3D convolutional neural networks-based multiclass classification of Alzheimer’s and Parkinson’s diseases using PET and SPECT neuroimaging modalities
Abstract Background Alzheimer’s disease (AD) is a neurodegenerative brain pathology formed due to piling up of amyloid proteins, development of plaques and disappearance of neurons. Another common subtype of dementia like AD, Parkinson’s disease (PD) is determined by the disappearance of dopaminergi...
Guardado en:
Autores principales: | , , , , , , , , |
---|---|
Formato: | article |
Lenguaje: | EN |
Publicado: |
SpringerOpen
2021
|
Materias: | |
Acceso en línea: | https://doaj.org/article/c93289134d2245668be9476b0854b66d |
Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
id |
oai:doaj.org-article:c93289134d2245668be9476b0854b66d |
---|---|
record_format |
dspace |
spelling |
oai:doaj.org-article:c93289134d2245668be9476b0854b66d2021-11-07T12:11:55Z3D convolutional neural networks-based multiclass classification of Alzheimer’s and Parkinson’s diseases using PET and SPECT neuroimaging modalities10.1186/s40708-021-00144-22198-40182198-4026https://doaj.org/article/c93289134d2245668be9476b0854b66d2021-11-01T00:00:00Zhttps://doi.org/10.1186/s40708-021-00144-2https://doaj.org/toc/2198-4018https://doaj.org/toc/2198-4026Abstract Background Alzheimer’s disease (AD) is a neurodegenerative brain pathology formed due to piling up of amyloid proteins, development of plaques and disappearance of neurons. Another common subtype of dementia like AD, Parkinson’s disease (PD) is determined by the disappearance of dopaminergic neurons in the region known as substantia nigra pars compacta located in the midbrain. Both AD and PD target aged population worldwide forming a major chunk of healthcare costs. Hence, there is a need for methods that help in the early diagnosis of these diseases. PD subjects especially those who have confirmed postmortem plaque are a strong candidate for a second AD diagnosis. Modalities such as positron emission tomography (PET) and single photon emission computed tomography (SPECT) can be combined with deep learning methods to diagnose these two diseases for the benefit of clinicians. Result In this work, we deployed a 3D Convolutional Neural Network (CNN) to extract features for multiclass classification of both AD and PD in the frequency and spatial domains using PET and SPECT neuroimaging modalities to differentiate between AD, PD and Normal Control (NC) classes. Discrete Cosine Transform has been deployed as a frequency domain learning method along with random weak Gaussian blurring and random zooming in/out augmentation methods in both frequency and spatial domains. To select the hyperparameters of the 3D-CNN model, we deployed both 5- and 10-fold cross-validation (CV) approaches. The best performing model was found to be AD/NC(SPECT)/PD classification with random weak Gaussian blurred augmentation in the spatial domain using fivefold CV approach while the worst performing model happens to be AD/NC(PET)/PD classification without augmentation in the frequency domain using tenfold CV approach. We also found that spatial domain methods tend to perform better than their frequency domain counterparts. Conclusion The proposed model provides a good performance in discriminating AD and PD subjects due to minimal correlation between these two dementia types on the clinicopathological continuum between AD and PD subjects from a neuroimaging perspective.Ahsan Bin TufailYong-Kui MaQiu-Na ZhangAdil KhanLei ZhaoQiang YangMuhammad AdeelRahim KhanInam UllahSpringerOpenarticleDementiaNeuroimaging modalitiesPattern recognitionDeep learningDiscrete cosine transformComputer applications to medicine. Medical informaticsR858-859.7Computer softwareQA76.75-76.765ENBrain Informatics, Vol 8, Iss 1, Pp 1-9 (2021) |
institution |
DOAJ |
collection |
DOAJ |
language |
EN |
topic |
Dementia Neuroimaging modalities Pattern recognition Deep learning Discrete cosine transform Computer applications to medicine. Medical informatics R858-859.7 Computer software QA76.75-76.765 |
spellingShingle |
Dementia Neuroimaging modalities Pattern recognition Deep learning Discrete cosine transform Computer applications to medicine. Medical informatics R858-859.7 Computer software QA76.75-76.765 Ahsan Bin Tufail Yong-Kui Ma Qiu-Na Zhang Adil Khan Lei Zhao Qiang Yang Muhammad Adeel Rahim Khan Inam Ullah 3D convolutional neural networks-based multiclass classification of Alzheimer’s and Parkinson’s diseases using PET and SPECT neuroimaging modalities |
description |
