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 3D-Unet-based convolutional neural networks for iterative multi-scale localization and multi-rater segmentation and non-deep learning-based components for automated biomarker extraction. We trained on the healthy aging cohort and did not carry out any adaption or fine-tuning prior to the application to Parkinson’s disease subjects. Results The localization and segmentation pipeline demonstrated sufficient performance as measured by Euclidean distance (on average around 1.3mm on healthy aging subjects and 2.2mm in Parkinson’s disease subjects) and Dice similarity coefficient (overall around $$71\%$$ 71 % on healthy aging subjects and $$60\%$$ 60 % for subjects with Parkinson’s disease) as well as promising agreement with respect to contrast ratios in terms of intraclass correlation coefficient of $$\ge 0.80$$ ≥ 0.80 for healthy aging subjects compared to a manual segmentation procedure. Lower values ($$\ge 0.48$$ ≥ 0.48 ) for Parkinson’s disease subjects indicate the need for further investigation and tests before the application to clinical samples. Conclusion These promising results suggest the usability of the proposed algorithm for data of healthy aging subjects and pave the way for further investigations using this approach on different clinical datasets to validate its practical usability more conclusively.

NigraNet: An automatic framework to assess nigral neuromelanin content in early Parkinson’s disease using convolutional neural network

“…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 ).…”

Rostral-middle locus coeruleus integrity and subjective cognitive decline in early old age

“…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).…”

Automatic Geometry-based Estimation of the Locus Coeruleus Region on T1-Weighted Magnetic Resonance Images

“…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).…”