A toolbox for multiple sclerosis lesion segmentation

​
orcId Roura Perez, Eloy​ ​ scopusId Roura Perez, Eloy​ ​
Roura Perez, Eloy
orcId Oliver i Malagelada, Arnau​ ​ scopusId Oliver i Malagelada, Arnau​ ​
Oliver i Malagelada, Arnau
orcId Cabezas Grebol, Mariano​ researcherId Cabezas Grebol, Mariano​ scopusId Cabezas Grebol, Mariano​ ​
Cabezas Grebol, Mariano
orcId Valverde Valverde, Sergi​ ​ scopusId Valverde Valverde, Sergi​ ​
Valverde Valverde, Sergi
​ ​ ​ ​
Pareto, Deborah
orcId Vilanova, Joan Carles​ ​ scopusId Vilanova, Joan Carles​ ​
Vilanova, Joan Carles
orcId Ramió i Torrentà, Lluís​ ​ ​ ​
Ramió i Torrentà, Lluís
​ ​ ​ ​
Rovira, Àlex
orcId Lladó Bardera, Xavier​ researcherId Lladó Bardera, Xavier​ scopusId Lladó Bardera, Xavier​ ​
Lladó Bardera, Xavier
Texto Completo
Toolbox-for-multiple.pdf embargoed access ​
Solicita copia
Solicita copia
Al rellenar este formulario estáis solicitando una copia del artículo, depositado en el repositorio institucional (DUGiDocs), a su autor o al autor principal del artículo. Será el mismo autor quien decidirá enviar una copia del documento a quien lo solicite si lo considera oportuno. En todo caso, la Biblioteca de la UdG no interviene en este proceso ya que no está autorizada a facilitar artículos cuando éstos son de acceso restringido.
​
Compartir
​
Lesion segmentation plays an important role in the diagnosis and follow-up of multiple sclerosis (MS). This task is very time-consuming and subject to intra- and inter-rater variability. In this paper, we present a new tool for automated MS lesion segmentation using T1w and fluid-attenuated inversion recovery (FLAIR) images. Methods: Our approach is based on two main steps, initial brain tissue segmentation according to the gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) performed in T1w images, followed by a second step where the lesions are segmented as outliers to the normal apparent GM brain tissue on the FLAIR image. Results: The tool has been validated using data from more than 100 MS patients acquired with different scanners and at different magnetic field strengths. Quantitative evaluation provided a better performance in terms of precision while maintaining similar results on sensitivity and Dice similarity measures compared with those of other approaches. Conclusion: Our tool is implemented as a publicly available SPM8/12 extension that can be used by both the medical and research communities ​
​Tots els drets reservats
Mostrar el registro completo del ítem