Malignant nodule edge detection image processing method based on benign thyroid template

Abstract

The invention provides a malignant nodule edge detection image processing method based on a benign thyroid template. The method comprises the steps: learning an obtained thyroid three-dimensional image data set through a neural network, and forming a parameterized benign thyroid template; matching with the benign thyroid template according to the labeling information and the image information of the thyroid nodule ultrasonic image to be recognized, and performing coarse positioning on the nodule by combining the three-dimensional image and the feature information of the benign thyroid templateto obtain an initial contour curve of the nodule; adopting a local binary fitting model to iterate and evolve the initial contour curve to obtain an evolved contour curve; and performing effective contour selection on the evolved contour curve to obtain a final peripheral contour curve and a segmentation result, and performing fine positioning on the position of the nodule. The method is higher in autonomous recognition capability, better in adaptability to input of different thyroid images, better in segmentation effect, more accurate in numerical value implementation and higher in segmentation adaptability to images with uneven gray levels.

Description

technical field [0001] The present invention relates to the technical field of image processing, in particular to an image processing method for edge detection of malignant nodules based on a benign thyroid template and a corresponding system, device and medium. Background technique [0002] Thyroid nodules are scattered lesions caused by local abnormal growth of thyroid cells, and the formed mass can move up and down with the thyroid gland with the swallowing action. In recent years, similar to the United States and other countries, the incidence of thyroid diseases in my country, including thyroid nodules and thyroid cancer, has increased rapidly. Thyroid nodules can be used as a diagnostic indicator for thyroid cancer, and thyroid cancer is a curable disease in the early stage. Therefore, it is necessary to accurately identify benign and malignant nodules, their size, and location to ensure that malignant nodules can be diagnosed. Get the right clinical treatment. [00...

AI Technical Summary

Problems solved by technology

[0007] The Chinese patent application with the publication number CN106056595A proposes a method for automatically identifying benign and malignant thyroid nodules based on a deep convolutional neural network. For benign and malignant, the fine segmentation of nodule margins is still a traditional region-based segmentation method, which cannot well solve the problem of uneven gray levels in thyroid ultrasound images

[0008] The Chinese patent application with the publication number CN110060235A proposes a deep learning-based ultrasound image segmentation method for thyroid nodules that can improve the accuracy of nodule segmentation, but the steps are complicated, the segmentation efficiency is low, and it relies on large-scale Nodule Image Dataset

Images