Intestinal tumor microscopic hyperspectral image processing method based on convolutional neural network

A convolutional neural network and hyperspectral image technology, applied in the field of microscopic hyperspectral image processing of intestinal tumors based on convolutional neural network, can solve the problems of inconvenient practical application, increased computing cost, and increased analysis volume, achieving Effects of removing noise pollution, improving accuracy, and facilitating understanding

Inactive Publication Date: 2019-09-27
隋心
View PDF1 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0006] However, when the above-mentioned technical solution is actually used, there are still many shortcomings. For example, the hyperspectral image in the above-mentioned solution is analyzed in batches. As the number of bands in the hyperspectral image increases, the internal data The amo

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

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0028] The present invention provides a method for processing a microscopic hyperspectral image of an intestinal tumor based on a convolutional neural network. The hyperspectral image processing method includes the following steps:

[0029] Step 1: Obtain the initial hyperspectral image, and irradiate the patient's gastrointestinal tumor with relevant equipment, where the relevant equipment uses an imaging spectrometer, and maintain a relatively quiet environment during the process of microscopic hyperspectral image acquisition. Reducing these noises as much as possible not only affects the visual effect of the image, but also affects its subsequent processing and application, so as to obtain the hyperspectral initial image at the patient's gastrointestinal tumor location, and perform related operations to obtain multiple sets of hyperspectral initial images;

[0030] Step 2: Obtain the first sub-image, and perform segmentation processing on the hyperspectral initial image coll...

Embodiment 2

[0037] The present invention provides a method for processing a microscopic hyperspectral image of an intestinal tumor based on a convolutional neural network. The hyperspectral image processing method includes the following steps:

[0038] Step 1: Obtain the initial hyperspectral image, and irradiate the patient's gastrointestinal tumor with relevant equipment, where the relevant equipment uses an imaging spectrometer, and maintain a relatively quiet environment during the process of microscopic hyperspectral image acquisition. Reducing these noises as much as possible not only affects the visual effect of the image, but also affects its subsequent processing and application, so as to obtain the hyperspectral initial image at the patient's gastrointestinal tumor location, and perform related operations to obtain multiple sets of hyperspectral initial images;

[0039] Step 2: Obtain the first sub-image, and perform segmentation processing on the hyperspectral initial image coll...

Embodiment 3

[0046] The present invention provides a method for processing a microscopic hyperspectral image of an intestinal tumor based on a convolutional neural network. The hyperspectral image processing method includes the following steps:

[0047] Step 1: Obtain the initial hyperspectral image, and irradiate the patient's gastrointestinal tumor with relevant equipment, where the relevant equipment uses an imaging spectrometer, and maintain a relatively quiet environment during the process of microscopic hyperspectral image acquisition. Reducing these noises as much as possible not only affects the visual effect of the image, but also affects its subsequent processing and application, so as to obtain the hyperspectral initial image at the patient's gastrointestinal tumor location, and perform related operations to obtain multiple sets of hyperspectral initial images;

[0048] Step 2: Obtain the first sub-image, and perform segmentation processing on the hyperspectral initial image coll...

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 intestinal tumor microscopic hyperspectral image processing method based on a convolutional neural network, and particularly relates to the technical field of gastrointestinal tumor detection, and the hyperspectral image processing method comprises the following steps: 1, obtaining a hyperspectral initial image, and irradiating the gastrointestinal tumor position of a patient by using related equipment. According to the invention, the hyperspectral initial image is segmented; a second sub-image is obtained by using the first sub-image, the feature points in each section of the second sub-image is extracted in a convolutional neural network manner; a third sub-image is constructed, and the feature points are integrated in each group of third sub-images; therefore, the hyperspectral target image formed by combining the feature points is obtained, the hyperspectral initial image can be effectively processed, the hyperspectral initial image is more visual and concise, the processing efficiency of a large amount of data in the hyperspectral initial image is improved, and meanwhile the disease diagnosis accuracy of people is improved.

Description

technical field [0001] The invention relates to the technical field of gastrointestinal tumor detection, and more specifically, the invention relates to a method for processing microscopic hyperspectral images of intestinal tumors based on a convolutional neural network. Background technique [0002] Gastrointestinal tumors, benign and malignant tumors that occur in the small intestine and large intestine. Clinical manifestations vary according to the nature and location of tumor occurrence. In general, benign tumors can be asymptomatic or have very mild symptoms. Some malignant tumors have no obvious symptoms in the early stage, which affects diagnosis, treatment and prognosis. Among intestinal tumors, the incidence of tumors in the small intestine is lower than those in the esophagus, stomach, and large intestine. The clinical manifestations of patients are anemia, weight loss, increased stool frequency, deformation, and mucus and bloody stools. Sometimes an abdominal ...

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): G06T7/00G06T5/20G06T5/00
CPCG06T5/001G06T5/20G06T7/0012G06T2207/10056G06T2207/20084G06T2207/30096
Inventor 隋心孔庆斌
Owner 隋心
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