Cargando…
AD-NET: Age-adjust neural network for improved MCI to AD conversion prediction
The prediction of Mild Cognitive Impairment (MCI) patients who are at higher risk converting to Alzheimer's Disease (AD) is critical for effective intervention and patient selection in clinical trials. Different biomarkers including neuroimaging have been developed to serve the purpose. With ex...
Autores principales: | , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
Elsevier
2020
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7306626/ https://www.ncbi.nlm.nih.gov/pubmed/32570205 http://dx.doi.org/10.1016/j.nicl.2020.102290 |
_version_ | 1783548694091530240 |
---|---|
author | Gao, Fei Yoon, Hyunsoo Xu, Yanzhe Goradia, Dhruman Luo, Ji Wu, Teresa Su, Yi |
author_facet | Gao, Fei Yoon, Hyunsoo Xu, Yanzhe Goradia, Dhruman Luo, Ji Wu, Teresa Su, Yi |
author_sort | Gao, Fei |
collection | PubMed |
description | The prediction of Mild Cognitive Impairment (MCI) patients who are at higher risk converting to Alzheimer's Disease (AD) is critical for effective intervention and patient selection in clinical trials. Different biomarkers including neuroimaging have been developed to serve the purpose. With extensive methodology development efforts on neuroimaging, an emerging field is deep learning research. One great challenge facing deep learning is the limited medical imaging data available. To address the issue, researchers explore the use of transfer learning to extend the applicability of deep models on neuroimaging research for AD diagnosis and prognosis. Existing transfer learning models mostly focus on transferring the features from the pre-training into the fine-tuning stage. Recognizing the advantages of the knowledge gained during the pre-training, we propose an AD-NET (Age-adjust neural network) with the pre-training model serving two purposes: extracting and transferring features; and obtaining and transferring knowledge. Specifically, the knowledge being transferred in this research is an age-related surrogate biomarker. To evaluate the effectiveness of the proposed approach, AD-NET is compared with 8 classification models from literature using the same public neuroimaging dataset. Experimental results show that the proposed AD-NET outperforms the competing models in predicting the MCI patients at risk for conversion to the AD stage. |
format | Online Article Text |
id | pubmed-7306626 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2020 |
publisher | Elsevier |
record_format | MEDLINE/PubMed |
spelling | pubmed-73066262020-06-25 AD-NET: Age-adjust neural network for improved MCI to AD conversion prediction Gao, Fei Yoon, Hyunsoo Xu, Yanzhe Goradia, Dhruman Luo, Ji Wu, Teresa Su, Yi Neuroimage Clin Regular Article The prediction of Mild Cognitive Impairment (MCI) patients who are at higher risk converting to Alzheimer's Disease (AD) is critical for effective intervention and patient selection in clinical trials. Different biomarkers including neuroimaging have been developed to serve the purpose. With extensive methodology development efforts on neuroimaging, an emerging field is deep learning research. One great challenge facing deep learning is the limited medical imaging data available. To address the issue, researchers explore the use of transfer learning to extend the applicability of deep models on neuroimaging research for AD diagnosis and prognosis. Existing transfer learning models mostly focus on transferring the features from the pre-training into the fine-tuning stage. Recognizing the advantages of the knowledge gained during the pre-training, we propose an AD-NET (Age-adjust neural network) with the pre-training model serving two purposes: extracting and transferring features; and obtaining and transferring knowledge. Specifically, the knowledge being transferred in this research is an age-related surrogate biomarker. To evaluate the effectiveness of the proposed approach, AD-NET is compared with 8 classification models from literature using the same public neuroimaging dataset. Experimental results show that the proposed AD-NET outperforms the competing models in predicting the MCI patients at risk for conversion to the AD stage. Elsevier 2020-06-01 /pmc/articles/PMC7306626/ /pubmed/32570205 http://dx.doi.org/10.1016/j.nicl.2020.102290 Text en © 2020 The Authors http://creativecommons.org/licenses/by-nc-nd/4.0/ This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/). |
spellingShingle | Regular Article Gao, Fei Yoon, Hyunsoo Xu, Yanzhe Goradia, Dhruman Luo, Ji Wu, Teresa Su, Yi AD-NET: Age-adjust neural network for improved MCI to AD conversion prediction |
title | AD-NET: Age-adjust neural network for improved MCI to AD conversion prediction |
title_full | AD-NET: Age-adjust neural network for improved MCI to AD conversion prediction |
title_fullStr | AD-NET: Age-adjust neural network for improved MCI to AD conversion prediction |
title_full_unstemmed | AD-NET: Age-adjust neural network for improved MCI to AD conversion prediction |
title_short | AD-NET: Age-adjust neural network for improved MCI to AD conversion prediction |
title_sort | ad-net: age-adjust neural network for improved mci to ad conversion prediction |
topic | Regular Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7306626/ https://www.ncbi.nlm.nih.gov/pubmed/32570205 http://dx.doi.org/10.1016/j.nicl.2020.102290 |
work_keys_str_mv | AT gaofei adnetageadjustneuralnetworkforimprovedmcitoadconversionprediction AT yoonhyunsoo adnetageadjustneuralnetworkforimprovedmcitoadconversionprediction AT xuyanzhe adnetageadjustneuralnetworkforimprovedmcitoadconversionprediction AT goradiadhruman adnetageadjustneuralnetworkforimprovedmcitoadconversionprediction AT luoji adnetageadjustneuralnetworkforimprovedmcitoadconversionprediction AT wuteresa adnetageadjustneuralnetworkforimprovedmcitoadconversionprediction AT suyi adnetageadjustneuralnetworkforimprovedmcitoadconversionprediction AT adnetageadjustneuralnetworkforimprovedmcitoadconversionprediction |