Research
Print page Print page
Switch language
Rigshospitalet - a part of Copenhagen University Hospital
Published

Performance of five research-domain automated WM lesion segmentation methods in a multi-center MS study

Research output: Contribution to journalJournal articleResearchpeer-review

  1. Validity and reliability of extrastriatal [11C]raclopride binding quantification in the living human brain

    Research output: Contribution to journalJournal articleResearchpeer-review

  2. Optimization of preprocessing strategies in Positron Emission Tomography (PET) neuroimaging: A [11C]DASB PET study

    Research output: Contribution to journalJournal articleResearchpeer-review

  3. Functional neuroimaging of recovery from motor conversion disorder: A case report

    Research output: Contribution to journalJournal articleResearchpeer-review

  4. Comparing fully automated state-of-the-art cerebellum parcellation from magnetic resonance images

    Research output: Contribution to journalJournal articleResearchpeer-review

  5. Men with high serotonin 1B receptor binding respond to provocations with heightened amygdala reactivity

    Research output: Contribution to journalJournal articleResearchpeer-review

  1. Functional-structural assessment of the optic pathways in patients with optic neuritis

    Research output: Contribution to journalJournal articleResearchpeer-review

  2. Facing privacy in neuroimaging: removing facial features degrades performance of image analysis methods

    Research output: Contribution to journalJournal articleResearchpeer-review

  3. Randomized trial of daily high-dose vitamin D3 in patients with RRMS receiving subcutaneous interferon β-1a

    Research output: Contribution to journalJournal articleResearchpeer-review

  4. Author response: Nationwide prevalence and incidence study of neuromyelitis optica spectrum disorder in Denmark

    Research output: Contribution to journalComment/debateResearchpeer-review

  5. Treatment escalation leads to fewer relapses compared with switching to another moderately effective therapy

    Research output: Contribution to journalJournal articleResearchpeer-review

  • Alexandra de Sitter
  • Martijn D Steenwijk
  • Aurélie Ruet
  • Adriaan Versteeg
  • Yaou Liu
  • Ronald A van Schijndel
  • Petra J W Pouwels
  • Iris D Kilsdonk
  • Keith S Cover
  • Bob W van Dijk
  • Stefan Ropele
  • Maria A Rocca
  • Marios Yiannakas
  • Mike P Wattjes
  • Soheil Damangir
  • Giovanni B Frisoni
  • Jaume Sastre-Garriga
  • Alex Rovira
  • Christian Enzinger
  • Massimo Filippi
  • Jette Frederiksen
  • Olga Ciccarelli
  • Ludwig Kappos
  • Frederik Barkhof
  • Hugo Vrenken
  • MAGNIMS study group and for neuGRID
View graph of relations

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.

Original languageEnglish
JournalNeuroImage
Volume163
Pages (from-to)106-114
Number of pages9
ISSN1053-8119
DOIs
Publication statusPublished - Dec 2017

    Research areas

  • Journal Article

ID: 52168785