Journal Article

DZNE-2023-00191

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Performance evaluation of automated white matter hyperintensity segmentation algorithms in a multicenter cohort on cognitive impairment and dementia

Gaubert, M. (First author)DZNE* ; Dell Orco, A.DZNE* ; Lange, C.DZNE* ; Garnier-Crussard, A. ; Zimmermann, I.DZNE* ; Dyrba, M.DZNE* ; Duering, M. ; Ziegler, G.DZNE* ; Peters, O.DZNE* ; Preis, L.Extern* ; Priller, J.DZNE* ; Spruth, E. J.DZNE* ; Schneider, A.DZNE* ; Fliessbach, K.DZNE* ; Wiltfang, J.DZNE* ; Schott, B. H.DZNE* ; Maier, F. ; Glanz, W.DZNE* ; Buerger, K.DZNE* ; Janowitz, D.DZNE* ; Perneczky, R.DZNE* ; Rauchmann, B.-S.Extern* ; Teipel, S.DZNE* ; Kilimann, I.DZNE* ; Laske, C.DZNE* ; Munk, M. H.DZNE* ; Spottke, A.DZNE* ; Roy, N.DZNE* ; Dobisch, L.DZNE* ; Ewers, M.DZNE* ; Dechent, P. ; Haynes, J. D. ; Scheffler, K. ; Düzel, E.DZNE* ; Jessen, F.DZNE* ; Wirth, M. (Last author)DZNE*

2023
Frontiers Research Foundation Lausanne

This record in other databases:    

Please use a persistent id in citations: doi:10.3389/fpsyt.2022.1010273

Abstract: White matter hyperintensities (WMH), a biomarker of small vessel disease, are often found in Alzheimer's disease (AD) and their advanced detection and quantification can be beneficial for research and clinical applications. To investigate WMH in large-scale multicenter studies on cognitive impairment and AD, appropriate automated WMH segmentation algorithms are required. This study aimed to compare the performance of segmentation tools and provide information on their application in multicenter research.We used a pseudo-randomly selected dataset (n = 50) from the DZNE-multicenter observational Longitudinal Cognitive Impairment and Dementia Study (DELCODE) that included 3D fluid-attenuated inversion recovery (FLAIR) images from participants across the cognitive continuum. Performances of top-rated algorithms for automated WMH segmentation [Brain Intensity Abnormality Classification Algorithm (BIANCA), lesion segmentation toolbox (LST), lesion growth algorithm (LGA), LST lesion prediction algorithm (LPA), pgs, and sysu_media] were compared to manual reference segmentation (RS).Across tools, segmentation performance was moderate for global WMH volume and number of detected lesions. After retraining on a DELCODE subset, the deep learning algorithm sysu_media showed the highest performances with an average Dice's coefficient of 0.702 (±0.109 SD) for volume and a mean F1-score of 0.642 (±0.109 SD) for the number of lesions. The intra-class correlation was excellent for all algorithms (>0.9) but BIANCA (0.835). Performance improved with high WMH burden and varied across brain regions.To conclude, the deep learning algorithm, when retrained, performed well in the multicenter context. Nevertheless, the performance was close to traditional methods. We provide methodological recommendations for future studies using automated WMH segmentation to quantify and assess WMH along the continuum of cognitive impairment and AD dementia.

Keyword(s): Alzheimer’s disease ; Alzheimer’s disease ; FLAIR ; aging ; deep learning ; evaluation ; white matter hyperintensities segmentation

Note: The DELCODE study was funded by the German Center for Neurodegenerative Diseases (reference no. BN012). The DELCODE study was supported by the Max-Delbrück-centrum für Molekulare Medizin in der Helmholtz-Gemeinschaft (MDC), Freie Universität Berlin Center for Cognitive Neuroscience Berlin (CCNB), Nuklearmedizin und Klinische Molekulare Bildgebung—Univeristätsklinikum Tübingen Bernstein Center für Computional Neuroscience Berlin, Universitätsmedizin Göttingen Core Facility MR-Research Göttingen, Institut für Klinische Radiologie Klinikum der Universität München, and Universitätsklinikum Tübingen MR-Forschungszentrum.

---

Contributing Institute(s):

1. Brain Resilience (AG Wirth)
2. Clinical Planning and Intersite Group (AG Donix)
3. Clinical Neurophysiology and Memory (AG Düzel)
4. Clinical Dementia Research (Rostock /Greifswald) (AG Teipel)
5. Vascular Pathology (AG Dirnagl)
6. Translational Neuropsychiatry (AG Priller)
7. Interdisciplinary Dementia Research (AG Endres)
8. Translational Dementia Research (Bonn) (AG Schneider)
9. Patient Studies Bonn (Patient Studies Bonn)
10. Molecular biomarkers for predictive diagnostics of neurodegenerative diseases (AG Wiltfang)
11. Epigenetics and Systems Medicine in Neurodegenerative Diseases (AG Fischer)
12. Clinical Alzheimer’s Disease Research (AG Jessen)
13. Vascular Cognitive Impairment & Post-Stroke Dementia (AG Dichgans)
14. Clinical Research Platform (CRP) (Clinical Research Platform (CRP))
15. Molecular Neurobiology (AG Simons)
16. Delcode (Delcode)

Research Program(s):

1. 353 - Clinical and Health Care Research (POF4-353) (POF4-353)
2. 352 - Disease Mechanisms (POF4-352) (POF4-352)
3. 351 - Brain Function (POF4-351) (POF4-351)

Experiment(s):

1. Longitudinal Cognitive Impairment and Dementia Study

Appears in the scientific report 2023

---

Database coverage:
; ; ; ; Article Processing Charges ; Clarivate Analytics Master Journal List ; Current Contents - Clinical Medicine ; Current Contents - Social and Behavioral Sciences ; DOAJ Seal ; Essential Science Indicators ; Fees ; IF < 5 ; JCR ; PubMed Central ; SCOPUS ; Science Citation Index Expanded ; Social Sciences Citation Index ; Web of Science Core Collection

---

---

Linked articles:

http://join2-wiki.gsi.de/foswiki/pub/Main/Artwork/join2_logo100x88.png Software Dell Orco, A.DZNE* ; Gaubert, M.DZNE*
Software: WMHpypes: Nipype based implementations of WMH segmentation pipelines (v1)
Zenodo (2022) [10.5281/ZENODO.5831210]2022   Fulltext BibTeX | EndNote: XML, Text | RIS

---