Small data set esophageal cancer tumor target image automatic sketching method based on improved spatial pyramid model

A space pyramid, esophageal cancer technology, applied in image data processing, biological neural network model, image enhancement and other directions, can solve the problem of automatic delineation of difficult esophageal cancer tumor target area images, and achieve the effect of improving segmentation effect and accurate automatic segmentation.

Active Publication Date: 2022-02-08
ANHUI MEDICAL UNIV +1
View PDF9 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to solve the defect in the prior art that it is difficult to automatically delineate esophageal cancer tumor target images of small data sets, and to provide an automatic delineation method for small data set esophageal cancer tumor target images based on an improved spatial pyramid model to solve the above problems

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
  • Small data set esophageal cancer tumor target image automatic sketching method based on improved spatial pyramid model
  • Small data set esophageal cancer tumor target image automatic sketching method based on improved spatial pyramid model
  • Small data set esophageal cancer tumor target image automatic sketching method based on improved spatial pyramid model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0087] In order to have a further understanding and understanding of the structural features of the present invention and the achieved effects, the preferred embodiments and accompanying drawings are used for a detailed description, as follows:

[0088] Such as figure 1 As shown, a method for automatically delineating tumor target area images of esophageal cancer in a small data set based on an improved spatial pyramid model according to the present invention comprises the following steps:

[0089] The first step is the acquisition and preprocessing of the small data training set: obtain the CT image data of patients with esophageal cancer who have undergone intensity-modulated radiotherapy, and export the tumor target area as a Mask file; perform normalization and data enhancement preprocessing on the CT image data . The specific steps are as follows:

[0090] (1) Read the original CT image in Dicom format.

[0091] (2) Generate the Mask image of the tumor target area of ​...

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 relates to a small data set esophageal cancer tumor target image automatic sketching method based on an improved spatial pyramid model. Compared with the prior art, the defect that automatic sketching of small-data-set esophageal cancer tumor target images is difficult is overcome. The method comprises the following steps: obtaining and preprocessing a small data training set; establishing an esophageal cancer tumor target image automatic sketching model; training the esophageal cancer tumor target image automatic sketching model; acquiring an image to be sketched; and obtaining an esophageal cancer tumor target region image sketching result. According to the method, the problem of overfitting caused by a small data set and the problems of low segmentation precision and the like caused by small tumor target regions and variable shapes of esophageal cancer CT images can be effectively solved, so that the segmentation effect of the target region is improved, the esophageal cancer tumor target regions are segmented more accurately and automatically, and the esophageal cancer tumor target region sketching is more universal.

Description

technical field [0001] The invention relates to the technical field of medical image processing, in particular to a method for automatically delineating images of tumor target areas of esophageal cancer in small data sets based on an improved spatial pyramid model. Background technique [0002] Esophageal cancer (esophageal cancer, EC) is a highly aggressive malignant tumor, and its incidence is on the rise worldwide, especially in China. Currently, the 5-year survival rate is only 15% to 25%. Surgical resection is the treatment of choice for esophageal cancer, but the recurrence rate after radical resection is still high. Local recurrence is the main reason for treatment failure, and postoperative radiotherapy is the main treatment to control local recurrence and prolong survival. [0003] The basic principle of computer tomography (Computed Tomography, CT) is image reconstruction. According to the characteristic of X-ray absorption of various human tissues (including nor...

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): G06T7/11G06T7/73G16H30/20G06N3/04
CPCG06T7/11G06T7/73G16H30/20G06T2207/10081G06T2207/20016G06T2207/30096G06T2207/20081G06T2207/20084G06N3/045
Inventor 黄晓雨黄勇汪琦张梅吴齐兵
Owner ANHUI MEDICAL 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