Abstract Background Alzheimer’s disease (AD) is a neurodegenerative brain pathology formed due to piling up of amyloid proteins, development of plaques and disappearance of neurons. Another common subtype of dementia like AD, Parkinson’s disease (PD) is determined by the disappearance of dopaminergic neurons in the region known as substantia nigra pars compacta located in the midbrain. Both AD and PD target aged population worldwide forming a major chunk of healthcare costs. Hence, there is a need for methods that help in the early diagnosis of these diseases. PD subjects especially those who have confirmed postmortem plaque are a strong candidate for a second AD diagnosis. Modalities such as positron emission tomography (PET) and single photon emission computed tomography (SPECT) can be combined with deep learning methods to diagnose these two diseases for the benefit of clinicians. Result In this work, we deployed a 3D Convolutional Neural Network (CNN) to extract features for multiclass classification of both AD and PD in the frequency and spatial domains using PET and SPECT neuroimaging modalities to differentiate between AD, PD and Normal Control (NC) classes. Discrete Cosine Transform has been deployed as a frequency domain learning method along with random weak Gaussian blurring and random zooming in/out augmentation methods in both frequency and spatial domains. To select the hyperparameters of the 3D-CNN model, we deployed both 5- and 10-fold cross-validation (CV) approaches. The best performing model was found to be AD/NC(SPECT)/PD classification with random weak Gaussian blurred augmentation in the spatial domain using fivefold CV approach while the worst performing model happens to be AD/NC(PET)/PD classification without augmentation in the frequency domain using tenfold CV approach. We also found that spatial domain methods tend to perform better than their frequency domain counterparts. Conclusion The proposed model provides a good performance in discriminating AD and PD subjects due to minimal correlation between these two dementia types on the clinicopathological continuum between AD and PD subjects from a neuroimaging perspective. |
format |
article |
author |
Ahsan Bin Tufail Yong-Kui Ma Qiu-Na Zhang Adil Khan Lei Zhao Qiang Yang Muhammad Adeel Rahim Khan Inam Ullah |
author_facet |
Ahsan Bin Tufail Yong-Kui Ma Qiu-Na Zhang Adil Khan Lei Zhao Qiang Yang Muhammad Adeel Rahim Khan Inam Ullah |
author_sort |
Ahsan Bin Tufail |
title |
3D convolutional neural networks-based multiclass classification of Alzheimer’s and Parkinson’s diseases using PET and SPECT neuroimaging modalities |
title_short |
3D convolutional neural networks-based multiclass classification of Alzheimer’s and Parkinson’s diseases using PET and SPECT neuroimaging modalities |
title_full |
3D convolutional neural networks-based multiclass classification of Alzheimer’s and Parkinson’s diseases using PET and SPECT neuroimaging modalities |
title_fullStr |
3D convolutional neural networks-based multiclass classification of Alzheimer’s and Parkinson’s diseases using PET and SPECT neuroimaging modalities |
title_full_unstemmed |
3D convolutional neural networks-based multiclass classification of Alzheimer’s and Parkinson’s diseases using PET and SPECT neuroimaging modalities |
title_sort |
3d convolutional neural networks-based multiclass classification of alzheimer’s and parkinson’s diseases using pet and spect neuroimaging modalities |
publisher |
SpringerOpen |
publishDate |
2021 |
url |
https://doaj.org/article/c93289134d2245668be9476b0854b66d |
work_keys_str_mv |
AT ahsanbintufail 3dconvolutionalneuralnetworksbasedmulticlassclassificationofalzheimersandparkinsonsdiseasesusingpetandspectneuroimagingmodalities AT yongkuima 3dconvolutionalneuralnetworksbasedmulticlassclassificationofalzheimersandparkinsonsdiseasesusingpetandspectneuroimagingmodalities AT qiunazhang 3dconvolutionalneuralnetworksbasedmulticlassclassificationofalzheimersandparkinsonsdiseasesusingpetandspectneuroimagingmodalities AT adilkhan 3dconvolutionalneuralnetworksbasedmulticlassclassificationofalzheimersandparkinsonsdiseasesusingpetandspectneuroimagingmodalities AT leizhao 3dconvolutionalneuralnetworksbasedmulticlassclassificationofalzheimersandparkinsonsdiseasesusingpetandspectneuroimagingmodalities AT qiangyang 3dconvolutionalneuralnetworksbasedmulticlassclassificationofalzheimersandparkinsonsdiseasesusingpetandspectneuroimagingmodalities AT muhammadadeel 3dconvolutionalneuralnetworksbasedmulticlassclassificationofalzheimersandparkinsonsdiseasesusingpetandspectneuroimagingmodalities AT rahimkhan 3dconvolutionalneuralnetworksbasedmulticlassclassificationofalzheimersandparkinsonsdiseasesusingpetandspectneuroimagingmodalities AT inamullah 3dconvolutionalneuralnetworksbasedmulticlassclassificationofalzheimersandparkinsonsdiseasesusingpetandspectneuroimagingmodalities |
_version_ |
1718443515783938048 |