Segmentation of incident lacunes during the course of ischemic cerebral small vessel diseases.

CADASIL cerebral small vessel disease clinical trial follow-up incident lacunes

Journal

Frontiers in neurology
ISSN: 1664-2295
Titre abrégé: Front Neurol
Pays: Switzerland
ID NLM: 101546899

Informations de publication

Date de publication:
2023
Historique:
received: 01 12 2022
accepted: 22 02 2023
medline: 11 4 2023
entrez: 10 4 2023
pubmed: 11 4 2023
Statut: epublish

Résumé

Lacunes represent key imaging markers of cerebral small vessel diseases (cSVDs). During their progression, incident lacunes are related to stroke manifestations and contribute to progressive cognitive and/or motor decline. Assessing new lesions has become crucial but remains time-consuming and error-prone, even for an expert. We, thus, sought to develop and validate an automatic segmentation method of incident lacunes in CADASIL caused by cysteine mutation in the EGFr domains of the NOTCH3 gene, a severe and progressive monogenic form of cSVD. Incident lacunes were identified based on difference maps of 3D T1-weighted MRIs obtained at the baseline and 2 years later. These maps were thresholded using clustering analysis and compared with results obtained by expert visual analysis, which is considered the gold standard approach. The median number of lacunes at the baseline in 30 randomly selected patients was 7 (IQR = [2, 11]). The median number of incident lacunes was 2 (IQR = [0, 3]) using the automatic method (mean time-processing: 25 s/patient) and 0.5 (IQR = [0, 2]) using the standard visual approach (mean time-processing: 8 min/patient). The complementary analysis of segmentation results is enabled to quickly remove false positives detected in specific locations and to identify true incident lesions not previously detected by the standard analysis (2 min/case). A combined approach based on automatic segmentation of incident lacunes followed by quick corrections of false positives allowed to reach high individual sensitivity (median at 0.66, IQR = [0.21, 1.00]) and global specificity scores (0.80). The automatic segmentation of incident lacunes followed by quick corrections of false positives appears promising for properly and rapidly quantifying incident lacunes in large cohorts of cSVDs.

Sections du résumé

Background UNASSIGNED
Lacunes represent key imaging markers of cerebral small vessel diseases (cSVDs). During their progression, incident lacunes are related to stroke manifestations and contribute to progressive cognitive and/or motor decline. Assessing new lesions has become crucial but remains time-consuming and error-prone, even for an expert. We, thus, sought to develop and validate an automatic segmentation method of incident lacunes in CADASIL caused by cysteine mutation in the EGFr domains of the NOTCH3 gene, a severe and progressive monogenic form of cSVD.
Methods UNASSIGNED
Incident lacunes were identified based on difference maps of 3D T1-weighted MRIs obtained at the baseline and 2 years later. These maps were thresholded using clustering analysis and compared with results obtained by expert visual analysis, which is considered the gold standard approach.
Results UNASSIGNED
The median number of lacunes at the baseline in 30 randomly selected patients was 7 (IQR = [2, 11]). The median number of incident lacunes was 2 (IQR = [0, 3]) using the automatic method (mean time-processing: 25 s/patient) and 0.5 (IQR = [0, 2]) using the standard visual approach (mean time-processing: 8 min/patient). The complementary analysis of segmentation results is enabled to quickly remove false positives detected in specific locations and to identify true incident lesions not previously detected by the standard analysis (2 min/case). A combined approach based on automatic segmentation of incident lacunes followed by quick corrections of false positives allowed to reach high individual sensitivity (median at 0.66, IQR = [0.21, 1.00]) and global specificity scores (0.80).
Conclusion UNASSIGNED
The automatic segmentation of incident lacunes followed by quick corrections of false positives appears promising for properly and rapidly quantifying incident lacunes in large cohorts of cSVDs.

Identifiants

pubmed: 37034061
doi: 10.3389/fneur.2023.1113644
pmc: PMC10076773
doi:

Types de publication

Journal Article

Langues

eng

Pagination

1113644

Informations de copyright

Copyright © 2023 Lebenberg, Zhang, Grosset, Guichard, Fernandes, Jouvent and Chabriat.

