Self-detection of pulmonary nodules on chest CT images
A technology for CT imaging and pulmonary nodules, applied in the field of medical diagnosis, can solve the problems of reduced accuracy of pulmonary nodules, omission of original information, few medical images, etc., and achieves the effect of reducing omission of features, improving detection accuracy, and improving accuracy.
Inactive Publication Date: 2019-01-04
CHANGZHOU NO 2 PEOPLES HOSPITAL
View PDF4 Cites 5 Cited by
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
[0007] 1. There are few existing medical images containing pulmonary nodules, and the amount of data in the database is insufficient, resulting in a decrease in the accuracy of detecting pulmonary nodules
[0008] 2. It cannot improve the robustness of CT to the occlusion of pulmonary nodules in medical images, which affects the detection accuracy of CT for pulmonary nodules
[0009] 3. The original information may be missed during the detection process, which reduces the accuracy of lung nodule detection
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
specific Embodiment approach
[0036] A method for self-detection of pulmonary nodules in chest CT images, comprising the following steps:
[0037] S1. Construction of sample database:
[0038] a. Randomly select images of several lung cases from the original data set in the LIDC database, and extract the lung nodule coordinate information by reading the XML format annotation file of the original data set, and use the case image and lung nodule coordinate information Form a sample database;
[0039] b. Intercept the sample data set after preprocessing, copy all the preprocessed samples, and add Gaussian noise to the copied samples to form an expanded sample data set;
[0040] S2. Data standardization: According to the statistical distribution of HU values in the sample database, select an appropriate HU value as the standardization range, and standardize the data to [0, 1];
[0041] S3. Building a model: building a three-dimensional convolutional neural network model, and setting model hyperparameters; ...
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 relates to the technical field of medical diagnosis, in particular to a pulmonary nodule self-detection method based on chest CT images. The method includes the following steps: constructing sample database, standardizing data, constructing model, constructing detection model one, constructing detection model two, constructing training detection model and detecting pulmonary nodules.The invention expands the data of the lung nodule target, which can make the network structure learn more characteristics, solves the problem of insufficient data in the database, and improves the detection accuracy of the lung nodule. Furthermore, the construction of the detection model improves the robustness of CT to the occlusion of pulmonary nodules in medical images, and improves the detection accuracy of CT to pulmonary nodules. In addition, the sample prepared by the invention is a three-dimensional sample, and the preparation of the three-dimensional sample can retain the original information to the maximum extent, and reduce the feature omission, thereby improving the accuracy of detecting the pulmonary nodules.
Description
technical field [0001] The invention relates to the technical field of medical diagnosis, in particular to a method for self-detection of pulmonary nodules in chest CT images. Background technique [0002] CT, that is, computerized tomography, uses precisely collimated X-ray beams, γ-rays, ultrasound, etc., together with highly sensitive detectors, to perform cross-sectional scans one after another around a certain part of the human body. , clear images, etc., can be used for the examination of various diseases; according to the different rays used, it can be divided into: X-ray CT (X-CT), ultrasound CT (UCT) and γ-ray CT (γ-CT). [0003] CT scans a layer of a certain thickness of a certain part of the human body with an X-ray beam. The X-rays that pass through this layer are received by the detector and converted into visible light, which is converted from photoelectricity into an electrical signal, and then converted by an analog / digital converter. It is a number, which i...
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): G06T7/00
CPCG06T7/0012G06T2207/10081G06T2207/20081G06T2207/20084G06T2207/30064
Inventor 李晶
Owner CHANGZHOU NO 2 PEOPLES HOSPITAL