Automated detection of MCI to Alzheimer's disease conversion before clinical onset by evaluation of atrophy rates, Steiglechner et al., 2022

Kurzfassung

Ziel der Studie war es, für Personen mit leichten kognitiven Beeinträchtigungen (MCI) eine Vorhersage zu treffen, ob sie Alzheimer entwickeln werden. Dafür wurden sie über einen Zeitraum beobachtet und mittels einer KI-basierten Software die Atrophieraten im Gehirn in dieser Zeit bestimmt. Personen mit MCI, die später Alzheimer entwickelten, hatten höhere Atrophieraten, besonders im Temporallappen und Hippocampus. Die Auswertung von MRT-Daten mit einer Software eignet sich demnach, um bereits zu einem frühen Zeitpunkt vorherzusagen, ob eine Person möglicherweise Alzheimer entwickeln wird.

 

Published in

ECR 2022 Book of Abstracts, RPS 1505-9, S.277

 

Autoren

J. Steiglechner, B. Bender, U. Ernemann, K. Scheffler, T. Lindig

 

Abstract

Purpose:

Alzheimer's disease (AD) is the most common type of an irreversible neurodegenerative disorder, affecting millions of people. Especially early stratification of patients with mild cognitive impairment (MCI) into patients who will convert to AD remains a challenging task. We aimed to predict automatically whether MCI patients will develop the disease (MCIc) by following subjects over time and quantifying spatial atrophy rates (AR) in magnetic resonance imaging (MRI).

Methods or Background:

3D T1w MRIs at 3T from 276 MCI patients participating in the first period of Alzheimer’s Disease National Initiative (ADNI1) with at least two MRIs more than 60 days apart without evident artifacts were segmented by a deep-learning-based 3D-UNet into 30 anatomical regions. Z-scores of TIV-adjusted volumes were calculated compared to a normal reference population, and AR of these z-scores were calculated longitudinally per subject (AR=0 normal aging). Rolling AR were calculated as the mean AR over a half-year time window (mRAR). A 80:20 train-test-partition was used to train a logistic regression to discriminate MCIc vs MCInc.

Results or Findings:

We found accelerated regional mRAR in MCIc. The temporal cortex and hippocampal regions showed the most striking mRAR. On the test set, of 34 MCIc, the classifier predicted 27 as true positive with a median of 1.7 Y (Q1/3=2.0/0.6Y) before conversion (sensitivity=0.79), with 5/22 false positives MCInc (stable specificity=0.77, AUC ROC=0.81).

Conclusion:

Our method provides reliable results due to a stable specificity that can be obtained well before previous clinical diagnoses for conversions to disease. Therefore, it is suitable for use in subsequent studies.

 

Original Publikation