Fully Automated MRI-based Analysis of the Locus Coeruleus in Aging and Alzheimer’s Disease Dementia using ELSI-Net

Abstract

Abstract INTRODUCTION The Locus Coeruleus (LC) is linked to the development and pathophysiology of neurodegenerative diseases such as Alzheimer’s Disease (AD). Magnetic Resonance Imaging based LC features have shown potential to assess LC integrity in vivo. METHODS We present a Deep Learning based LC segmentation and feature extraction method: ELSI-Net and apply it to healthy aging and AD dementia datasets. Agreement to expert raters and previously published LC atlases were assessed. We aimed to reproduce previously reported differences in LC integrity in aging and AD dementia and correlate extracted features to cerebrospinal fluid (CSF) biomarkers of AD pathology. RESULTS ELSI-Net demonstrated high agreement to expert raters and published atlases. Previously reported group differences in LC integrity were detected and correlations to CSF biomarkers were found. DISCUSSION Although we found excellent performance, further evaluations on more diverse datasets from clinical cohorts are required for a conclusive assessment of ELSI-Nets general applicability. Highlights thorough evaluation of a fully automatic LC segmentation method termed ELSI-Net in aging and AD dementia ELSI-Net outperforms previous work and shows high agreement with manual ratings and previously published LC atlases ELSI-Net replicates previously shown LC group differences in aging and AD ELSI-Net’s LC volume correlates with CSF biomarkers of AD pathology RESEARCH IN CONTEXT Systematic Review: The authors reviewed the literature using traditional sources (e.g. Pubmed, Google Scholar). Although there are several publications introducing semi-automatic methods for LC segmentation, the application of Deep Learning methods is underexplored. To the best of our knowledge, this is the first paper using a Deep Learning based approach for automated LC segmentation in AD dementia. Interpretation: Our work introduces and evaluates an improved automatic, Deep Learning based LC segmentation and analysis approach. The results suggest a very high potential for practical applicability, e.g. in large-scale clinical studies for neurodegenerative diseases. Future Directions: ELSI-Net can be used to assess LC integrity on large- or small-scale studies in Alzheimer’s Disease dementia. To ensure robust performance, ELSI-Net should be further evaluated in larger, more diverse datasets comprising varying LC MRI protocols and clinical populations.