Item


Improving automated multiple sclerosis lesion segmentation with a cascaded 3D convolutional neural network approach

In this paper, we present a novel automated method for White Matter (WM) lesion segmentation of Multiple Sclerosis (MS) patient images. Our approach is based on a cascade of two 3D patch-wise convolutional neural networks (CNN). The first network is trained to be more sensitive revealing possible candidate lesion voxels while the second network is trained to reduce the number of misclassified voxels coming from the first network. This cascaded CNN architecture tends to learn well from a small (n≤35) set of labeled data of the same MRI contrast, which can be very interesting in practice, given the difficulty to obtain manual label annotations and the large amount of available unlabeled Magnetic Resonance Imaging (MRI) data. We evaluate the accuracy of the proposed method on the public MS lesion segmentation challenge MICCAI2008 dataset, comparing it with respect to other state-of-the-art MS lesion segmentation tools. Furthermore, the proposed method is also evaluated on two private MS clinical datasets, where the performance of our method is also compared with different recent public available state-of-the-art MS lesion segmentation methods. At the time of writing this paper, our method is the best ranked approach on the MICCAI2008 challenge, outperforming the rest of 60 participant methods when using all the available input modalities (T1-w, T2-w and FLAIR), while still in the top-rank (3rd position) when using only T1-w and FLAIR modalities. On clinical MS data, our approach exhibits a significant increase in the accuracy segmenting of WM lesions when compared with the rest of evaluated methods, highly correlating (r≥0.97) also with the expected lesion volume

This work has been partially supported by “La Fundació la Marató de TV3”, by Retos de InvestigaciónTIN2014-55710-R, and by the MPC UdG 2016/022 grant

© NeuroImage, 2017, vol. 155, p. 159-168

Elsevier

Author: Valverde Valverde, Sergi
Cabezas Grebol, Mariano
Roura Perez, Eloy
González Villà, Sandra
Pareto, Deborah
Vilanova Busquets, Joan Carles
Ramió i Torrentà, Lluís
Rovira, Àlex
Oliver i Malagelada, Arnau
Lladó Bardera, Xavier
Date: 2017 July 15
Abstract: In this paper, we present a novel automated method for White Matter (WM) lesion segmentation of Multiple Sclerosis (MS) patient images. Our approach is based on a cascade of two 3D patch-wise convolutional neural networks (CNN). The first network is trained to be more sensitive revealing possible candidate lesion voxels while the second network is trained to reduce the number of misclassified voxels coming from the first network. This cascaded CNN architecture tends to learn well from a small (n≤35) set of labeled data of the same MRI contrast, which can be very interesting in practice, given the difficulty to obtain manual label annotations and the large amount of available unlabeled Magnetic Resonance Imaging (MRI) data. We evaluate the accuracy of the proposed method on the public MS lesion segmentation challenge MICCAI2008 dataset, comparing it with respect to other state-of-the-art MS lesion segmentation tools. Furthermore, the proposed method is also evaluated on two private MS clinical datasets, where the performance of our method is also compared with different recent public available state-of-the-art MS lesion segmentation methods. At the time of writing this paper, our method is the best ranked approach on the MICCAI2008 challenge, outperforming the rest of 60 participant methods when using all the available input modalities (T1-w, T2-w and FLAIR), while still in the top-rank (3rd position) when using only T1-w and FLAIR modalities. On clinical MS data, our approach exhibits a significant increase in the accuracy segmenting of WM lesions when compared with the rest of evaluated methods, highly correlating (r≥0.97) also with the expected lesion volume
This work has been partially supported by “La Fundació la Marató de TV3”, by Retos de InvestigaciónTIN2014-55710-R, and by the MPC UdG 2016/022 grant
Format: application/pdf
Citation: https://doi.org/10.1016/j.neuroimage.2017.04.034
ISSN: 1053-8119
Document access: http://hdl.handle.net/10256/14477
Language: eng
Publisher: Elsevier
Collection: MINECO/PE 2015-2017/TIN2014-55710-R
Reproducció digital del document publicat a: https://doi.org/10.1016/j.neuroimage.2017.04.034
Articles publicats (D-ATC)
Is part of: © NeuroImage, 2017, vol. 155, p. 159-168
Rights: Tots els drets reservats
Subject: Esclerosi múltiple
Multiple sclerosis
Imatge -- Segmentació
Imaging segmentation
Imatges -- Processament -- Tècniques digitals
Image processing -- Digital techniques
Imatges -- Processament
Image processing
Imatgeria tridimensional
Three-dimensional imaging
Title: Improving automated multiple sclerosis lesion segmentation with a cascaded 3D convolutional neural network approach
Type: info:eu-repo/semantics/article
Repository: DUGiDocs

Subjects

Authors