eprintid: 1572458
rev_number: 36
eprint_status: archive
userid: 608
dir: disk0/01/57/24/58
datestamp: 2017-09-08 15:02:42
lastmod: 2021-09-28 22:27:07
status_changed: 2017-09-08 15:02:42
type: article
metadata_visibility: show
creators_name: De Sitter, A
creators_name: Steenwijk, MD
creators_name: Ruet, A
creators_name: Versteeg, A
creators_name: Liu, Y
creators_name: Van Schijndel, RA
creators_name: Pouwels, PJW
creators_name: Kilsdonk, ID
creators_name: Cover, KS
creators_name: Van Dijk, BW
creators_name: Ropele, S
creators_name: Rocca, MA
creators_name: Yiannakas, M
creators_name: Wattjes, MP
creators_name: Damangir, S
creators_name: Frisoni, GB
creators_name: Sastre-Garriga, J
creators_name: Rovira, A
creators_name: Enzinger, C
creators_name: Filippi, M
creators_name: Frederiksen, J
creators_name: Ciccarelli, O
creators_name: Kappos, L
creators_name: Barkhof, F
creators_name: Vrenken, H
creators_name: MAGNIMS Study Group, .
creators_name: neuGRID, .
title: Performance of five research-domain automated WM lesion segmentation methods in a multi-center MS study
ispublished: pub
divisions: UCL
divisions: B02
divisions: C07
divisions: D07
divisions: F82
divisions: F87
keywords: Multiple sclerosis, White matter lesion, Automated methods segmentation, MRI
note: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
abstract: Background and Purpose: In vivoidentification of white matter lesions plays a key-role in evaluation of patients with multiple sclerosis (MS). Automated lesion segmentation methods have been developed to substitute manual outlining, but evidence of their performance in multi-center investigations is lacking. In this work, five research-domain automated segmentation methods were evaluated using a multi-center MS dataset. / Methods: 70 MS patients (median EDSS of 2.0 [range 0.0–6.5]) were included from a six-center dataset of the MAGNIMS Study Group (www.magnims.eu) which included 2D FLAIR and 3D T1 images with manual lesion segmentation as a reference. Automated lesion segmentations were produced using five algorithms: Cascade; Lesion Segmentation Toolbox (LST) with both the Lesion growth algorithm (LGA) and the Lesion prediction algorithm (LPA); Lesion-Topology preserving Anatomical Segmentation (Lesion-TOADS); and k-Nearest Neighbor with Tissue Type Priors (kNN-TTP). Main software parameters were optimized using a training set (N = 18), and formal testing was performed on the remaining patients (N = 52). To evaluate volumetric agreement with the reference segmentations, intraclass correlation coefficient (ICC) as well as mean difference in lesion volumes between the automated and reference segmentations were calculated. The Similarity Index (SI), False Positive (FP) volumes and False Negative (FN) volumes were used to examine spatial agreement. All analyses were repeated using a leave-one-center-out design to exclude the center of interest from the training phase to evaluate the performance of the method on ‘unseen’ center. / Results: Compared to the reference mean lesion volume (4.85 ± 7.29 mL), the methods displayed a mean difference of 1.60 ± 4.83 (Cascade), 2.31 ± 7.66 (LGA), 0.44 ± 4.68 (LPA), 1.76 ± 4.17 (Lesion-TOADS) and −1.39 ± 4.10 mL (kNN-TTP). The ICCs were 0.755, 0.713, 0.851, 0.806 and 0.723, respectively. Spatial agreement with reference segmentations was higher for LPA (SI = 0.37 ± 0.23), Lesion-TOADS (SI = 0.35 ± 0.18) and kNN-TTP (SI = 0.44 ± 0.14) than for Cascade (SI = 0.26 ± 0.17) or LGA (SI = 0.31 ± 0.23). All methods showed highly similar results when used on data from a center not used in software parameter optimization. / Conclusion: The performance of the methods in this multi-center MS dataset was moderate, but appeared to be robust even with new datasets from centers not included in training the automated methods.
date: 2017-12
date_type: published
publisher: Elsevier
official_url: http://dx.doi.org/10.1016/j.neuroimage.2017.09.011
oa_status: green
full_text_type: other
language: eng
primo: open
primo_central: open_green
verified: verified_manual
elements_id: 1418460
doi: 10.1016/j.neuroimage.2017.09.011
lyricists_name: Barkhof, Frederik
lyricists_name: Ciccarelli, Olga
lyricists_name: Yiannakas, Marios
lyricists_id: FBARK32
lyricists_id: OCICC52
lyricists_id: MYIAN77
actors_name: Flynn, Bernadette
actors_id: BFFLY94
actors_role: owner
full_text_status: public
publication: NeuroImage
volume: 163
pagerange: 106-114
issn: 1053-8119
citation:        De Sitter, A;    Steenwijk, MD;    Ruet, A;    Versteeg, A;    Liu, Y;    Van Schijndel, RA;    Pouwels, PJW;                                                                                 ... neuGRID, .; + view all <#>        De Sitter, A;  Steenwijk, MD;  Ruet, A;  Versteeg, A;  Liu, Y;  Van Schijndel, RA;  Pouwels, PJW;  Kilsdonk, ID;  Cover, KS;  Van Dijk, BW;  Ropele, S;  Rocca, MA;  Yiannakas, M;  Wattjes, MP;  Damangir, S;  Frisoni, GB;  Sastre-Garriga, J;  Rovira, A;  Enzinger, C;  Filippi, M;  Frederiksen, J;  Ciccarelli, O;  Kappos, L;  Barkhof, F;  Vrenken, H;  MAGNIMS Study Group, .;  neuGRID, .;   - view fewer <#>    (2017)    Performance of five research-domain automated WM lesion segmentation methods in a multi-center MS study.                   NeuroImage , 163    pp. 106-114.    10.1016/j.neuroimage.2017.09.011 <https://doi.org/10.1016/j.neuroimage.2017.09.011>.       Green open access   
 
document_url: https://discovery.ucl.ac.uk/id/eprint/1572458/1/de-Sitter_Performance_five_research-domain.pdf