DSA image detection method, apparatus and equipment based on deep learning

An image detection and deep learning technology, applied in medical images, image enhancement, image analysis, etc., can solve the problems of difficult DSA image judgment and recognition, complex arterial vascular structure, poor shooting device effect, etc., and achieve a wide and good application prospect. , to avoid subjective bias, the effect of good accuracy

Inactive Publication Date: 2018-11-27
ZHONGAN INFORMATION TECH SERVICES CO LTD +1
View PDF5 Cites 13 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] However, at present, DSA observation and detection are used manually by doctors to assist in the diagnosis of moyamoya disease. Second, some DSA image images include a lot of non-vascular information, such as skull, teeth and other noise information, due to the poor shooting device eff

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
  • DSA image detection method, apparatus and equipment based on deep learning
  • DSA image detection method, apparatus and equipment based on deep learning
  • DSA image detection method, apparatus and equipment based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0037] figure 1 It is a schematic flow chart of the deep learning-based DSA image detection method provided in Embodiment 1 of the present invention, as figure 1 As shown, the deep learning-based DSA image detection method provided by the embodiment of the present invention includes the following steps:

[0038] 101. Mark the input DSA image to obtain marked training samples.

[0039] Specifically, the input DSA image is marked, and the DSA image marked as abnormal is set as a positive sample, and the DSA image marked as normal is set as a negative sample to obtain a marked training sample.

[0040] Here, the embodiment of the present invention does not limit the source of the input DSA image, which may come from the DSA image data collected by the front-end crystal shooting, or from the storage database.

[0041] Exemplarily, figure 2 and image 3 They are the schematic diagrams of the positive and negative samples of moyamoya disease DSA images marked respectively, and ...

Embodiment 2

[0102] Figure 4 It is a schematic flow chart of the deep learning-based DSA image detection method provided by Embodiment 2 of the present invention, as figure 2 As shown, the deep learning-based DSA image detection method provided by the embodiment of the present invention includes the following steps:

[0103] 201. Collect a DSA image, where the DSA image includes a DSA image to be detected.

[0104] Regarding DSA image acquisition, according to the different requirements of different types of DSA images in practice, the corresponding acquisition can better meet the requirements of DSA image detection. Exemplarily, according to the needs of moyamoya disease DSA image detection, two subtraction angiography DSA image sequences, left internal carotid artery LICA and right internal carotid artery RICA, are captured by corresponding data capture equipment or modules, including Several images sequenced in time are taken, and the images at different moments correspond to the di...

Embodiment 3

[0171] Figure 6 It is a schematic diagram of the composition of the DSA image detection device based on deep learning provided by Embodiment 3 of the present invention, as Figure 6 As shown, the deep learning-based DSA image detection device provided by the embodiment of the present invention includes a labeling module 31 , a preprocessing module 32 , a training module 33 and a detection module 34 .

[0172] Wherein, the labeling module 31 is used for labeling the input DSA image and obtaining marked training samples. Specifically, the input DSA image is marked, and the DSA image marked as abnormal is set as a positive sample, and the DSA image marked as normal is set as a negative sample to obtain a marked training sample.

[0173] The preprocessing module 32 is configured to preprocess the training samples to obtain a training data set. Specifically, the training sample is subjected to preprocessing including image size scaling, image contrast enhancement and / or image de...

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 discloses DSA image detection method, apparatus and equipment based on deep learning, and belongs to the technical field of deep learning and digital image processing. The DSA image detection method based on deep learning includes the steps: marking an input DSA image to obtain a labeled training sample; preprocessing the training sample to obtain a training data set; using the training data set to perform training through a convolutional neural network to obtain a DSA image detection network model; and detecting the input DSA image to be detected through the DSA image detectionnetwork model to obtain a detection result. The DSA image detection method based on deep learning can quickly and accurately obtain the DSA image detection result, so as to meet the daily enhanced andincreased medical service demand and solve the technical problems that current observation and detection methods of DSA images are low in efficiency, are time-consuming and labor consuming and are unsatisfactory in the detection effect, and has a wide and good application prospects in many medical fields involving medical image detection and recognition.

Description

technical field [0001] The present invention relates to the technical field of deep learning and digital image processing, in particular to a DSA image detection method, device and equipment based on deep learning. Background technique [0002] With the promulgation of the national "White Paper on Medical Artificial Intelligence Technology and Application" and more than 80 related national dividend policies, the application of the combination of artificial intelligence and medical treatment has good development opportunities. Moreover, there is a large imbalance between medical resources and demand in my country, which is even more serious in second- and third-tier cities. The lack of high-quality doctor resources hinders timely diagnosis and treatment of patients. [0003] At the same time, with the advancement of computer vision technology, deep learning technology has also made major breakthroughs in the field of medical imaging technology. In addition to teaching machine...

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
IPC IPC(8): G16H30/40G06T3/40G06T5/00G06T5/30G06N3/04
CPCG06T3/40G06T5/002G06T5/30G16H30/40G06T2207/20221G06T2207/30101G06N3/045
Inventor 雷宇梅鵾张鑫高超苏佳斌顾宇翔倪伟杨恒毛顺亿褚振方胡仲华傅致晖孙谷飞周建华陆王天宇
Owner ZHONGAN INFORMATION TECH SERVICES CO LTD
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