Cargando…

Self-Supervised Contrastive Learning to Predict the Progression of Alzheimer’s Disease with 3D Amyloid-PET

Early diagnosis of Alzheimer’s disease (AD) is an important task that facilitates the development of treatment and prevention strategies, and may potentially improve patient outcomes. Neuroimaging has shown great promise, including the amyloid-PET, which measures the accumulation of amyloid plaques...

Descripción completa

Detalles Bibliográficos
Autores principales: Kwak, Min Gu, Su, Yi, Chen, Kewei, Weidman, David, Wu, Teresa, Lure, Fleming, Li, Jing
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10604381/
https://www.ncbi.nlm.nih.gov/pubmed/37892871
http://dx.doi.org/10.3390/bioengineering10101141
_version_ 1785126821913690112
author Kwak, Min Gu
Su, Yi
Chen, Kewei
Weidman, David
Wu, Teresa
Lure, Fleming
Li, Jing
author_facet Kwak, Min Gu
Su, Yi
Chen, Kewei
Weidman, David
Wu, Teresa
Lure, Fleming
Li, Jing
author_sort Kwak, Min Gu
collection PubMed
description Early diagnosis of Alzheimer’s disease (AD) is an important task that facilitates the development of treatment and prevention strategies, and may potentially improve patient outcomes. Neuroimaging has shown great promise, including the amyloid-PET, which measures the accumulation of amyloid plaques in the brain—a hallmark of AD. It is desirable to train end-to-end deep learning models to predict the progression of AD for individuals at early stages based on 3D amyloid-PET. However, commonly used models are trained in a fully supervised learning manner, and they are inevitably biased toward the given label information. To this end, we propose a selfsupervised contrastive learning method to accurately predict the conversion to AD for individuals with mild cognitive impairment (MCI) with 3D amyloid-PET. The proposed method, SMoCo, uses both labeled and unlabeled data to capture general semantic representations underlying the images. As the downstream task is given as classification of converters vs. non-converters, unlike the general self-supervised learning problem that aims to generate task-agnostic representations, SMoCo additionally utilizes the label information in the pre-training. To demonstrate the performance of our method, we conducted experiments on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset. The results confirmed that the proposed method is capable of providing appropriate data representations, resulting in accurate classification. SMoCo showed the best classification performance over the existing methods, with AUROC = 85.17%, accuracy = 81.09%, sensitivity = 77.39%, and specificity = 82.17%. While SSL has demonstrated great success in other application domains of computer vision, this study provided the initial investigation of using a proposed self-supervised contrastive learning model, SMoCo, to effectively predict MCI conversion to AD based on 3D amyloid-PET.
format Online
Article
Text
id pubmed-10604381
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-106043812023-10-28 Self-Supervised Contrastive Learning to Predict the Progression of Alzheimer’s Disease with 3D Amyloid-PET Kwak, Min Gu Su, Yi Chen, Kewei Weidman, David Wu, Teresa Lure, Fleming Li, Jing Bioengineering (Basel) Article Early diagnosis of Alzheimer’s disease (AD) is an important task that facilitates the development of treatment and prevention strategies, and may potentially improve patient outcomes. Neuroimaging has shown great promise, including the amyloid-PET, which measures the accumulation of amyloid plaques in the brain—a hallmark of AD. It is desirable to train end-to-end deep learning models to predict the progression of AD for individuals at early stages based on 3D amyloid-PET. However, commonly used models are trained in a fully supervised learning manner, and they are inevitably biased toward the given label information. To this end, we propose a selfsupervised contrastive learning method to accurately predict the conversion to AD for individuals with mild cognitive impairment (MCI) with 3D amyloid-PET. The proposed method, SMoCo, uses both labeled and unlabeled data to capture general semantic representations underlying the images. As the downstream task is given as classification of converters vs. non-converters, unlike the general self-supervised learning problem that aims to generate task-agnostic representations, SMoCo additionally utilizes the label information in the pre-training. To demonstrate the performance of our method, we conducted experiments on the Alzheimer’s Disease Neuroimaging Initiative (ADNI) dataset. The results confirmed that the proposed method is capable of providing appropriate data representations, resulting in accurate classification. SMoCo showed the best classification performance over the existing methods, with AUROC = 85.17%, accuracy = 81.09%, sensitivity = 77.39%, and specificity = 82.17%. While SSL has demonstrated great success in other application domains of computer vision, this study provided the initial investigation of using a proposed self-supervised contrastive learning model, SMoCo, to effectively predict MCI conversion to AD based on 3D amyloid-PET. MDPI 2023-09-28 /pmc/articles/PMC10604381/ /pubmed/37892871 http://dx.doi.org/10.3390/bioengineering10101141 Text en © 2023 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Kwak, Min Gu
Su, Yi
Chen, Kewei
Weidman, David
Wu, Teresa
Lure, Fleming
Li, Jing
Self-Supervised Contrastive Learning to Predict the Progression of Alzheimer’s Disease with 3D Amyloid-PET
title Self-Supervised Contrastive Learning to Predict the Progression of Alzheimer’s Disease with 3D Amyloid-PET
title_full Self-Supervised Contrastive Learning to Predict the Progression of Alzheimer’s Disease with 3D Amyloid-PET
title_fullStr Self-Supervised Contrastive Learning to Predict the Progression of Alzheimer’s Disease with 3D Amyloid-PET
title_full_unstemmed Self-Supervised Contrastive Learning to Predict the Progression of Alzheimer’s Disease with 3D Amyloid-PET
title_short Self-Supervised Contrastive Learning to Predict the Progression of Alzheimer’s Disease with 3D Amyloid-PET
title_sort self-supervised contrastive learning to predict the progression of alzheimer’s disease with 3d amyloid-pet
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC10604381/
https://www.ncbi.nlm.nih.gov/pubmed/37892871
http://dx.doi.org/10.3390/bioengineering10101141
work_keys_str_mv AT kwakmingu selfsupervisedcontrastivelearningtopredicttheprogressionofalzheimersdiseasewith3damyloidpet
AT suyi selfsupervisedcontrastivelearningtopredicttheprogressionofalzheimersdiseasewith3damyloidpet
AT chenkewei selfsupervisedcontrastivelearningtopredicttheprogressionofalzheimersdiseasewith3damyloidpet
AT weidmandavid selfsupervisedcontrastivelearningtopredicttheprogressionofalzheimersdiseasewith3damyloidpet
AT wuteresa selfsupervisedcontrastivelearningtopredicttheprogressionofalzheimersdiseasewith3damyloidpet
AT lurefleming selfsupervisedcontrastivelearningtopredicttheprogressionofalzheimersdiseasewith3damyloidpet
AT lijing selfsupervisedcontrastivelearningtopredicttheprogressionofalzheimersdiseasewith3damyloidpet
AT selfsupervisedcontrastivelearningtopredicttheprogressionofalzheimersdiseasewith3damyloidpet