Where is VALDO? VAscular Lesions Detection and segmentatiOn challenge at MICCAI 2021
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
Where is VALDO? VAscular Lesions Detection and segmentatiOn challenge at MICCAI 2021. / ALFA study.
In: Medical Image Analysis, Vol. 91, 103029, 2024.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - Where is VALDO?
T2 - VAscular Lesions Detection and segmentatiOn challenge at MICCAI 2021
AU - Sudre, Carole H
AU - Van Wijnen, Kimberlin
AU - Dubost, Florian
AU - Adams, Hieab
AU - Atkinson, David
AU - Barkhof, Frederik
AU - Birhanu, Mahlet A
AU - Bron, Esther E
AU - Camarasa, Robin
AU - Chaturvedi, Nish
AU - Chen, Yuan
AU - Chen, Zihao
AU - Chen, Shuai
AU - Dou, Qi
AU - Evans, Tavia
AU - Ezhov, Ivan
AU - Gao, Haojun
AU - Girones Sanguesa, Marta
AU - Gispert, Juan Domingo
AU - Gomez Anson, Beatriz
AU - Hughes, Alun D
AU - Ikram, M Arfan
AU - Ingala, Silvia
AU - Jaeger, H Rolf
AU - Kofler, Florian
AU - Kuijf, Hugo J
AU - Kutnar, Denis
AU - Lee, Minho
AU - Li, Bo
AU - Lorenzini, Luigi
AU - Menze, Bjoern
AU - Molinuevo, Jose Luis
AU - Pan, Yiwei
AU - Puybareau, Elodie
AU - Rehwald, Rafael
AU - Su, Ruisheng
AU - Shi, Pengcheng
AU - Smith, Lorna
AU - Tillin, Therese
AU - Tochon, Guillaume
AU - Urien, Hélène
AU - van der Velden, Bas H M
AU - van der Velpen, Isabelle F
AU - Wiestler, Benedikt
AU - Wolters, Frank J
AU - Yilmaz, Pinar
AU - de Groot, Marius
AU - Vernooij, Meike W
AU - de Bruijne, Marleen
AU - ALFA study
N1 - Copyright © 2023 The Author(s). Published by Elsevier B.V. All rights reserved.
PY - 2024
Y1 - 2024
N2 - Imaging markers of cerebral small vessel disease provide valuable information on brain health, but their manual assessment is time-consuming and hampered by substantial intra- and interrater variability. Automated rating may benefit biomedical research, as well as clinical assessment, but diagnostic reliability of existing algorithms is unknown. Here, we present the results of the VAscular Lesions DetectiOn and Segmentation (Where is VALDO?) challenge that was run as a satellite event at the international conference on Medical Image Computing and Computer Aided Intervention (MICCAI) 2021. This challenge aimed to promote the development of methods for automated detection and segmentation of small and sparse imaging markers of cerebral small vessel disease, namely enlarged perivascular spaces (EPVS) (Task 1), cerebral microbleeds (Task 2) and lacunes of presumed vascular origin (Task 3) while leveraging weak and noisy labels. Overall, 12 teams participated in the challenge proposing solutions for one or more tasks (4 for Task 1-EPVS, 9 for Task 2-Microbleeds and 6 for Task 3-Lacunes). Multi-cohort data was used in both training and evaluation. Results showed a large variability in performance both across teams and across tasks, with promising results notably for Task 1-EPVS and Task 2-Microbleeds and not practically useful results yet for Task 3-Lacunes. It also highlighted the performance inconsistency across cases that may deter use at an individual level, while still proving useful at a population level.
AB - Imaging markers of cerebral small vessel disease provide valuable information on brain health, but their manual assessment is time-consuming and hampered by substantial intra- and interrater variability. Automated rating may benefit biomedical research, as well as clinical assessment, but diagnostic reliability of existing algorithms is unknown. Here, we present the results of the VAscular Lesions DetectiOn and Segmentation (Where is VALDO?) challenge that was run as a satellite event at the international conference on Medical Image Computing and Computer Aided Intervention (MICCAI) 2021. This challenge aimed to promote the development of methods for automated detection and segmentation of small and sparse imaging markers of cerebral small vessel disease, namely enlarged perivascular spaces (EPVS) (Task 1), cerebral microbleeds (Task 2) and lacunes of presumed vascular origin (Task 3) while leveraging weak and noisy labels. Overall, 12 teams participated in the challenge proposing solutions for one or more tasks (4 for Task 1-EPVS, 9 for Task 2-Microbleeds and 6 for Task 3-Lacunes). Multi-cohort data was used in both training and evaluation. Results showed a large variability in performance both across teams and across tasks, with promising results notably for Task 1-EPVS and Task 2-Microbleeds and not practically useful results yet for Task 3-Lacunes. It also highlighted the performance inconsistency across cases that may deter use at an individual level, while still proving useful at a population level.
U2 - 10.1016/j.media.2023.103029
DO - 10.1016/j.media.2023.103029
M3 - Journal article
C2 - 37988921
VL - 91
JO - Medical Image Analysis
JF - Medical Image Analysis
SN - 1361-8415
M1 - 103029
ER -
ID: 375725811