Cargando…
3D Compressed Convolutional Neural Network Differentiates Neuromyelitis Optical Spectrum Disorders From Multiple Sclerosis Using Automated White Matter Hyperintensities Segmentations
BACKGROUND: Magnetic resonance imaging (MRI) has a wide range of applications in medical imaging. Recently, studies based on deep learning algorithms have demonstrated powerful processing capabilities for medical imaging data. Previous studies have mostly focused on common diseases that usually have...
Autores principales: | , , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Frontiers Media S.A.
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7786373/ https://www.ncbi.nlm.nih.gov/pubmed/33424635 http://dx.doi.org/10.3389/fphys.2020.612928 |
_version_ | 1783632611785048064 |
---|---|
author | Wang, Zhuo Yu, Zhezhou Wang, Yao Zhang, Huimao Luo, Yishan Shi, Lin Wang, Yan Guo, Chunjie |
author_facet | Wang, Zhuo Yu, Zhezhou Wang, Yao Zhang, Huimao Luo, Yishan Shi, Lin Wang, Yan Guo, Chunjie |
author_sort | Wang, Zhuo |
collection | PubMed |
description | BACKGROUND: Magnetic resonance imaging (MRI) has a wide range of applications in medical imaging. Recently, studies based on deep learning algorithms have demonstrated powerful processing capabilities for medical imaging data. Previous studies have mostly focused on common diseases that usually have large scales of datasets and centralized the lesions in the brain. In this paper, we used deep learning models to process MRI images to differentiate the rare neuromyelitis optical spectrum disorder (NMOSD) from multiple sclerosis (MS) automatically, which are characterized by scattered and overlapping lesions. METHODS: We proposed a novel model structure to capture 3D MRI images’ essential information and converted them into lower dimensions. To empirically prove the efficiency of our model, firstly, we used a conventional 3-dimensional (3D) model to classify the T2-weighted fluid-attenuated inversion recovery (T2-FLAIR) images and proved that the traditional 3D convolutional neural network (CNN) models lack the learning capacity to distinguish between NMOSD and MS. Then, we compressed the 3D T2-FLAIR images by a two-view compression block to apply two different depths (18 and 34 layers) of 2D models for disease diagnosis and also applied transfer learning by pre-training our model on ImageNet dataset. RESULTS: We found that our models possess superior performance when our models were pre-trained on ImageNet dataset, in which the models’ average accuracies of 34 layers model and 18 layers model were 0.75 and 0.725, sensitivities were 0.707 and 0.708, and specificities were 0.759 and 0.719, respectively. Meanwhile, the traditional 3D CNN models lacked the learning capacity to distinguish between NMOSD and MS. CONCLUSION: The novel CNN model we proposed could automatically differentiate the rare NMOSD from MS, especially, our model showed better performance than traditional3D CNN models. It indicated that our 3D compressed CNN models are applicable in handling diseases with small-scale datasets and possess overlapping and scattered lesions. |
format | Online Article Text |
id | pubmed-7786373 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2020 |
publisher | Frontiers Media S.A. |
record_format | MEDLINE/PubMed |
spelling | pubmed-77863732021-01-07 3D Compressed Convolutional Neural Network Differentiates Neuromyelitis Optical Spectrum Disorders From Multiple Sclerosis Using Automated White Matter Hyperintensities Segmentations Wang, Zhuo Yu, Zhezhou Wang, Yao Zhang, Huimao Luo, Yishan Shi, Lin Wang, Yan Guo, Chunjie Front Physiol Physiology BACKGROUND: Magnetic resonance imaging (MRI) has a wide range of applications in medical imaging. Recently, studies based on deep learning algorithms have demonstrated powerful processing capabilities for medical imaging data. Previous studies have mostly focused on common diseases that usually have large scales of datasets and centralized the lesions in the brain. In this paper, we used deep learning models to process MRI images to differentiate the rare neuromyelitis optical spectrum disorder (NMOSD) from multiple sclerosis (MS) automatically, which are characterized by scattered and overlapping lesions. METHODS: We proposed a novel model structure to capture 3D MRI images’ essential information and converted them into lower dimensions. To empirically prove the efficiency of our model, firstly, we used a conventional 3-dimensional (3D) model to classify the T2-weighted fluid-attenuated inversion