning, ear CT image diagnosis and the like. Background technique [0002] The structure of the ear is specific in shape, precise in structure, and complex in function, and most of the structures are located in the temporal bone. The temporal bone is divided into three parts: inner ear, middle ear and outer ear, mainly including malleus, incus, stapes, outer wall of cochlea, inner cavity of cochlea, vestibule, anterior semicircular canal, outer semicircular canal, posterior semicircular canal, internal auditory canal, jugular vein ball and socket, etc. More than 30 organs. [0003] The vestibule is one of the important organs of the inner ear. It is located between the cochlea and the semicircular canal. It is an irregular oval cavity on the CT image. Vestibular abnormality is the most common inner ear dise...

AI Technical Summary

Problems solved by technology

The method of 2D CNN is to divide the three-dimensional body into multiple two-dimensional slices and send them to the network for training. This method has low complexity and is easy to train, but it cannot make good use of the contextual semantic information between the slices, resulting in poor segmentation performance. Difficult to improve

Although the 3D CNN method can take advantage of the correlation between slices, it requires huge computing resources and is difficult to train.

[0007] (3) Due to objective reasons such as difficulty in sample data collection and high labeling threshold, the quantity and quality of labeling sample data are very scarce.

Deep neural networks require large-scale data samples for training to achieve excellent performance. The lack of labeled samples and the imbalance of categories have brought great technical challenges to vestibular segmentation.

Images