A deep learning MRI approach outperforms other biomarkers of prodromal Alzheimer’s disease
Abstract Background The three core pathologies of Alzheimer’s disease (AD) are amyloid pathology, tau pathology, and neurodegeneration. Biomarkers exist for each. Neurodegeneration is often detected by neuroimaging, and we hypothesized that a voxel-based deep learning approach using structural MRI m...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2022-03-01
|
| Series: | Alzheimer’s Research & Therapy |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13195-022-00985-x |
| _version_ | 1823970241990885376 |
|---|---|
| author | Xinyang Feng Frank A. Provenzano Scott A. Small for the Alzheimer’s Disease Neuroimaging Initiative |
| author_facet | Xinyang Feng Frank A. Provenzano Scott A. Small for the Alzheimer’s Disease Neuroimaging Initiative |
| author_sort | Xinyang Feng |
| collection | DOAJ |
| description | Abstract Background The three core pathologies of Alzheimer’s disease (AD) are amyloid pathology, tau pathology, and neurodegeneration. Biomarkers exist for each. Neurodegeneration is often detected by neuroimaging, and we hypothesized that a voxel-based deep learning approach using structural MRI might outperform other neuroimaging methods. Methods First, we implement an MRI-based deep learning model, trained with a data augmentation strategy, which classifies Alzheimer’s dementia and generates class activation maps. Next, we tested the model in prodromal AD and compared its performance to other biomarkers of amyloid pathology, tau pathology, and neuroimaging biomarkers of neurodegeneration. Results The model distinguished between controls and AD with high accuracy (AUROC = 0.973) with class activation maps that localized to the hippocampal formation. As hypothesized, the model also outperformed other neuroimaging biomarkers of neurodegeneration in prodromal AD (AUROC = 0.788) but also outperformed biomarkers of amyloid (CSF Aβ = 0.702) or tau pathology (CSF tau = 0.682), and the findings are interpreted in the context of AD’s known anatomical biology. Conclusions The advantages of using deep learning to extract biomarker information from conventional MRIs extend practically, potentially reducing patient burden, risk, and cost. |
| first_indexed | 2024-12-18T03:09:52Z |
| format | Article |
| id | doaj.art-249f999a55b542a69ffa0040de801d0a |
| institution | Directory Open Access Journal |
| issn | 1758-9193 |
| language | English |
| last_indexed | 2024-12-18T03:09:52Z |
| publishDate | 2022-03-01 |
| publisher | BMC |
| record_format | Article |
| series | Alzheimer’s Research & Therapy |
| spelling | doaj.art-249f999a55b542a69ffa0040de801d0a2022-12-21T21:23:03ZengBMCAlzheimer’s Research & Therapy1758-91932022-03-0114111110.1186/s13195-022-00985-xA deep learning MRI approach outperforms other biomarkers of prodromal Alzheimer’s diseaseXinyang Feng0Frank A. Provenzano1Scott A. Small2for the Alzheimer’s Disease Neuroimaging InitiativeDepartment of Biomedical Engineering, Columbia UniversityDepartment of Neurology, Columbia UniversityDepartment of Neurology, Columbia UniversityAbstract Background The three core pathologies of Alzheimer’s disease (AD) are amyloid pathology, tau pathology, and neurodegeneration. Biomarkers exist for each. Neurodegeneration is often detected by neuroimaging, and we hypothesized that a voxel-based deep learning approach using structural MRI might outperform other neuroimaging methods. Methods First, we implement an MRI-based deep learning model, trained with a data augmentation strategy, which classifies Alzheimer’s dementia and generates class activation maps. Next, we tested the model in prodromal AD and compared its performance to other biomarkers of amyloid pathology, tau pathology, and neuroimaging biomarkers of neurodegeneration. Results The model distinguished between controls and AD with high accuracy (AUROC = 0.973) with class activation maps that localized to the hippocampal formation. As hypothesized, the model also outperformed other neuroimaging biomarkers of neurodegeneration in prodromal AD (AUROC = 0.788) but also outperformed biomarkers of amyloid (CSF Aβ = 0.702) or tau pathology (CSF tau = 0.682), and the findings are interpreted in the context of AD’s known anatomical biology. Conclusions The advantages of using deep learning to extract biomarker information from conventional MRIs extend practically, potentially reducing patient burden, risk, and cost.https://doi.org/10.1186/s13195-022-00985-xNeuroimagingProdromal Alzheimer’s diseaseBiomarkersDeep learning |
| spellingShingle | Xinyang Feng Frank A. Provenzano Scott A. Small for the Alzheimer’s Disease Neuroimaging Initiative A deep learning MRI approach outperforms other biomarkers of prodromal Alzheimer’s disease Alzheimer’s Research & Therapy Neuroimaging Prodromal Alzheimer’s disease Biomarkers Deep learning |
| title | A deep learning MRI approach outperforms other biomarkers of prodromal Alzheimer’s disease |
| title_full | A deep learning MRI approach outperforms other biomarkers of prodromal Alzheimer’s disease |
| title_fullStr | A deep learning MRI approach outperforms other biomarkers of prodromal Alzheimer’s disease |
| title_full_unstemmed | A deep learning MRI approach outperforms other biomarkers of prodromal Alzheimer’s disease |
| title_short | A deep learning MRI approach outperforms other biomarkers of prodromal Alzheimer’s disease |
| title_sort | deep learning mri approach outperforms other biomarkers of prodromal alzheimer s disease |
| topic | Neuroimaging Prodromal Alzheimer’s disease Biomarkers Deep learning |
| url | https://doi.org/10.1186/s13195-022-00985-x |
| work_keys_str_mv | AT xinyangfeng adeeplearningmriapproachoutperformsotherbiomarkersofprodromalalzheimersdisease AT frankaprovenzano adeeplearningmriapproachoutperformsotherbiomarkersofprodromalalzheimersdisease AT scottasmall adeeplearningmriapproachoutperformsotherbiomarkersofprodromalalzheimersdisease AT forthealzheimersdiseaseneuroimaginginitiative adeeplearningmriapproachoutperformsotherbiomarkersofprodromalalzheimersdisease AT xinyangfeng deeplearningmriapproachoutperformsotherbiomarkersofprodromalalzheimersdisease AT frankaprovenzano deeplearningmriapproachoutperformsotherbiomarkersofprodromalalzheimersdisease AT scottasmall deeplearningmriapproachoutperformsotherbiomarkersofprodromalalzheimersdisease AT forthealzheimersdiseaseneuroimaginginitiative deeplearningmriapproachoutperformsotherbiomarkersofprodromalalzheimersdisease |