A denoising method for ultrasound images of thyroid nodules
A technology for thyroid nodules and ultrasound images, applied in image enhancement, image analysis, image data processing, etc., can solve the problems of less than 5% of thyroid disease treatment rate, thyroid disease awareness rate, low treatment rate, etc., to improve the level of diagnosis , the effect of improving the proportion of diagnostic accuracy
Active Publication Date: 2020-05-12
WENZHOU MEDICAL UNIV
View PDF9 Cites 0 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
As the second largest disease in the field of endocrine, the awareness rate and treatment rate of thyroid disease in my country are very low, and the overall treatment rate of thyroid disease is less than 5%.
Method used
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View moreImage
Smart Image Click on the blue labels to locate them in the text.
Smart ImageViewing Examples
Examples
Experimental program
Comparison scheme
Effect test
Embodiment Construction
[0032] The present invention is described in further detail below in conjunction with accompanying drawing:
[0033] Such as Figure 4 As shown, a method for denoising ultrasound images of thyroid nodules, comprising the following steps:
[0034] S1. Construct a database of ultrasound images of thyroid nodules; the image database adopts a standard database (BSD database) and a database composed of a large number of clinical front-line patient data.
[0035] S2. Perform NSST decomposition on the ultrasound image of thyroid nodules, and according to the characteristics of the speckle noise distribution of the ultrasound image of the thyroid, obtain a corresponding sparse representation model for low-frequency component denoising, so as to eliminate the speckle noise of the low-frequency component and improve image contrast;
[0036] S3. Design a deep learning network training model, and combine the high-frequency components transformed by NSST with the deep learning network tra...
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More PUM
Login to View More Abstract
The invention discloses a thyroid nodule ultrasound image denoising method, which includes the following steps: constructing a database of thyroid nodule ultrasound images; performing NSST decomposition on the thyroid nodule ultrasound image, and targeting the speckle noise distribution characteristics of the thyroid ultrasound image, Obtain the corresponding sparse representation model for denoising the low-frequency components to eliminate the speckle noise of the low-frequency components and improve the image contrast; design a deep learning network training model, and combine the high-frequency components after NSST transformation with the deep learning network training model to More effectively separate speckle noise and image edges; reconstruct the ultrasound image of thyroid nodules after removing speckle noise through INSST. The present invention has the following advantages and effects: it is based on the combination of multi-scale geometric analysis and deep learning, and establishes a corresponding speckle noise suppression model and framework, in order to obtain good thyroid nodule ultrasound image processing results.
Description
technical field [0001] The invention relates to the field of ultrasonic image denoising, in particular to a method for denoising ultrasonic images of thyroid nodules. Background technique [0002] With the improvement of living standards, people's health awareness is also constantly strengthened. The number of patients seeing a doctor because of thyroid disease is also increasing. According to the Chinese Health Association, thyroid disease has become the fifth leading cause of disease in the world, and it is expected to jump to the second leading cause of disease by 2020 and become a fatal disease. In recent years, the growth rate of thyroid diseases in China has risen sharply. The Beijing Municipal Health Bureau released in 2012 that the growth rate of thyroid cancer in Beijing exceeded 200% from 2000 to 2010, ranking first in the growth rate of various cancers. According to official statistics It shows that the prevalence of thyroid nodules is as high as 18.6%, which me...
Claims
the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More Application Information
Patent Timeline
Login to View More Patent Type & Authority Patents(China)
IPC IPC(8): G06T5/00G06T7/00
CPCG06T7/0012G06T2207/10132G06T2207/20081G06T2207/20084G06T2207/20192G06T2207/30096G06T5/70
Inventor 张鑫陈伟斌
Owner WENZHOU MEDICAL UNIV