Image identification method and apparatus

An image recognition and image technology, which is applied in the field of medical imaging, can solve problems such as low universality, threat to patients' lives, and unrecognizable pulmonary nodules, and achieve the effect of strong universality and improved accuracy

Inactive Publication Date: 2015-12-16
NEUSOFT CORP
View PDF6 Cites 55 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, the artificially selected features are not necessarily representative, and some pulmonary nodules may not conform to some selected features, so in the process of image recognition, these pulmonary nodules that do not conform to the artificially selected features may be can not be identified, leading to misdiagnosis and threatening the patient's life
[0005

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
  • Image identification method and apparatus
  • Image identification method and apparatus
  • Image identification method and apparatus

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0070] see figure 1 , which is a flow chart of Embodiment 1 of an image recognition method provided by the present invention.

[0071] The image recognition method provided in this embodiment includes the following steps:

[0072] Step S101: Obtain a training image set, the training area set includes images of lung nodule areas and images of non-lung nodule areas.

[0073] Deep Convolutional Neural Networks (DCNN) is a kind of artificial neural network, which mines the spatial local association information of interest targets in natural images by strengthening the local connection pattern (Local Connectivity Pattern) of nodes between adjacent layers in the neural network. . The deep convolutional neural network is a kind of deep learning (Deep Learning). The so-called deep learning is relative to shallow learning (Shallow Learning). The biggest difference between the two is that shallow learning has only one layer of hidden layer nodes. Deep learning has multiple hidden lay...

Embodiment 2

[0147] In practical applications, some pulmonary nodules are relatively large, and some pulmonary nodules are relatively small. If the pulmonary nodule image is extracted according to the same preset size, there will be more redundant data involved in the smaller pulmonary nodules. The calculation increases the workload of detecting pulmonary nodules and reduces the detection efficiency. In order to solve this technical problem, in this embodiment, it is divided into two different extraction sizes according to the different sizes of pulmonary nodules. The extraction size of larger pulmonary nodules is larger, and the extraction size of smaller pulmonary nodules is smaller. Small, for smaller pulmonary nodules, the detection workload is reduced and the detection efficiency is improved.

[0148] Specifically, see figure 2 , which is a flow chart of Embodiment 2 of an image recognition method provided by the present invention.

[0149] The image recognition method provided in ...

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

An embodiment of the invention discloses an image identification method. The method comprises: obtaining a training image set, wherein the training image set comprises a pulmonary nodule region image and a non pulmonary nodule region image; constructing a deep convolutional neural network, and taking the pulmonary nodule region image carrying a pulmonary nodule identifier and the non pulmonary nodule region image carrying a non pulmonary nodule identifier as inputs for training the deep convolutional neural network; constructing a testing network according to the deep convolutional neural network obtained by training; and obtaining a suspected pulmonary nodule region image, and inputting the suspected pulmonary nodule region image into the testing network to obtain a judgment result of judgment whether a pulmonary nodule exists in the suspected pulmonary nodule region image or not, thereby realizing identification of the suspected pulmonary nodule region image. An embodiment of the invention furthermore discloses an image identification apparatus. According to the image identification method and apparatus, the identification accuracy of the suspected pulmonary nodule region image is improved.

Description

technical field [0001] The invention relates to the field of medical imaging, in particular to an image recognition method and device. Background technique [0002] This section is intended to provide a background or context for implementations of the invention that are recited in the claims. The descriptions herein are not admitted to be prior art by inclusion in this section. [0003] Pulmonary nodules are one of the common lung diseases. Pulmonary nodules develop malignantly and will transform into lung malignant tumors. Due to the high mortality rate of lung cancer, timely treatment in the early stage of lung cancer formation has a high cure rate. Therefore, early detection of pulmonary nodules plays a vital role in preventing the formation of malignant tumors. [0004] With the development of computed tomography technology, high-resolution CT equipment can perform imaging more accurately, which lays the foundation for the identification of pulmonary nodules. At pres...

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): G06K9/62G06N3/08G06T7/00
CPCG06N3/088G06T7/0012G06T2207/30061G06F18/214
Inventor 赵大哲栗伟王军搏周庆华孟勤
Owner NEUSOFT CORP
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