Ultrasonic image-based thyroid diffuse disease intelligent diagnosis method and system

Abstract

The invention relates to the field of ultrasonic image analysis, in particular to an ultrasonic image-based thyroid diffuse disease intelligent diagnosis method, which comprises the following steps ofintercepting an area of interest of an ultrasonic image based on a Faster R-CNN model, and highlighting the area of interest by image enhancement; based on a DSSDInceptionV3 model, realizing detection and identification of a thyroid diffusion area in the area of interest, and intercepting the thyroid diffusion area; measuring the size of the thyroid diffusion area based on the length-width ratioof the connected component bounding rectangle, and outputting a measurement result; and making diagnosis of a thyroid diffusion disease according to the position parameter, the quantity parameter andthe corresponding size parameter of the thyroid diffusion area. According to the invention, the type and probability of the thyroid diffusion disease can be automatically detected, and the size, position and coverage degree of the thyroid diffusion disease can be accurately identified.

Description

technical field [0001] The invention relates to the field of ultrasonic image analysis, in particular to an intelligent diagnosis method and system for diffuse thyroid disease based on ultrasonic images. Background technique [0002] Diffuse thyroid disease is a common thyroid disease, and the most common ones are Hashimoto's disease and Graves' disease. Ultrasound image examination is one of the widely used methods of thyroid disease examination. It is of great clinical significance to conduct research on diffuse thyroid disease based on texture features of ultrasound images and timely diagnose patients suffering from diffuse thyroid disease. [0003] At present, in the field of computer-aided diagnosis, it is common to use methods such as deep learning and radiomics to study thyroid nodular diseases based on ultrasound images, but there are few radiomics research data on diffuse thyroid diseases, and only some researchers use imaging The omics method can distinguish Hash...

AI Technical Summary

Problems solved by technology

[0003] At present, in the field of computer-aided diagnosis, it is common to use methods such as deep learning and radiomics to study thyroid nodular diseases based on ultrasound images, but there are few radiomics research data on diffuse thyroid diseases, and only some researchers use imaging Omics method, by extracting the texture features of the image, the distinction between Hashimoto's disease and normal thyroid, or the distinction between hyperthyroidism and addition and subtraction

However, the classification of ultrasound images of a variety of common diffuse thyroid diseases, such as Graves' disease, Hashimoto's disease, and normal thyroid tissue, is still blank, and no research has specifically proposed corresponding texture features for the characteristics of thyroid diseases to improve diffuse Disease diagnostic accuracy

Images