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

Sergi Valverde*, Mariano Cabezas, Eloy Roura, Sandra González-Villà, Deborah Pareto, Joan C. Vilanova, Lluís Ramió-Torrentà, Àlex Rovira, Arnau Oliver, Xavier Lladó

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

262 Citations (Scopus)

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.

Original languageEnglish
Pages (from-to)159-168
Number of pages10
JournalNeuroImage
Volume155
DOIs
Publication statusPublished - 15 Jul 2017
Externally publishedYes

Keywords

  • automatic lesion segmentation
  • brain
  • convolutional neural networks
  • MRI
  • multiple sclerosis

Fingerprint

Dive into the research topics of 'Improving automated multiple sclerosis lesion segmentation with a cascaded 3D convolutional neural network approach'. Together they form a unique fingerprint.

Cite this