Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Computerized auxiliary diagnosing method for malignant tumor in early stage based on deep learning algorithm

A computer-aided, malignant tumor technology, applied in computing, image data processing, instruments, etc., can solve the problems of high time-consuming and low precision, and achieve the effect of reducing segmentation time, improving segmentation accuracy, and reducing the workload of doctors

Inactive Publication Date: 2017-10-10
HEFEI UNIV OF TECH
View PDF0 Cites 74 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a computer-aided early diagnosis method for malignant tumors based on a deep learning algorithm to solve the problems of low precision and high time-consuming in the prior art prostate tissue segmentation method

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
  • Computerized auxiliary diagnosing method for malignant tumor in early stage based on deep learning algorithm
  • Computerized auxiliary diagnosing method for malignant tumor in early stage based on deep learning algorithm
  • Computerized auxiliary diagnosing method for malignant tumor in early stage based on deep learning algorithm

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment

[0035] exist figure 1 Among them, the computer-aided early diagnosis technology of malignant tumors based on the deep learning algorithm is mainly divided into two stages: training and testing. Its steps include:

[0036] (1), select 600 prostate MRI images of 50 patients, and expand them to 8000 as a training data set, including manual segmentation of real images of each patient's prostate tissue, and the edges of the patient's magnetic resonance tissue are different .

[0037] (2) Input the training set image into the convolutional neural network for training, and the convolutional layer extracts the advanced features of the image rich in target detail information.

[0038] (3) In the downsampling layer, several adjacent features in the feature map of the previous layer are combined to reduce the resolution of the feature.

[0039] (4) Reconstruct the input target size through the deconvolution network, and finally generate a classification probability map with the same s...

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 a computerized auxiliary diagnosing method for malignant tumor in early stage based on deep learning algorithm. According to the invention, a deep convolution neural network is used to extract the high-level characteristics of an image layer by layer so that the obtained characteristic dimensions become smaller and smaller. To realize the dimension matching between an outputted probability predicting image and a pre-segmented image, the method uses the reverse convolution network to expand the dimensions of the characteristic image so as to obtain a dimension-consistent probability predicting image. The network generated probability predicting image extracts the binarization of the predicting image through the training of a softmax classifier to finally obtain the segmentation result of the prostate tissue. To some extent, the method effectively increases the accuracy and efficiency for doctors to diagnose prostate diseases.

Description

technical field [0001] The invention relates to the technical field of computer neural networks, in particular to a method for computer-aided early diagnosis of malignant tumors based on deep learning algorithms. Background technique [0002] Prostate cancer is one of the major problems affecting the health of older men. Early diagnosis and early treatment are the key to improving the survival rate and reducing the mortality rate of prostate cancer patients, and the segmentation of lesion tissue is an indispensable part of prostate cancer diagnosis. For the detection and treatment planning of prostate lesions, doctors first need to outline the outline of the prostate tissue, distinguish the prostate from the surrounding organs, and then decide to adopt corresponding treatment methods. However, this process currently mainly relies on physicians to complete it manually, which is a very time-consuming process, and the segmentation results vary from person to person. At the sa...

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): G06T7/11
CPCG06T7/11G06T2207/10088G06T2207/20081G06T2207/20084G06T2207/30081G06T2207/30096
Inventor 詹曙季栋杨福猛
Owner HEFEI UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com