Thyroid nodule invasiveness prediction method based on target detection

Abstract

The invention belongs to the technical field of image processing, and particularly relates to a thyroid nodule invasiveness prediction method based on target detection. The method comprises the following steps: S1, preprocessing a thyroid ultrasound image obtained clinically to obtain an original data set; S2, constructing a positioning network model of a network structure based on a traditional Faster RCNN, and pre-training the positioning network model; S3, extracting nodule form information in the ultrasonic image by using a positioning network, and obtaining aspect ratio information of the nodules and context information of gland tissues; S4, constructing a classification network model; S5, establishing a multi-model fusion thyroid nodule invasiveness prediction network, and predicting the thyroid nodule invasiveness in the ultrasonic image; and S6, training and updating the classification network model in the fused network model, and storing the model with the highest accuracy in the verification set. According to the method, end-to-end full-automatic auxiliary diagnosis can be achieved, and the defects that a traditional method is insufficient in accuracy and low in detection rate are overcome.

Description

technical field [0001] The invention belongs to the technical field of image processing, in particular to a method for predicting the aggressiveness of thyroid nodules based on target detection. Background technique [0002] The thyroid is the largest endocrine gland in the human body. Ultrasound examination can make qualitative and quantitative estimates of its size, volume and blood flow, and can make qualitative or semi-qualitative diagnosis of benign and malignant tumors. Therefore, ultrasonic detection methods have also become imaging examinations. The preferred method for thyroid disease. In the past, the results of thyroid ultrasound examination were mainly judged by doctors based on experience, and conclusions were predicted. After the introduction of image recognition technology, various detection systems based on classification can replace manual processing and prediction of ultrasound image data, thereby greatly improving the detection efficiency of images; Prel...

AI Technical Summary

Problems solved by technology

[0005] In view of the problems existing in the existing technical solutions, the purpose of the present invention is to provide a method for predicting the invasiveness of thyroid nodules based on target detection, which can overcome the difficulty of taking into account the context information of the nodule itself and the glandular tissue in the traditional detection method, resulting in The disadvantages of insufficient accuracy, and the shortcomings of traditional algorithms that cannot realize an end-to-end fully automatic system

Images