SPECT thyroid imaging intelligent recognition method based on deep neural network

A technology of deep neural network and intelligent recognition, which is applied in the field of intelligent recognition of SPECT thyroid imaging based on deep neural network, can solve the problems of high proportion of experience dependence, easy missed diagnosis of lesions, and long time consumption, so as to reduce manual operation and avoid oversimulation Combined phenomenon, the effect of improving robustness

Active Publication Date: 2021-04-16
SICHUAN UNIV
View PDF11 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The purpose of the present invention is: in order to solve the technical problems of long time consumption, high proportion of experience dependence, easy misdiagnosis and misdiagnosis of lesions when doctors diagnose by reading thyroid nuclide images, the present invention provides a SPECT thyroid imaging based on deep neural network Intelligent identification method to improve the accuracy and timeliness of thyroid nuclide image diagnosis

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
  • SPECT thyroid imaging intelligent recognition method based on deep neural network
  • SPECT thyroid imaging intelligent recognition method based on deep neural network
  • SPECT thyroid imaging intelligent recognition method based on deep neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0038] Such as Figures 1 to 4 As shown, a kind of SPECT thyroid imaging intelligent identification method based on deep neural network in this embodiment comprises the following steps:

[0039] Step 1. Data acquisition: Collect SPECT thyroid imaging images, and then perform data labeling and data set division:

[0040] Step 1a, Data annotation: Divide the uptake patterns presented on SPECT thyroid imaging images into six types: diffuse increase, diffuse decrease, local increase, local decrease, uneven distribution and normal, and confirm each SPECT thyroid imaging image Based on the acquired SPECT thyroid imaging images, each SPECT thyroid imaging image is discussed by multiple professional radiologists to determine the patient’s thyroid uptake mode as one of the six types;

[0041] Step 2b, data set division: the SPECT thyroid imaging image set after data labeling is divided into training set and verification set;

[0042] Step 2, deep neural network model construction:

...

Embodiment 2

[0055] This implementation is further optimized on the basis of Embodiment 1, specifically:

[0056] In step 2b, the deep feature extraction module consists of a series of convolutional layers (Convolutional layer), batch labeling layer (Batch normalization), ReLU activation function, maximum pooling layer (Max pooling) and fully connected layer (Fullyconnected layer), It is used to extract abstract features from raw images and ROI images.

[0057] Specifically, two sub-networks are used to extract the features of the original image and the ROI image respectively, and the features extracted by the two sub-networks are represented by and respectively. These two sub-networks are composed of a convolutional layer, a batch labeling layer, and a The ReLU activation function is composed of a maximum pooling layer; the extracted features are aggregated using a feature aggregation module, and the aggregated features are then used to extract deeper abstract features using 8 serial resi...

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 an SPECT thyroid imaging intelligent identification method based on a deep neural network, and relates to the technical field of image analysis and processing. The method comprises the following three steps: data acquisition, deep neural network model construction and model verification. According to the method, the SPECT thyroid image is processed by utilizing a computer technology, a doctor is replaced to complete identification of a thyroid shooting mode, manual operation can be reduced, a consistent processing result and considerable accuracy are achieved, and integration and large-scale application are facilitated.

Description

technical field [0001] The present invention relates to the technical field of image analysis and processing, more specifically to the technical field of SPECT thyroid imaging intelligent recognition method based on deep neural network. Background technique [0002] In recent years, the incidence of thyroid disease has risen rapidly. According to the results of the "Epidemiological Survey of Thyroid Diseases in Community Residents" conducted by the Endocrine Society of the Chinese Medical Association, the prevalence rate of hyperthyroidism is 1.3%, and the prevalence rate of hypothyroidism is 6.5%. The prevalence of thyroid nodules is 18.6%, and 5%-15% of thyroid nodules are malignant, that is, thyroid cancer. It is estimated that there are 10 million patients with hyperthyroidism in my country, 90 million patients with hypothyroidism (hypothyroidism), and more than 100 million patients with thyroid nodules and thyroid cancer. At present, there are more than 200 million thyr...

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): G06T7/00G06N3/08
Inventor 章毅赵祯皮勇蔡华伟魏建安蒋丽莎
Owner SICHUAN UNIV
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