A 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. The convolutional neural network of deep learning of artificial intelligence realizes the clinical diagnosis of amnesiac mild cognitive impairment and the clinical diagnosis of normal elderly group. According to the classification of the three cases of Alzheimer's disease diagnosed on the Internet, it is determined by using the imaging data of the normal elderly group, the clinically diagnosed amnestic mild cognitive impairment and the clinically diagnosed Alzheimer's disease. For the training set, verification set and test set of deep learning of artificial intelligence, two-dimensional slices can be selected to convert the three-dimensional data of nuclear magnetic resonance into two-dimensional data.

Description

technical field [0001] The invention relates to a medical image processing device and method using a convolutional neural network. 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 ...

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