Accuracy and reproducibility of automated white matter hyperintensities segmentation with lesion segmentation tool: A European multi-site 3T study - Institut de Neurosciences des Systèmes
Article Dans Une Revue Magnetic Resonance Imaging Année : 2021

Accuracy and reproducibility of automated white matter hyperintensities segmentation with lesion segmentation tool: A European multi-site 3T study

1 IRCCS - Centro San Giovanni di Dio, Fatebenefratelli, Brescia
2 Laboratory of Neuroimaging of aging, Memory clinic and LANVIE
3 CIMEC - Center for Mind/Brain Sciences
4 DINOGMI - Dipartimento di Neuroscienze, riabilitazione, oftalmologia, genetica e scienze materno-infantili [Genova]
5 UNIVR | DDSP - Department of Diagnostics and Public Health [Verona]
6 IRCCS SDN Napoli
7 Department of Clinic Sciences and Bioimaging, University G. d'Annunzio Chieti-Pescara
8 Interbalkan Medical Center of Thessaloniki
9 Dept. of Child and Adolescent Psychiatry and Psychology, Institut Clinic of Neurosciences IDIBAPS (Institut d'Investigacions Biomèdiques August Pi Sunyer)
10 Department of Child and Adolescent Psychiatry
11 Department of Neuroscience, Catholic University, Roma
12 CMIC - Centre for Medical Image Computing
13 Department of Radiology and Nuclear Medicine [Amsterdam]
14 ToNIC - Toulouse NeuroImaging Center
15 CRMBM - Centre de résonance magnétique biologique et médicale
16 CEMEREM - Centre d'Exploration Métabolique par Résonance Magnétique [Hôpital de la Timone - APHM]
17 UMG - University Medical Center Göttingen
18 Leipzig University / Universität Leipzig
19 UNIPG - Università degli Studi di Perugia = University of Perugia
20 Department of Clinic Sciences and Bioimaging, University G. d'Annunzio Chieti-Pescara
21 INS - Institut de Neurosciences des Systèmes
22 Neurology Department, Hospital Clinic, IDIBAPS, Facultad de Medicina, Barcelona
23 Dept. Neuroscience & Neurorehabilitation, IRCCS-San Raffaele-Pisana, Rome
24 Neuroradiology Unit, Perugia General Hospital, Perugia,
25 Alzheimer Center Amsterdam
26 LilNCog - Lille Neurosciences & Cognition - U 1172
27 Medical Physics Unit, Perugia General Hospital, Perugia
28 LVR-Clinic for Psychiatry and Psychotherapy, Institutes and Clinics of the University Duisburg-Essen,
29 Neurosciences Therapeutic Area, GlaxoSmithKline R&D,
Jorge Jovicich
Carlo Cavaliere
  • Fonction : Auteur
Helene Gros-Dagnac
  • Fonction : Auteur
  • PersonId : 1370060
  • IdRef : 068901356
Jens Wiltfang
Marco Aiello
  • Fonction : Auteur
Marco Salvatore
  • Fonction : Auteur
Mira Didic
Olivier Blin
Pierre Payoux
Pieter Jelle Visser

Résumé

Brain vascular damage accumulate in aging and often manifest as white matter hyperintensities (WMHs) on MRI. Despite increased interest in automated methods to segment WMHs, a gold standard has not been achieved and their longitudinal reproducibility has been poorly investigated. The aim of present work is to evaluate accuracy and reproducibility of two freely available segmentation algorithms. A harmonized MRI protocol was implemented in 3T-scanners across 13 European sites, each scanning five volunteers twice (test-retest) using 2D-FLAIR. Automated segmentation was performed using Lesion segmentation tool algorithms (LST): the Lesion growth algorithm (LGA) in SPM8 and 12 and the Lesion prediction algorithm (LPA). To assess reproducibility, we applied the LST longitudinal pipeline to the LGA and LPA outputs for both the test and retest scans. We evaluated volumetric and spatial accuracy comparing LGA and LPA with manual tracing, and for reproducibility the test versus retest. Median volume difference between automated WMH and manual segmentations (mL) was -0.22[IQR = 0.50] for LGA-SPM8, -0.12[0.57] for LGA-SPM12, -0.09[0.53] for LPA, while the spatial accuracy (Dice Coefficient) was 0.29[0.31], 0.33[0.26] and 0.41[0.23], respectively. The reproducibility analysis showed a median reproducibility error of 20%[IQR = 41] for LGA-SPM8, 14% [31] for LGA-SPM12 and 10% [27] with the LPA cross-sectional pipeline. Applying the LST longitudinal pipeline, the reproducibility errors were considerably reduced (LGA: 0%[IQR = 0], p < 0.001; LPA: 0% [3], p < 0.001) compared to those derived using the cross-sectional algorithms. The DC using the longitudinal pipeline was excellent (median = 1) for LGA [IQR = 0] and LPA [0.02]. LST algorithms showed moderate accuracy and good reproducibility. Therefore, it can be used as a reliable cross-sectional and longitudinal tool in multi-site studies.
Fichier principal
Vignette du fichier
Barkhof_Ribaldi.pdf (1.15 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03500597 , version 1 (14-09-2024)

Identifiants

Citer

Federica Ribaldi, Daniele Altomare, Jorge Jovicich, Clarissa Ferrari, Agnese Picco, et al.. Accuracy and reproducibility of automated white matter hyperintensities segmentation with lesion segmentation tool: A European multi-site 3T study. Magnetic Resonance Imaging, 2021, 76, pp.108-115. ⟨10.1016/j.mri.2020.11.008⟩. ⟨hal-03500597⟩
27 Consultations
0 Téléchargements

Altmetric

Partager

More