Fully automated deep learning-based localization and segmentation of the locus coeruleus in aging and Parkinson’s disease using neuromelanin-sensitive MRI
Abstract:Purpose
Development and performance measurement of a fully automated pipeline that localizes and segments the locus coeruleus in so-called neuromelanin-sensitive magnetic resonance imaging data for the derivation of quantitative biomarkers of neurodegenerative diseases such as Alzheimer’s disease and Parkinson’s disease.
Methods
We propose a pipeline composed of several … Show more
“…Recently, we also used a similar approach on patients with isolated REM sleep behavior disorder, ( Gaurav et al, 2022 ) the prodromal phase of parkinsonism ( Iranzo et al, 2014 , Pyatigorskaya et al, 2017 ). Lastly, a recent study in PD patients employed U-net to automatically segment the locus coeruleus, which can also be visualized using the same neuromelanin-sensitive MRI acquisitions ( Dünnwald et al, 2021 ).…”
“…Recently, we also used a similar approach on patients with isolated REM sleep behavior disorder, ( Gaurav et al, 2022 ) the prodromal phase of parkinsonism ( Iranzo et al, 2014 , Pyatigorskaya et al, 2017 ). Lastly, a recent study in PD patients employed U-net to automatically segment the locus coeruleus, which can also be visualized using the same neuromelanin-sensitive MRI acquisitions ( Dünnwald et al, 2021 ).…”
“…The location of our slices can be compared to other studies based on the location of the middle and rostral slices relative to the inferior colliculus (e.g., the middle slices in 7 mm below the inferior edge of the inferior colliculus). However, automated protocols for LC assessment are a key goal of ongoing research to provide further standardization across studies (Dünnwald et al, 2021). Another limitation of our LC measure is that the caudal LC is more diffuse in structure and is more difficult to visualize in acquisitions such as the one used here (Tona et al, 2017).…”
Objectives:
Abnormal tau, a hallmark Alzheimer’s disease (AD) pathology, may appear in the locus coeruleus (LC) decades before AD symptom onset. Reports of subjective cognitive decline are also often present prior to formal diagnosis. Yet, the relationship between LC structural integrity and subjective cognitive decline has remained unexplored. Here, we aimed to explore these potential associations.
Methods:
We examined 381 community-dwelling men (mean age = 67.58; SD = 2.62) in the Vietnam Era Twin Study of Aging who underwent LC-sensitive magnetic resonance imaging and completed the Everyday Cognition scale to measure subjective cognitive decline along with their selected informants. Mixed models examined the associations between rostral-middle and caudal LC integrity and subjective cognitive decline after adjusting for depressive symptoms, physical morbidities, and family. Models also adjusted for current objective cognitive performance and objective cognitive decline to explore attenuation.
Results:
For participant ratings, lower rostral-middle LC contrast to noise ratio (LCCNR) was associated with significantly greater subjective decline in memory, executive function, and visuospatial abilities. For informant ratings, lower rostral-middle LCCNR was associated with significantly greater subjective decline in memory only. Associations remained after adjusting for current objective cognition and objective cognitive decline in respective domains.
Conclusions:
Lower rostral-middle LC integrity is associated with greater subjective cognitive decline. Although not explained by objective cognitive performance, such a relationship may explain increased AD risk in people with subjective cognitive decline as the LC is an important neural substrate important for higher order cognitive processing, attention, and arousal and one of the first sites of AD pathology.
“…Our internal evaluation of (the optimal variations of) the ELV and U-Net automatic segmentation approaches on our data resulted in a similar cross-validation Dice score of 0.63∼0.64 for both methods. In comparison, the LC label Dice scores reported in the literature for inter-rater reliability are 0.50 (20), 0.54∼0.64 (18), 0.64 (33), and 0.68 (19), for scan-rescan reliability are 0.24∼0.48 (21) and 0.63 (50), and for automatic segmentation are 0.40 (20), 0.54∼0.64 (21), and 0.60∼0.71 (19).…”
The locus coeruleus (LC) is a key brain structure implicated in cognitive function and neurodegenerative disease. Automatic segmentation of the LC is a crucial step in quantitative non-invasive analysis of the LC in large MRI cohorts. Most publicly available imaging databases for training automatic LC segmentation models take advantage of specialized contrast-enhancing (e.g., neuromelanin-sensitive) MRI. Segmentation models developed with such image contrasts, however, are not readily applicable to existing datasets with conventional MRI sequences. In this work, we evaluate the feasibility of using non-contrast neuroanatomical information to geometrically approximate the LC region from standard 3-Tesla T1-weighted images of 20 subjects from the Human Connectome Project (HCP). We employ this dataset to train and internally/externally evaluate two automatic localization methods, the Expected Label Value and the U-Net. We also test the hypothesis that using the phase image as input can improve the robustness of out-of-sample segmentation. We then apply our trained models to a larger subset of HCP, while exploratorily correlating LC imaging variables and structural connectivity with demographic and clinical data. This report contributes and provides an evaluation of two computational methods estimating neural structure.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.