Thyroid cancer CT image classification system based on deep residual network

Abstract

The invention discloses a thyroid cancer CT image classification system based on a deep residual network, and the system comprises: a thyroid cancer CT image obtaining module which is used for obtaining CT images of a plurality of thyroid cancer patients with labels; a multi-scale segmentation module which is used for segmenting the CT image according to different scales, and sequentially intercepting a tumor, a cubic area with the tumor expanded by 5 mm and a cubic area with the tumor expanded by 10 mm to obtain a tumor image, a tumor expanded image with the tumor expanded by 5 mm and a tumor expanded image with the tumor expanded by 10 mm; a preprocessing module which is used for preprocessing the image to obtain a training data set; a deep residual network training module which is used for training and optimizing the deep residual network by using the training data set; and a thyroid cancer CT image classification module which is used for inputting thyroid cancer CT images to be classified into the optimized deep residual network for classification to obtain a classification result of the thyroid cancer CT images. According to the system, the thyroid cancer CT images can be accurately classified.

Description

technical field [0001] The invention relates to the technical fields of medical imaging and artificial intelligence, in particular to a thyroid cancer CT image classification system based on a deep residual network. Background technique [0002] In recent years, computer technology has been widely used in the medical field, especially computer-aided diagnosis technology, which relies on medical imaging and medical image processing technology, combined with computer-related algorithms, to assist radiologists in diagnosis and improve the accuracy and efficiency of diagnosis. [0003] Thyroid cancer is a cancer with a relatively high incidence rate, and it is reported that up to 60%-70% of patients have lymph node metastasis. Therefore, before the initial operation, it is necessary to accurately determine the scope of lymph node dissection and determine the risk of lymph node metastasis. Clinically, it is usually determined by CT examination, because CT images need to be identi...

AI Technical Summary

Problems solved by technology

If the existing framework for ordinary image classification is adopted, it is impossible to accurately classify CT images of thyroid cancer, and thus cannot assist doctors in judging whether lymph nodes have metastasized in CT images of thyroid cancer

Images