Corneal ulcer classification detection method and system based on neural network model

A neural network model, corneal ulcer technology, applied in biological neural network models, neural learning methods, neural architecture, etc., can solve problems such as differences in judgment results and time spent
CN112712122APending Publication Date: 2021-04-27HANGZHOU DIANZI UNIV
0 Cites 5 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
HANGZHOU DIANZI UNIV
Publication Date
2021-04-27

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention discloses a corneal ulcer classification detection method and system based on a neural network model, and relates to the field of corneal ulcer classification detection and disease discrimination. The method mainly comprises the following steps: collecting cornea images of a testee after fluorescence staining at multiple angles by utilizing a plurality of cameras; making and adding a mask to the cornea image, and extracting an effective part; further processing the extracted effective cornea image, and taking the effective cornea image as network input; using the Inception-ResNet-V2 neural network model which is trained by a large amount of effective data to complete preliminary classification of spotting type corneal ulcer, spotting sheet-shaped mixed type corneal ulcer and sheet-shaped corneal ulcer; and processing cornea image detection results of different angles by using the trained support vector machine, and making a final classification judgment. The system provided by the invention can realize high-accuracy corneal ulcer type detection, and data can be uploaded to the cloud server for further analysis.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The invention relates to the technical field of classification detection and disease discrimination of corneal ulcers, in particular to a method and system for classification detection of corneal ulcers based on a neural network model. Background technique

[0002] Corneal ulcers are the most common symptom of corneal disease. As the transparent film at the front of the eyeball, the cornea is often exposed to the air and has many chances of contacting germs, thus increasing the prevalence of corneal ulcers. In addition, vitamin A deficiency, chemical burns, long-term use of contact lenses, dry eyes or herpes can also cause corneal ulcers. Corneal ulcers are very harmful to the human body, especially the visual function. Without timely and correct treatment, it will lead to vision loss and even blindness, which is called corneal blindness in medicine.

[0003] With the gradual improvement of the medical level, more and more effective treatment options...

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