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

A kind of medical image processing device and method based on autoencoder

A self-encoder and processing device technology, applied in medical imaging, healthcare informatics, instruments, etc., can solve problems such as unavailable nuclear magnetic resonance imaging, difficult technical solutions, and huge computational load

Active Publication Date: 2021-11-12
GENERAL HOSPITAL OF PLA +1
View PDF3 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, this document only processes the 3D voxel data of the MRI of the head, and the technical solution used is a 3D convolutional autoencoder
Since it is necessary to process all the 3-dimensional voxel data of the magnetic resonance imaging of each subject's head, this technical solution requires a huge amount of calculation, even if a high-performance computer or a high-performance computer cluster is used, the technical solution It is also difficult or even impossible to use clinically
In addition, the image data of the MRI of the clinical common scanning head is the image data of 20 to 40 two-dimensional slices, the method in the above-mentioned arXiv:1607.00556v1 document cannot be used for the MRI of the clinical common scanning head Imaging image data

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
  • A kind of medical image processing device and method based on autoencoder
  • A kind of medical image processing device and method based on autoencoder
  • A kind of medical image processing device and method based on autoencoder

Examples

Experimental program
Comparison scheme
Effect test

Embodiment approach 1

[0028] Embodiment 1 Utilize the data of the Alzheimer's Disease Neuroimaging Initiative (ADNI for short) in the United States to realize the technical solution of the present invention for computer-aided recognition of the image data of the MRI image data of the cranium and the image data of the whole brain . Download cranial MRIs of clinically confirmed Alzheimer's disease (AD), amnestic mild cognitive impairment (MCI) and normal aged group (NC) from the official website of the Alzheimer's Disease Neuroimaging Program in the United States image data,

[0029] The data of the Alzheimer's disease neuroimaging project in the United States, 3013 scan results (scans), 321 subjects (subject), can be divided into training set, verification set and test set

[0030] The condition of the training set

[0031]

[0032] The case of the validation set

[0033]

[0034] The case of the test set

[0035]

[0036] Whole-brain three-dimensional data of the above-mentioned crania...

Embodiment approach 2

[0045] Embodiment 2 Utilize the data of the Alzheimer's Disease Neuroimaging Initiative (ADNI for short) in the United States to realize the technical solution of the present invention for computer-aided recognition of the image data of the MRI image data of the cranium and the image data of the whole brain . Download cranial MRIs of clinically confirmed Alzheimer's disease (AD), amnestic mild cognitive impairment (MCI) and normal aged group (NC) from the official website of the Alzheimer's Disease Neuroimaging Program in the United States image data,

[0046] The data of the Alzheimer's disease neuroimaging project in the United States, 3013 scan results (scans), 321 subjects (subject), can be divided into training set, verification set and test set

[0047] The condition of the training set

[0048]

[0049] The case of the validation set

[0050]

[0051] The case of the test set

[0052]

[0053] Whole-brain three-dimensional data of the above-mentioned crania...

Embodiment approach 3

[0064] Embodiment 3 Utilize the data of the Alzheimer's Disease Neuroimaging Initiative (ADNI for short) in the United States to realize the technical solution of the present invention for computer-aided recognition of the image data of the MRI image data of the cranium and the image data of the whole brain . Download cranial MRIs of clinically confirmed Alzheimer's disease (AD), amnestic mild cognitive impairment (MCI) and normal aged group (NC) from the official website of the Alzheimer's Disease Neuroimaging Program in the United States image data,

[0065] The data of the Alzheimer's disease neuroimaging project in the United States, 3013 scan results (scans), 321 subjects (subject), can be divided into training set, verification set and test set

[0066] The condition of the training set

[0067]

[0068] The case of the validation set

[0069]

[0070] The case of the test set

[0071]

[0072] Whole-brain three-dimensional image data of the above-mentioned ...

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 a medical image processing device and method based on an autoencoder, and relates to a two-dimensional autoencoder using deep learning of artificial intelligence to achieve the normal elderly group, clinically diagnosed as amnesiac mild cognitive impairment and in the Three categories of clinically diagnosed Alzheimer's disease were carried out using a three-category classification method, using the MRI of the normal elderly group, clinically diagnosed amnestic mild cognitive impairment and clinically diagnosed Alzheimer's disease The resonance image data determines the training set, verification set and test set of the deep learning of artificial intelligence, and the three-dimensional data of nuclear magnetic resonance can be converted into two-dimensional data by selecting two-dimensional slices.

Description

technical field [0001] The present invention relates to a medical image processing device and method based on an autoencoder, in particular, to a deep learning-based two-dimensional autoencoder that utilizes cranial nuclear magnetic resonance imaging to perform Alzheimer's disease on the whole brain and / or hippocampus. An image analysis device and method for pairwise discrimination between patients with disease, amnestic mild cognitive impairment, and normal elderly groups. Background technique [0002] Alzheimer's disease is a neurodegenerative disease. Existing research work has confirmed that in the MRI image files of the head, although there are individual differences in the MRI image data of each subject, in the sense of biostatistics, Alzheimer's disease, Alzheimer's disease, Amnestic mild cognitive impairment and the three categories of normal elderly group exist differences between the three categories of MRI imaging data. The deep learning method of machine learni...

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): G16H30/00G06K9/62
CPCG06F18/214
Inventor 张熙周波郭艳娥冯枫安宁豫姚洪祥罗亚川樊茂华赵思远
Owner GENERAL HOSPITAL OF PLA