Déclaration de conflit d'intérêts

The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.

Références

Neuroinformatics. 2011 Dec;9(4):381-400
pubmed: 21373993
Nat Rev Neurol. 2020 Mar;16(3):137-153
pubmed: 32094487
J Comput Assist Tomogr. 2002 Nov-Dec;26(6):902-4
pubmed: 12488733
Brain. 2008 Aug;131(Pt 8):2201-8
pubmed: 18577545
Eur J Neurol. 2020 Aug;27(8):1588-1595
pubmed: 32348626
J Cereb Blood Flow Metab. 2020 May;40(5):909-921
pubmed: 32126874
Ann Neurol. 2019 Oct;86(4):582-592
pubmed: 31340067
Eur Stroke J. 2021 Jun;6(2):CXI-CLXII
pubmed: 34414301
J Neurol. 1998 Feb;245(2):116-22
pubmed: 9507419
Med Image Comput Comput Assist Interv. 2006;9(Pt 2):58-66
pubmed: 17354756
Lancet Neurol. 2010 Jul;9(7):689-701
pubmed: 20610345
Med Image Anal. 2008 Feb;12(1):26-41
pubmed: 17659998
Sci Rep. 2021 Apr 8;11(1):7714
pubmed: 33833297
Stroke. 2021 Aug;52(9):3025-3032
pubmed: 34399586
Brain. 2019 Apr 1;142(4):1009-1023
pubmed: 30859180
J Cereb Blood Flow Metab. 2020 Feb;40(2):231-245
pubmed: 31744377
Neuroimage Clin. 2017 Feb 04;14:391-399
pubmed: 28271039
Lancet Neurol. 2013 Aug;12(8):822-38
pubmed: 23867200
Front Neuroinform. 2022 Mar 03;16:803934
pubmed: 35311005
Hum Brain Mapp. 2005 Nov;26(3):210-20
pubmed: 16161162
Stroke. 2020 Jan;51(1):170-178
pubmed: 31699021
Lancet Neurol. 2007 Jul;6(7):611-9
pubmed: 17582361
N Engl J Med. 2003 Mar 27;348(13):1215-22
pubmed: 12660385
Brain. 2013 Sep;136(Pt 9):2717-26
pubmed: 23864274
IEEE Trans Med Imaging. 2010 Jun;29(6):1310-20
pubmed: 20378467

Auteurs

Jessica Lebenberg (J)

APHP, Lariboisière Hospital, Translational Neurovascular Centre, FHU Neurovasc, Université Paris Cité, Paris, France.
U1141, Université Paris Cité, Inserm, Neurodiderot, Paris, France.

Ruiting Zhang (R)

U1141, Université Paris Cité, Inserm, Neurodiderot, Paris, France.
Department of Radiology, School of Medicine, The Second Affiliated Hospital of Zhejiang University, Hangzhou, China.

Lina Grosset (L)

U1141, Université Paris Cité, Inserm, Neurodiderot, Paris, France.
APHP, Lariboisière Hospital, Department of Neurology, FHU NeuroVasc, Université Paris Cité, Paris, France.
Faculté de Santé, Université Paris Cité, Paris, France.

Jean Pierre Guichard (JP)

APHP, Lariboisière Hospital, Department of Neuroradiology, Université Paris Cité, Paris, France.

Fanny Fernandes (F)

APHP, Lariboisière Hospital, Translational Neurovascular Centre, FHU Neurovasc, Université Paris Cité, Paris, France.

Eric Jouvent (E)

U1141, Université Paris Cité, Inserm, Neurodiderot, Paris, France.
APHP, Lariboisière Hospital, Department of Neurology, FHU NeuroVasc, Université Paris Cité, Paris, France.
Faculté de Santé, Université Paris Cité, Paris, France.

Hugues Chabriat (H)

APHP, Lariboisière Hospital, Translational Neurovascular Centre, FHU Neurovasc, Université Paris Cité, Paris, France.
U1141, Université Paris Cité, Inserm, Neurodiderot, Paris, France.
Faculté de Santé, Université Paris Cité, Paris, France.

Classifications MeSH