Multi-branch Convolutional Neural Network for Multiple Sclerosis Lesion Segmentation

Abstract

In this paper, we present an automated approach for segmenting multiple sclerosis (MS) lesions from multi-modal brain magnetic resonance images. Our method is based on a deep end-to-end 2D convolutional neural network (CNN) for slice-based segmentation of 3D volumetric data. The proposed CNN includes a multi-branch downsampling path, which enables the network to encode information from multiple modalities separately. Multi-scale feature fusion blocks are proposed to combine feature maps from different modalities at different stages of the network. Then, multi-scale feature upsampling blocks are introduced to upsize combined feature maps to leverage information from lesion shape and location. We trained and tested the proposed model using orthogonal plane orientations of each 3D modality to exploit the contextual information in all directions. The proposed pipeline is evaluated on two different datasets: a private dataset including 37 MS patients and a publicly available dataset known as the ISBI 2015 longitudinal MS lesion segmentation challenge dataset, consisting of 14 MS patients. Considering the ISBI challenge, at the time of submission, our method was amongst the top performing solutions. On the private dataset, using the same array of performance metrics as in the ISBI challenge, the proposed approach shows high improvements in MS lesion segmentation compared with other publicly available tools.

arXiv commentThis paper has been accepted for publication in NeuroImage

References in corpus (10)

• Adam: A Method for Stochastic Optimization
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Brain Tumor Segmentation with Deep Neural Networks
• Fully Convolutional Networks for Semantic Segmentation
• Automatic segmentation of MR brain images with a convolutional neural network
• Deep Multi-scale Location-aware 3D Convolutional Neural Networks for Automated Detection of Lacunes of Presumed Vascular Origin
• DCAN: Deep Contour-Aware Networks for Accurate Gland Segmentation
• Highly Efficient Forward and Backward Propagation of Convolutional Neural Networks for Pixelwise Classification
• Multiple Sclerosis Lesion Segmentation from Brain MRI via Fully Convolutional Neural Networks
• DeepVesselNet: Vessel Segmentation, Centerline Prediction, and Bifurcation Detection in 3-D Angiographic Volumes

Cited by in corpus (14)

• Applications of Deep Learning Techniques for Automated Multiple Sclerosis Detection Using Magnetic Resonance Imaging: A Review
• DeepLesionBrain: Towards a broader deep-learning generalization for multiple sclerosis lesion segmentation
• Boosting multiple sclerosis lesion segmentation through attention mechanism
• Geometric Loss for Deep Multiple Sclerosis lesion Segmentation
• Ensembling Low Precision Models for Binary Biomedical Image Segmentation
• Hyper-Convolution Networks for Biomedical Image Segmentation
• Spatially Covariant Lesion Segmentation
• Automatic acute ischemic stroke lesion segmentation using semi-supervised learning
• UNISELF: A Unified Network with Instance Normalization and Self-Ensembled Lesion Fusion for Multiple Sclerosis Lesion Segmentation
• Multiple Sclerosis Lesion Segmentation -- A Survey of Supervised CNN-Based Methods
• Latent Space Analysis of VAE and Intro-VAE applied to 3-dimensional MR Brain Volumes of Multiple Sclerosis, Leukoencephalopathy, and Healthy Patients
• Self-supervised Lesion Change Detection and Localisation in Longitudinal Multiple Sclerosis Brain Imaging
• VeMo: A Lightweight Data-Driven Approach to Model Vehicle Dynamics
• Radio Galaxy Zoo: Giant Radio Galaxy Classification using Multi-Domain Deep Learning