English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
Add to Basket
 Local TagsRelease HistoryDetailsSummary
  Integration of Automated Brain MRI Segmentation and Longitudinal Atrophy Analysis Generalizes In Forecasting Progression from Mild Cognitive Impairment to Alzheimer’s Disease

Steiglechner, J., Bender, B., Lohmann, G., Scheffler, K., Ernemann, U., & Lindig, T. (2023). Integration of Automated Brain MRI Segmentation and Longitudinal Atrophy Analysis Generalizes In Forecasting Progression from Mild Cognitive Impairment to Alzheimer’s Disease. Clinical Neuroradiology, 33(Supplement 1): 321, S78-S79.

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/21.11116/0000-000D-D83E-B Version Permalink: https://hdl.handle.net/21.11116/0000-000D-D840-7
Genre: Meeting Abstract

Files

show Files

Locators

show
hide
Locator:
https://link.springer.com/content/pdf/10.1007/s00062-023-01336-5 (Publisher version)
Description:
-
OA-Status:
Not specified

Creators

show
hide
 Creators:
Steiglechner, J1, Author           
Bender, B, Author                 
Lohmann, G1, Author                 
Scheffler, K1, Author                 
Ernemann, U, Author
Lindig, T1, Author                 
Affiliations:
1Department High-Field Magnetic Resonance, Max Planck Institute for Biological Cybernetics, Max Planck Society, ou_1497796              

Content

show
hide
Free keywords: -
 Abstract: Background: Predicting progression from mild cognitive impairment ( MCI) to Alzheimer’s disease (AD) is critical for early intervention. This study aims to combine brain magnetic resonance image (MRI) segmentation and longitudinal changes to develop a generalized ac- curate classifier for progressive MCI (pMCI) vs. stable MCI (sMCI). Methods: First, our framework (Figure) is based on a segmentation model out of clinical practice [AIRAmed] for 3D T1w high-field MRI that provides labels for 30 anatomical regions. Second, we compare by age and sex with a reference cohort of TIV-adjusted volume meas- ures to generate z-statistics. Third, we propose a time scaled quanti- fication of atrophy rates. The combination of z-statistics and atrophy rates serves as input to a classifier. An 80:20 train-test-partition of the Alzheimer’s Disease National Initiative (ADNI) is used to train a logis- tic regression to discriminate pMCI from sMCI.

Details

show
hide
Language(s):
 Dates: 2023-09
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: DOI: 10.1007/s00062-023-01336-5
 Degree: -

Event

show
hide
Title: 58. Jahrestagung der Deutschen Gesellschaft für Neuroradiologie e.V. und 30. Jahrestagung der Österreichischen Gesellschaft für Neuroradiologie e.V. (NEURORAD 2023)
Place of Event: Kassel, Germany
Start-/End Date: 2023-10-04 - 2023-10-06

Legal Case

show

Project information

show

Source 1

show
hide
Title: Clinical Neuroradiology
Source Genre: Journal
 Creator(s):
Affiliations:
Publ. Info: Springer
Pages: - Volume / Issue: 33 (Supplement 1) Sequence Number: 321 Start / End Page: S78 - S79 Identifier: ISSN: 0939-7116