Ítem


Automated Detection of Lupus White Matter Lesions in MRI

Brain magnetic resonance imaging provides detailed information which can be used to detectand segment white matter lesions (WML). In this work we propose an approach to automatically segment WML in Lupus patients by using T1 wandfluid-attenuated inversion recovery (FLAIR) images. Lupus WML appear as small fo calabnormal tissue observed as hyperintensities in the FLAIR images. The quantification of these WML is a key factor for the stratification of lupus patients and therefore both lesion detection and segmentation play an important role. In our approach, the T1 wimage is first used to classify the three maint issues of the brain , white matter (WM), graymatter (GM) ,and cerebro spinal fluid (CSF), while the FLAIR image is then used to detect focal WM La soutliers of its GMintensity distribution. Aset of post-processing steps based on lesionsize, tissue neighborhood, and location are used to refine the lesion candidates. The propos alise valuated on 20 patients, presenting qualitative, and quantitative results in terms of precision and sensitivity of lesion detection [True Positive Rate (62%) and Positive Prediction Value (80%), respectively] as well as segmentation accuracy [Dice Similarity Coefficient (72%)]. Obtained results illustrate the validity of the aproach to automatically detectand segment lupus lesions. Besides,our approach is publicly available as a SPM8/12 tool box extension with a simple parameter configuration

ER holds a BR-UdG2013 Ph.D. grant. SV holds a FI-DGR2013 Ph.D.grant. This work has been supported by“L aFundació la Marató de TV3”,by Retos de Investigación TIN2014-55710-R, and by MP CUdG2016/022grant

Frontiers in Neuroinformatics, 2016, vol. 10, art.33

Frontiers Media

Director: Ministerio de Economía y Competitividad (Espanya)
Autor: Roura Perez, Eloy
Sarbu, Nicolae
Oliver i Malagelada, Arnau
Valverde Valverde, Sergi
González Villà, Sandra
Cervera, Ricard
Bargalló, Núria
Lladó Bardera, Xavier
Data: 12 agost 2016
Resum: Brain magnetic resonance imaging provides detailed information which can be used to detectand segment white matter lesions (WML). In this work we propose an approach to automatically segment WML in Lupus patients by using T1 wandfluid-attenuated inversion recovery (FLAIR) images. Lupus WML appear as small fo calabnormal tissue observed as hyperintensities in the FLAIR images. The quantification of these WML is a key factor for the stratification of lupus patients and therefore both lesion detection and segmentation play an important role. In our approach, the T1 wimage is first used to classify the three maint issues of the brain , white matter (WM), graymatter (GM) ,and cerebro spinal fluid (CSF), while the FLAIR image is then used to detect focal WM La soutliers of its GMintensity distribution. Aset of post-processing steps based on lesionsize, tissue neighborhood, and location are used to refine the lesion candidates. The propos alise valuated on 20 patients, presenting qualitative, and quantitative results in terms of precision and sensitivity of lesion detection [True Positive Rate (62%) and Positive Prediction Value (80%), respectively] as well as segmentation accuracy [Dice Similarity Coefficient (72%)]. Obtained results illustrate the validity of the aproach to automatically detectand segment lupus lesions. Besides,our approach is publicly available as a SPM8/12 tool box extension with a simple parameter configuration
ER holds a BR-UdG2013 Ph.D. grant. SV holds a FI-DGR2013 Ph.D.grant. This work has been supported by“L aFundació la Marató de TV3”,by Retos de Investigación TIN2014-55710-R, and by MP CUdG2016/022grant
Format: application/pdf
Cita: 025433
ISSN: 1662-5196
Accés al document: http://hdl.handle.net/10256/13182
Llenguatge: eng
Editor: Frontiers Media
Col·lecció: MINECO/PE 2015-2017/TIN2014-55710-R
Reproducció digital del document publicat a: http://dx.doi.org/10.3389/fninf.2016.00033
Articles publicats (D-ATC)
És part de: Frontiers in Neuroinformatics, 2016, vol. 10, art.33
Drets: Attribution 3.0 Spain
URI Drets: http://creativecommons.org/licenses/by/3.0/es/
Matèria: Imatgeria per ressonància magnètica
Magnetic resonance imaging
Malalties cerebrovasculars -- Imatges per ressonància magnètica
Cerebrovascular disease -- Magnetic resonance imaging
Imatges -- Segmentació
Imaging segmentation
Imatgeria mèdica
Imaging systems in medicine
Títol: Automated Detection of Lupus White Matter Lesions in MRI
Tipus: info:eu-repo/semantics/article
Repositori: DUGiDocs

Matèries

Autors