Thyroid CT image computer-aided diagnosis system and method
A computer-aided CT image technology, applied in the field of medical image analysis, can solve the problems of low detection rate of thyroid disease and insufficient standard treatment rate, and achieve the effect of improving identification accuracy, avoiding the influence of human subjective factors, and low cost
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Publication Date
- 2014-08-27
- Estimated Expiration
- Not applicable · inactive patent
Smart Images

Figure 1 
Figure 2 
Figure 3
Abstract
Description
technical field
[0001] The invention relates to the technical field of medical image analysis, in particular to a system and method for computer-aided diagnosis of thyroid CT images. Background technique
[0002] In 2012, the "Report on the Incidence of Malignant Tumors in Beijing Residents" released by the Beijing Municipal Health Bureau showed that from 2000 to 2010, the incidence of thyroid cancer increased by 223.75%, ranking first in the incidence (increase) of various cancers, causing general attention of the society. According to the latest data released by the China Health Education Center in June 2013, there are currently more than 200 million thyroid disease patients in my country. However, the detection rate of thyroid disease is very low, and the overall standard treatment rate is less than 5.0%.
[0003] At present, the diagnosis of thyroid disease is mainly based on medical history, physical examination, ultrasound, CT and isotope scanning. To determine its n...
Examples
Embodiment
[0110] Present embodiment a kind of thyroid CT image computer-aided diagnosis system, such as figure 1 As shown, it includes an input module 1 , an image texture feature extraction module 2 , a classification diagnosis module 3 and an output module 4 connected in sequence. This input module is used to import thyroid images after contour segmentation and extraction. The image texture feature extraction module performs image texture analysis on the extracted thyroid image containing lesions to obtain the image features of the target image, and the image features are 13-dimensional grayscale co-occurrence texture features and 15-dimensional gray-scale gradient co-occurrence texture features. The classification diagnosis module includes a classifier in the module. The module contains multiple cases of benign and malignant thyroid CT image texture feature databases that have been pathologically diagnosed after surgery. According to the diagnostic model established in the existing d...