Unlock instant, AI-driven research and patent intelligence for your innovation.

AI prediction method, apparatus and equipment for cerebral infarction, and storage medium

A prediction method and cerebral infarction technology, applied in the field of information processing, can solve problems such as stroke and inability to provide assistance to patients

Inactive Publication Date: 2019-01-25
深圳市医未医疗科技有限公司
View PDF6 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] When implementing the embodiment of the present invention, the inventor found that there is no AI prediction technology for cerebral infarction in the prior art. Because the onset of cerebral infarction is relatively rapid, most of them have no prodromal symptoms, and the focal neurological signs can be detected within a few minutes to several hours. Reached the peak, and often manifested as complete stroke, if there is no technology that can predict cerebral infarction, it is impossible to provide timely assistance to patients

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
  • AI prediction method, apparatus and equipment for cerebral infarction, and storage medium
  • AI prediction method, apparatus and equipment for cerebral infarction, and storage medium
  • AI prediction method, apparatus and equipment for cerebral infarction, and storage medium

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0052] See figure 1 , figure 1 It is a schematic diagram of the AI ​​prediction device for cerebral infarction provided by Embodiment 1 of the present invention, which is used to implement the AI ​​prediction method for cerebral infarction provided by the embodiment of the present invention, such as figure 1 As shown, the AI ​​prediction device for cerebral infarction includes: at least one processor 11, such as CPU, at least one network interface 14 or other user interface 13, memory 15, at least one communication bus 12, and the communication bus 12 is used to realize the communication between connections. Wherein, the user interface 13 may optionally include a USB interface, other standard interfaces, and a wired interface. The network interface 14 may optionally include a Wi-Fi interface and other wireless interfaces. The memory 15 may include a high-speed RAM memory, and may also include a non-volatile memory (non-volatile memory), such as at least one disk memory. Th...

Embodiment 2

[0062] figure 2 It is a schematic flowchart of an AI prediction method for cerebral infarction provided by Embodiment 2 of the present invention.

[0063] An AI prediction method for cerebral infarction, comprising the following steps:

[0064] S11. Obtain a training sample; wherein, the training sample includes an original CT image and a corresponding cerebral infarction label;

[0065] S12. Obtain the trained convolutional neural network based on the encoding and decoding architecture; wherein, the trained convolutional neural network based on the encoding and decoding architecture performs convolution neural network on the training samples and the initial convolutional neural network. Network training, using dice coefficients to evaluate prediction results during training, and performing backpropagation on the initial convolutional network according to the evaluation results.

[0066] S13. Preprocessing the CT image to be predicted to obtain a test sample;

[0067] S14....

Embodiment 3

[0101] see Figure 4 , a schematic structural diagram of the AI ​​prediction device for cerebral infarction provided by the third embodiment of the present invention;

[0102] An AI prediction device for cerebral infarction, comprising:

[0103] A training sample acquisition module 31, configured to acquire a training sample; wherein, the training sample includes an original CT image and a corresponding cerebral infarction label;

[0104] The network acquisition module 32 is used to obtain the trained convolutional neural network based on the encoding and decoding architecture; wherein, the trained convolutional neural network based on the encoding and decoding architecture passes through the training sample and the initial convolutional neural network. The network performs convolutional neural network training, uses dice coefficients to evaluate prediction results during training, and performs backpropagation on the initial convolutional network according to the evaluation r...

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 AI prediction method for cerebral infarction. Firstly, a training sample is obtained, wherein the training sample comprises an original CT image and a corresponding cerebralinfarction tag; then the trained convolutional neural network based on coding and decoding architecture is acquired, wherein, the trained convolutional neural network based on the coding and decodingstructure performs convolutional neural network training through the training sample and the initial convolutional neural network, and the dice coefficient is used to evaluate the prediction result during the training, and the initial convolutional network is backpropagated according to the evaluation result; CT images to be predicted are preprocessed to obtain test samples; and, according to thetrained convolutional neural network based on the coding and decoding architecture, the cerebral infarction prediction is performed on the CT image to be predicted, and the prediction result is obtained. Through the image recognition of the convolutional neural network based on the encoding and decoding architecture, whether there is a cerebral infarction and an area of the cerebral infarction can be predicted.

Description

technical field [0001] The present invention relates to the technical field of information processing, and in particular to an AI prediction method, device, equipment and storage medium for cerebral infarction. Background technique [0002] Cerebral infarction, formerly known as cerebral infarction, also known as cerebral ischemic stroke, refers to the localized ischemic necrosis or softening of brain tissue caused by cerebral blood supply disorder, ischemia and hypoxia. The common clinical types of cerebral infarction include cerebral thrombosis, lacunar infarction, and cerebral embolism. Cerebral infarction accounts for 80% of all strokes. Bringing great pain and a heavy burden. [0003] At present, the identification method of cerebral infarction is generally to go to the hospital for CT examination, MRI examination, routine examination or special examination; when performing CT examination, CT shows that the infarction focus is low density, and the location, shape and s...

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): A61B6/03
CPCA61B6/032A61B6/501A61B6/5205A61B6/5211
Inventor 王思伦
Owner 深圳市医未医疗科技有限公司