An artificial intelligence-based auxiliary diagnosis system for early cancer

An auxiliary diagnosis and artificial intelligence technology, applied in the field of image analysis, can solve the problems that it is difficult to achieve the training effect and cannot guarantee the accuracy of artificial intelligence algorithm diagnosis, so as to achieve the effect of improving user experience, improving training effect and reducing time

Active Publication Date: 2022-02-15
CHONGQING UNIV CANCER HOSPITAL
View PDF5 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Due to the differences between the recognition of artificial intelligence algorithms and human visual recognition, artificial intelligence algorithms may not necessarily recognize pictures that are easy for humans to recognize. If the format of the sample image is difficult for artificial intelligence algorithms to recognize, then no matter how many sample images are used for training, it is difficult to achieve the ideal training effect, and the accuracy of artificial intelligence algorithm diagnosis cannot be guaranteed

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
  • An artificial intelligence-based auxiliary diagnosis system for early cancer

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] like figure 1 As shown, an early cancer-assisted diagnostic system based on artificial intelligence, including image acquisition modules, model build modules, and diagnostic modules.

[0037] The image acquisition module is used to obtain a sample image of the labeled digestive trailer, preprocessing and randomly sort the sample image, generates a training image set, and normalizes all sample images within the training image set. In this implementation, normalization means normalizing the sample image into a DICOM format, NIFTI format, or the original binary format.

[0038] In this embodiment, the sample image includes one or more cancer categories in early esophageal cancer, early gastric cancer, early colon cancer, each cancer category corresponds to morphological categories and infiltration depth subcategories; mandatory sample images And the sample image of the wet deep subclass is not less than 5,000, and the pretreatment includes one or more of cut, rotation, stretch...

Embodiment 2

[0051] An early cancer assist diagnostic system based on artificial intelligence, and the difference from the embodiment is that the construction unit outputs a convolutional neural network model, the image acquisition module marks the adjusted pre-process manner as a valid pre-processing method. The image acquisition module is also used to obtain the diagnostic image to be preprocessed by the effective pre-treatment method after obtaining the image of the digestive tract, and transmits the pre-processed to the diagnostic module. The diagnostic module is used to receive the diagnostic image to be diagnosed with the diagnostic image based on the training successful convolutional neural network model to determine the judgment result. In this embodiment, the judgment result is normal or early cancer.

[0052] The diagnostic image is pretreated by the effective pre-processing method, so that the image to be diagnosed to meet the input requirements of the convolutional neural network m...

Embodiment 3

[0054] An early cancer assist diagnostic system based on artificial intelligence, and the difference between the second embodiment is that the evaluation module and environmental adjustment module are also included;

[0055] The evaluation module is used to obtain a doctor's judgment result, compare the judgment result of the medical students in the image to be diagnosed, and the judgment result of the diagnostic module is compared. If it is unanimous, if it is inconsistent, the evaluation module outputs request judgment information; the current convolutional neural network model is still mainly Auxiliary diagnosis, reducing the probability of misdiagnosis through dual verification while improving the doctor's diagnostic efficiency.

[0056] The evaluation module is also used to receive the judicial information; the judging information has been judged to be the correct or convolutional neural network model correctly. When the judgment information is inconsistent, the evaluation mo...

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 present invention relates to the technical field of image analysis, and specifically discloses an artificial intelligence-based auxiliary diagnosis system for early cancer, including an image acquisition module, which is used to acquire sample images of digestive tract endoscopes with labels, and preprocess and analyze the sample images. Randomly sorted to generate a training image set; the model building module is used to construct a convolutional neural network model, and iteratively trains the convolutional neural network model based on the training image set, and then performs a test, and outputs a successfully trained convolutional neural network after the test is completed A network model; a diagnosis module, which is used to obtain images to be diagnosed from the endoscope of the digestive tract, judge the images to be diagnosed based on the successfully trained convolutional neural network model, and output the judgment results. Adopting the technical scheme of the invention can improve the effectiveness of training.

Description

Technical field [0001] The present invention relates to the field of image analysis, and more particularly to an early cancer-assisted diagnostic system based on artificial intelligence. Background technique [0002] Early-occurrence in digestive tract cancer is very important in practical significance. However, there is more gas distribution of gastrointestinal gas, smaller lesions, stronger, and early cancer morphology, surface microstructure, surface microvascular and inflammatory and repair resistance, resulting in the pathological characteristics of digestive tracer Division, early symptoms are not easy to find. [0003] At present, the diagnosis of digestive tract cancer is mainly through digestive optical lenses and image sensors to collect images in the human body, and transmitted collected images to the display terminal, for medical staff to view. When the digestive tractue image provides more detailed, accurate diagnostic information, it also adds a work burden to the d...

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 Patents(China)
IPC IPC(8): G06T7/00
CPCG06T7/0012G06T2207/10068G06T2207/20081G06T2207/20084G06T2207/30096
Inventor 陈伟庆柴毅
Owner CHONGQING UNIV CANCER HOSPITAL
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