Pituitary tumor texture image grading method based on fine-grained medical image segmentation and true value discovery data amplification

A medical image and grading method technology, applied in the field of medical image processing, can solve the problems of too few medical image data sets, achieve the effect of solving difficult feature extraction, solving gray scale and assisting clinical diagnosis

Active Publication Date: 2020-01-31
XUZHOU MEDICAL UNIV
View PDF2 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0008] The technical problem to be solved by the present invention is to provide a pituitary tumor texture image classification method based on fine-grained medical image segmentation and truth val

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
  • Pituitary tumor texture image grading method based on fine-grained medical image segmentation and true value discovery data amplification
  • Pituitary tumor texture image grading method based on fine-grained medical image segmentation and true value discovery data amplification
  • Pituitary tumor texture image grading method based on fine-grained medical image segmentation and true value discovery data amplification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0062] The present invention will be further described below in conjunction with the accompanying drawings.

[0063] The principle of the density peak algorithm based on the present invention is as follows:

[0064] In the DPC algorithm, the selection of cluster centers (Cluster Centers) is its core idea. The characteristics of the selected cluster centers are that the local density and distance are as large as possible, and have a relatively large distance from any point with a higher density. distance. Consider the data set to be clustered S={χ i}N i=1, (N∈N+), according to the above two features, the algorithm for each data point χ in the data set S i Define the local density ρ for it i and the relative distance δ i . The distance d between these two variables and the data point ij relevant.

[0065] Data point χ i The local density of is defined as:

[0066]

[0067] which function

[0068]

[0069] The parameter dc>0 in the formula is the cut-off distance,...

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 pituitary tumor texture image grading method based on fine-grained medical image segmentation and true value discovery data amplification. The pituitary tumor texture image grading method comprises the following steps: 1, optimizing fruit fly-density peak clustering medical image segmentation based on fine granularity; 2, amplifying pituitary adenoma data discovered on the basis of true values; and 3, grading based on the pituitary adenoma texture images in the step 1 and the step 2. According to the pituitary tumor texture image grading method, the medical image is accurately segmented through fusion of a fine-grained division algorithm and an FOA-DPC algorithm; medical image data amplification based on a true value discovery theory is also realized, and the problem of few available medical image data sets is solved. The pituitary tumor texture image grading method combines a KFOA-DPC segmentation algorithm with deep learning, so as to solve the problems thatthe gray scale of a dicom format image is numerous and jumbled, and features are not easy to extract, realize classification of pituitary adenoma texture softness and toughness and assist clinical diagnosis.

Description

technical field [0001] The invention relates to a pituitary tumor texture image classification method, in particular to a pituitary tumor texture image classification method based on fine-grained medical image segmentation and truth value discovery data amplification, and belongs to the technical field of medical image processing. Background technique [0002] Pituitary tumors are a group of tumors arising from the anterior and posterior pituitary glands and residual epithelial cells of the craniopharynx. They occur frequently, accounting for about 10% of intracranial tumors. The soft and tough texture of pituitary tumors affects the approach and surgical plan of surgical treatment. At present, with the development of minimally invasive technology, minimally invasive surgery via transsphenoidal approach has become the preferred treatment method, but it is only suitable for patients with soft texture. Pituitary tumors, and for a small number of pituitary tumors with tough or ...

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): G06T7/10G06K9/62
CPCG06T7/10G06N3/006G06T2207/20081G06T2207/20084G06T2207/30016G06T2207/30096G06F18/23213
Inventor 朱红徐凯方谦昊王琳吴佳伟姜代红
Owner XUZHOU 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