Abdominal cavity CT image peritoneal metastasis marking method based on deep convolutional neural network

A CT image, depth convolution technology, applied in the field of medical image processing, can solve the problems of low detection accuracy, difficult to repeat, and influence

Active Publication Date: 2018-12-25
NANJING UNIV +1
View PDF2 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, CT will generate a large number of images, which contain image particles similar to nodules, such as lymph nodes and blood vessels. The detection of abdominal metastases through nodules requires experien

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
  • Abdominal cavity CT image peritoneal metastasis marking method based on deep convolutional neural network
  • Abdominal cavity CT image peritoneal metastasis marking method based on deep convolutional neural network
  • Abdominal cavity CT image peritoneal metastasis marking method based on deep convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] Elaborate the realization process of the present invention below in conjunction with accompanying drawing:

[0052] The present invention uses deep convolutional neural network technology to exclude false nodules among candidate nodules. The deep convolutional neural network directly takes images as input, and can superimpose different convolutional layers and pooling layers to process image information and extract hierarchical feature representations of images. ; The lower layer of the model generates shallow feature representations such as image edges and corners, and the higher layer generates abstract feature representations with category discrimination. In the research of convolutional neural network, network depth is a crucial factor. Many studies explore the use of high-depth models, but as the network depth increases, there will be a "degeneration" problem, that is, the accuracy of the model gradually reaches saturation. And drop rapidly, at this time the model ...

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 abdominal cavity CT image peritoneal metastasis marking method based on a deep convolutional neural network. The method includes the following steps: 1) performing CT imagepreprocessing; 2) dividing the preprocessed CT image by using a watershed method to extract candidate nodules; 3) constructing a corresponding neural network input for the candidate nodules; 4) constructing a deep convolutional neural network model, using the neural network input corresponding to the marked candidate nodules to train the neural network model; and 5) predicting the probability thatthe unmarked candidate nodules are tumor nodules by using the neural network model, and finally outputting all the CT images of the determined markers, wherein the negative markers indicate that no tumor metastasis has occurred, and the positive markers indicate that peritoneal metastasis has occurred. The method can complete the automatic marking of the peritoneal metastasis of a large number ofabdominal cavity CT images, provides a basis for the diagnosis and treatment of malignant tumors, is easy to understand and simple to implement, is suitable for automatic marking of massive abdominalcavity CT images, and has good expansibility, robustness and practicability. .

Description

technical field [0001] The invention belongs to the field of medical image processing, and relates to an automatic marking method for tumor peritoneal metastasis in abdominal CT images based on a deep convolutional neural network. Image processing technology and deep learning methods are used to realize automatic marking of tumor nodules in a large number of abdominal CT images. Background technique [0002] The peritoneum is a common metastatic site of various malignant tumors in the abdominal cavity, and marking peritoneal metastasis is an important basis for evaluating the curative effect of malignant tumors. Tumor patients with peritoneal metastases develop rapidly, have poor prognosis, and are difficult to treat clinically, requiring early diagnosis and timely treatment. Marking peritoneal metastases can be accomplished through nodule detection, and abdominal CT images are an important diagnostic basis for detecting tumor nodules. However, CT will generate a large numb...

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): G16H50/20G06K9/62G06N3/04
CPCG16H50/20G06N3/045G06F18/2415
Inventor 薛玉静杜娟刘松顾庆
Owner NANJING 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