Medical image processing device and method using convolutional neural network

Abstract

The invention relates to a medical image processing device and method using a convolutional neural network. A data enhancement technology and a migration technology are utilized; supervised learning of a convolutional neural network for deep learning of artificial intelligence is achieved by using one to twenty two-dimensional slices passing through a coronal plane of a hippocampus of image data of nuclear magnetic resonance imaging of a three-dimensional skull of a subject; one or two two-dimensional images passing through the coronal plane of the hippocampus of the three-dimensional skull nuclear magnetic resonance imaging image data of the subject is selected as tested images so as to realize three-class distinguishing and identification of the normal senile group, the forgetting type mild cognitive impairment and the Alzheimer's disease.

Description

technical field [0001] The invention relates to an artificial intelligence medical image processing device and method. Processing and analysis of MRI image data of the whole brain and / or hippocampus using cranial magnetic resonance imaging based on deep learning convolutional neural networks, in particular, involving cranial magnetic resonance imaging based on deep learning convolutional neural networks A device and method for pairwise discrimination between Alzheimer's disease, amnestic mild cognitive impairment, and normal elderly groups using magnetic resonance imaging of the whole brain and / or hippocampus. 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 catego...

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

Images