Pneumoconiosis detection method based on deep learning and system

A technology of deep learning and detection methods, applied in image data processing, instruments, character and pattern recognition, etc., can solve problems such as complicated method process, doctors spend a lot of energy, and affect life and work treatment, so as to reduce medical resources and reduce The effect of waiting time

Active Publication Date: 2018-09-07
四川元匠科技有限公司
View PDF7 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] Since the diagnosis and differentiation of pneumoconiosis requires doctors to observe from multiple angles and for a long time, it has the following defects: (1) The patient cannot get the exact diagnosis result immediately, which affects life and work and subsequent treatment; (2) The traditional method process It is complicated and requires a lot of energy from doctors; (3) The diagnostic results are highly subjective, and different doctors may have different diagnostic results

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 more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Pneumoconiosis detection method based on deep learning and system
  • Pneumoconiosis detection method based on deep learning and system
  • Pneumoconiosis detection method based on deep learning and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] Such as figure 1 As shown, a deep learning-based pneumoconiosis nodule detection method provided in Embodiment 1 includes the following steps:

[0039] Step S1, the CT machine scans a complete chest image of the patient, starts the image conversion program, converts the CT image in DICOM format into a lung image in numpy array format, and reads the CT image data information.

[0040] In step 1, the CT image information refers to the patient information in the DICOM format data, the length and width of the CT image, and the interval between image pixels. Each dimension of the numpy array is n, h, w. n represents the channel of the image, h represents the height of the image, and w represents the width of the image.

[0041] Step S2, performing morphological operations to obtain a parenchymal image in which only the lung parenchyma is preserved.

[0042] In step 2, the specific operation steps of the morphological operation are as follows:

[0043] S2.1. Using a thres...

Embodiment 2

[0059] like figure 2 As shown, a deep learning-based pneumoconiosis nodule detection system provided in Embodiment 2 includes a CT machine 1, a CT image conversion module 2, a lung parenchyma segmentation module 3, a pneumoconiosis lesion area segmentation and determination module 4, and detection results The saving module (the csv file of the data saved by the detection result saving module) 5, the CT image conversion module 2, the lung parenchyma segmentation module 3, the pneumoconiosis lesion area segmentation and judgment module are programmed in Python language; the CT image scanned by the CT machine is input into the CT image The conversion module 2, the input of the lung parenchyma segmentation module 3 is the output of the CT image conversion module 2, the input of the pneumoconiosis lesion area segmentation and judgment module 4 is the output of the lung parenchyma segmentation module 3, and the detection result preservation module 5 is saved in the database The dat...

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

No PUM Login to view more

Abstract

The invention relates to a detection method of pneumoconiosis nodules. The method comprises the following steps: S1, converting a CT image of a DICOM format into a lung image of a numpy array format,and reading CT image data information; S2, carrying out morphological operations to obtain a parenchyma image retaining only lung parenchyma; S3, dividing the parenchyma image into multiple small blocks of small-block images; S4, sending the small-block images into a convolutional neural network for screening and diagnosis of the pneumoconiosis nodules, and obtaining a detection result; and S5, storing the detection result as a csv format. According to the method, the number of the pneumoconiosis nodules and coordinate areas where the same are located are detected through converting, the morphological operations and screening of the CT image, automatic diagnosis of a pneumoconiosis symptom is realized, and the problem that pneumoconiosis identification requires massive medical resources isalleviated.

Description

technical field [0001] The invention relates to a pneumoconiosis detection technology for CT images, in particular to a pneumoconiosis nodule detection technology based on deep learning. Background technique [0002] With the increasing population and demand for pulmonary medical care, there is an urgent need to speed up the speed and quality of nodule detection in pulmonary medical care. Among them, the problem of diagnosis and differentiation of pneumoconiosis is particularly prominent. The traditional differential diagnosis of pneumoconiosis requires lung biopsy of the patient and reference to the patient's previous X-ray chest films and case summaries. [0003] Since the diagnosis and differentiation of pneumoconiosis requires doctors to observe from multiple angles and for a long time, it has the following defects: (1) The patient cannot get the exact diagnosis result immediately, which affects life and work and subsequent treatment; (2) The traditional method process ...

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
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06T7/00G06T7/136G06T7/155G06K9/62G06T5/30
CPCG06T5/30G06T7/0012G06T7/136G06T7/155G06T2207/30064G06T2207/20081G06T2207/20084G06T2207/10081G06F18/24
Inventor 吉普照臧宇航郑德生朱安婕张雪
Owner 四川元匠科技有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap