TY  - JOUR
AU  - Faber, Jennifer
AU  - Kügler, David
AU  - Bahrami, Emad
AU  - Heinz, Lea-Sophie
AU  - Timmann, Dagmar
AU  - Ernst, Thomas M
AU  - Deike-Hofmann, Katerina
AU  - Klockgether, Thomas
AU  - van de Warrenburg, Bart
AU  - van Gaalen, Judith
AU  - Reetz, Kathrin
AU  - Romanzetti, Sandro
AU  - Oz, Gulin
AU  - Joers, James M
AU  - Diedrichsen, Jorn
AU  - Reuter, Martin
AU  - Giunti, Paola
AU  - Garcia-Moreno, Hector
AU  - Jacobi, Heike
AU  - Jende, Johann
AU  - de Vries, Jeroen
AU  - Povazan, Michal
AU  - Barker, Peter B
AU  - Steiner, Katherina Marie
AU  - Krahe, Janna
TI  - CerebNet: A fast and reliable deep-learning pipeline for detailed cerebellum sub-segmentation.
JO  - NeuroImage
VL  - 264
SN  - 1053-8119
CY  - Orlando, Fla.
PB  - Academic Press
M1  - DZNE-2022-01674
SP  - 119703
PY  - 2022
AB  - Quantifying the volume of the cerebellum and its lobes is of profound interest in various neurodegenerative and acquired diseases. Especially for the most common spinocerebellar ataxias (SCA), for which the first antisense oligonculeotide-base gene silencing trial has recently started, there is an urgent need for quantitative, sensitive imaging markers at pre-symptomatic stages for stratification and treatment assessment. This work introduces CerebNet, a fully automated, extensively validated, deep learning method for the lobular segmentation of the cerebellum, including the separation of gray and white matter. For training, validation, and testing, T1-weighted images from 30 participants were manually annotated into cerebellar lobules and vermal sub-segments, as well as cerebellar white matter. CerebNet combines FastSurferCNN, a UNet-based 2.5D segmentation network, with extensive data augmentation, e.g. realistic non-linear deformations to increase the anatomical variety, eliminating additional preprocessing steps, such as spatial normalization or bias field correction. CerebNet demonstrates a high accuracy (on average 0.87 Dice and 1.742mm Robust Hausdorff Distance across all structures) outperforming state-of-the-art approaches. Furthermore, it shows high test-retest reliability (average ICC >0.97 on OASIS and Kirby) as well as high sensitivity to disease effects, including the pre-ataxic stage of spinocerebellar ataxia type 3 (SCA3). CerebNet is compatible with FreeSurfer and FastSurfer and can analyze a 3D volume within seconds on a consumer GPU in an end-to-end fashion, thus providing an efficient and validated solution for assessing cerebellum sub-structure volumes. We make CerebNet available as source-code (https://github.com/Deep-MI/FastSurfer).
KW  - Humans
KW  - Image Processing, Computer-Assisted: methods
KW  - Deep Learning
KW  - Magnetic Resonance Imaging: methods
KW  - Reproducibility of Results
KW  - Cerebellum: diagnostic imaging
KW  - CerebNet (Other)
KW  - Cerebellum (Other)
KW  - Computational neuroimaging (Other)
KW  - Deep learning (Other)
LB  - PUB:(DE-HGF)16
C2  - pmc:PMC9771831
C6  - pmid:36349595
DO  - DOI:10.1016/j.neuroimage.2022.119703
UR  - https://pub.dzne.de/record/165528
ER  -