Method for segmenting ultrasonic two-dimensional image of thyroid nodule

Abstract

The invention discloses a segmentation method for an ultrasonic two-dimensional image of a thyroid nodule. The segmentation method comprises the following steps: carrying out an image enhancement means on the ultrasonic two-dimensional image; the processed two-dimensional image is input into a model based on a U-net structure, the U-net structure comprises n down-sampling operations and n up-sampling operations, the down-sampling operations are composed of convolution modules of a plurality of different convolution kernels, each convolution module is composed of a pooling operation and a convolution operation, and each convolution operation is composed of a pooling operation and a convolution operation; in the convolution operation, convolution kernels with corresponding sizes are adopted to process an input image, and IN operation and Relu operation are added behind the input image; the up-sampling operation consists of a multi-head self-attention mechanism module and a deconvolution module, the deconvolution module consists of convolution with different convolution kernel sizes and bilinear interpolation or transpose convolution, and IN operation and Relu operation are performed after each convolution operation; a segmentation result is enhanced through a loss function and evaluation is carried out; and outputting the segmented ultrasonic two-dimensional image.

Description

technical field [0001] The present application relates to the field of medical technology, in particular to a method for segmenting an ultrasonic two-dimensional image of a thyroid nodule. Background technique [0002] At present, the number of patients with thyroid cancer is increasing, and the diagnosis and treatment of thyroid cancer are becoming more and more important. At this stage, ultrasound has become an important means of thyroid cancer screening due to its advantages of timeliness and no radiation. However, ultrasound examination is very dependent on the physician's technique and experience, and ultrasound imaging is also easily affected by various factors. In recent years, artificial intelligence technology has developed rapidly, and the use of artificial intelligence to analyze ultrasound images to assist physicians in diagnosing thyroid nodules has also received attention, but how to accurately segment the nodule area is still a relative difficulty. [0003] ...

AI Technical Summary

Problems solved by technology

However, due to the influence of ultrasound resolution and noise, the precise segmentation of nodules in thyroid ultrasound images is not accurate enough, which easily leads to misjudgment

[0004] The existing thyroid ultrasound image segmentation technology is not good in terms of accuracy, especially in the segmentation of edge details.

Images