Auxiliary diagnosis method for benign and malignant properties and infiltration degree of pulmonary nodules based on artificial intelligence
A technology of artificial intelligence and pulmonary nodules, applied in the field of image processing, can solve problems such as pain points and lack of functions of clinicians, achieve efficient deep learning and parallel computing, comprehensive functions, and improve efficiency and effectiveness
Inactive Publication Date: 2018-05-01
点内(上海)生物科技有限公司
View PDF0 Cites 6 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
For the pulmonary nodules found in the CT images of the people being screened, there are already some methods based on deep learning; however, most of the existing methods have not introduced the most advanced research results of the current deep learning methods. There is still room for improvement; at the same time, there is also a lack of functionality, which makes the existing methods unable to become a complete solution to solve the pain points of clinicians
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 1
[0023] Such as figure 1 As shown, this embodiment includes the following steps:
[0024] Step 1. CT-based pulmonary nodule detection, specifically: 1) Divide the original CT according to lung windows and perform equidistant and direction-changing data standardization operations; 2) Use morphological automatic thresholds on the standardized data , opening and closing operations, and region-growing region segmentation operations; 3) Take out negative samples of non-nodule regions and positive samples of nodule regions in the lung with a preset step size; 4) Train a specially designed deep neural network to segment nodules 5) Training a specialized deep neural network to complete false positive attenuation; 6) Using the trained neural network to complete the segmentation of each small block of nodules inside the lung and splicing the segmentation results of each small block through a preset strategy.
[0025] Step 2. Judgment of benign and malignant pulmonary nodules based on CT...
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 an auxiliary diagnosis method for benign and malignant properties and infiltration degree of pulmonary nodules based on artificial intelligence, the method comprises the following steps: detecting lung nodules based on a CT, judging benign and malignant properties of the lung nodules based on the CT, judging infiltration degree of the lung nodules based on the CT, and segmenting lung nodules nidus based on the CT and realizing auxiliary diagnosis. The method provided by the invention can automatically identify the nidus comprising the lung nodules, provides nidus segmentation, diagnosis of benign and malignant properties and judgement of infiltration degree, and improves efficiency and effect of discovering and diagnosing the lung nodules by doctors.
Description
technical field [0001] The invention relates to a technology in the field of image processing, in particular to an artificial intelligence-based auxiliary diagnosis method for benign and malignant pulmonary nodules and the degree of infiltration. Background technique [0002] Low-dose computed tomography (LDCT) examination in high-risk groups of lung cancer is an effective method for screening lung cancer. Early diagnosis of lung cancer can effectively improve prognosis and reduce mortality. Accurate identification of high-risk groups can not only improve screening efficiency, but also It can reduce the waste of medical resources and avoid unnecessary radiation for low-risk groups. CT interpretation has high requirements for professional level and clinical experience. Large tertiary hospitals have high standards and can meet the needs of screening and diagnosis and treatment. However, in primary hospitals, there are quite difficulties, which may easily lead to misdiagnosis a...
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 IPC IPC(8): G06T7/00G16H50/20
CPCG06T7/0012G06T2207/10081G06T2207/20081G06T2207/20084G06T2207/30064
Inventor 葛亮商丽君丁寅
Owner 点内(上海)生物科技有限公司