recovery (T2-FLAIR) images and proved that the traditional 3D convolutional neural network (CNN) models lack the learning capacity to distinguish between NMOSD and MS. Then, we compressed the 3D T2-FLAIR images by a two-view compression block to apply two different depths (18 and 34 layers) of 2D models for disease diagnosis and also applied transfer learning by pre-training our model on ImageNet dataset. RESULTS: We found that our models possess superior performance when our models were pre-trained on ImageNet dataset, in which the models’ average accuracies of 34 layers model and 18 layers model were 0.75 and 0.725, sensitivities were 0.707 and 0.708, and specificities were 0.759 and 0.719, respectively. Meanwhile, the traditional 3D CNN models lacked the learning capacity to distinguish between NMOSD and MS. CONCLUSION: The novel CNN model we proposed could automatically differentiate the rare NMOSD from MS, especially, our model showed better performance than traditional3D CNN models. It indicated that our 3D compressed CNN models are applicable in handling diseases with small-scale datasets and possess overlapping and scattered lesions. Frontiers Media S.A. 2020-12-23 /pmc/articles/PMC7786373/ /pubmed/33424635 http://dx.doi.org/10.3389/fphys.2020.612928 Text en Copyright © 2020 Wang, Yu, Wang, Zhang, Luo, Shi, Wang and Guo. http://creativecommons.org/licenses/by/4.0/ This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms. |
spellingShingle | Physiology Wang, Zhuo Yu, Zhezhou Wang, Yao Zhang, Huimao Luo, Yishan Shi, Lin Wang, Yan Guo, Chunjie 3D Compressed Convolutional Neural Network Differentiates Neuromyelitis Optical Spectrum Disorders From Multiple Sclerosis Using Automated White Matter Hyperintensities Segmentations |
title | 3D Compressed Convolutional Neural Network Differentiates Neuromyelitis Optical Spectrum Disorders From Multiple Sclerosis Using Automated White Matter Hyperintensities Segmentations |
title_full | 3D Compressed Convolutional Neural Network Differentiates Neuromyelitis Optical Spectrum Disorders From Multiple Sclerosis Using Automated White Matter Hyperintensities Segmentations |
title_fullStr | 3D Compressed Convolutional Neural Network Differentiates Neuromyelitis Optical Spectrum Disorders From Multiple Sclerosis Using Automated White Matter Hyperintensities Segmentations |
title_full_unstemmed | 3D Compressed Convolutional Neural Network Differentiates Neuromyelitis Optical Spectrum Disorders From Multiple Sclerosis Using Automated White Matter Hyperintensities Segmentations |
title_short | 3D Compressed Convolutional Neural Network Differentiates Neuromyelitis Optical Spectrum Disorders From Multiple Sclerosis Using Automated White Matter Hyperintensities Segmentations |
title_sort | 3d compressed convolutional neural network differentiates neuromyelitis optical spectrum disorders from multiple sclerosis using automated white matter hyperintensities segmentations |
topic | Physiology |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7786373/ https://www.ncbi.nlm.nih.gov/pubmed/33424635 http://dx.doi.org/10.3389/fphys.2020.612928 |
work_keys_str_mv | AT wangzhuo 3dcompressedconvolutionalneuralnetworkdifferentiatesneuromyelitisopticalspectrumdisordersfrommultiplesclerosisusingautomatedwhitematterhyperintensitiessegmentations AT yuzhezhou 3dcompressedconvolutionalneuralnetworkdifferentiatesneuromyelitisopticalspectrumdisordersfrommultiplesclerosisusingautomatedwhitematterhyperintensitiessegmentations AT wangyao 3dcompressedconvolutionalneuralnetworkdifferentiatesneuromyelitisopticalspectrumdisordersfrommultiplesclerosisusingautomatedwhitematterhyperintensitiessegmentations AT zhanghuimao 3dcompressedconvolutionalneuralnetworkdifferentiatesneuromyelitisopticalspectrumdisordersfrommultiplesclerosisusingautomatedwhitematterhyperintensitiessegmentations AT luoyishan 3dcompressedconvolutionalneuralnetworkdifferentiatesneuromyelitisopticalspectrumdisordersfrommultiplesclerosisusingautomatedwhitematterhyperintensitiessegmentations AT shilin 3dcompressedconvolutionalneuralnetworkdifferentiatesneuromyelitisopticalspectrumdisordersfrommultiplesclerosisusingautomatedwhitematterhyperintensitiessegmentations AT wangyan 3dcompressedconvolutionalneuralnetworkdifferentiatesneuromyelitisopticalspectrumdisordersfrommultiplesclerosisusingautomatedwhitematterhyperintensitiessegmentations AT guochunjie 3dcompressedconvolutionalneuralnetworkdifferentiatesneuromyelitisopticalspectrumdisordersfrommultiplesclerosisusingautomatedwhitematterhyperintensitiessegmentations |