Geometric Loss for Deep Multiple Sclerosis lesion Segmentation

Abstract

Multiple sclerosis (MS) lesions occupy a small fraction of the brain volume, and are heterogeneous with regards to shape, size and locations, which poses a great challenge for training deep learning based segmentation models. We proposed a new geometric loss formula to address the data imbalance and exploit the geometric property of MS lesions. We showed that traditional region-based and boundary-aware loss functions can be associated with the formula. We further develop and instantiate two loss functions containing first- and second-order geometric information of lesion regions to enforce regularization on optimizing deep segmentation models. Experimental results on two MS lesion datasets with different scales, acquisition protocols and resolutions demonstrated the superiority of our proposed methods compared to other state-of-the-art methods.

arXiv comment5 pages, three figures

References in corpus (6)

• Adam: A Method for Stochastic Optimization
• PyTorch: An Imperative Style, High-Performance Deep Learning Library
• Boundary loss for highly unbalanced segmentation
• Asymmetric Loss Functions and Deep Densely Connected Networks for Highly Imbalanced Medical Image Segmentation: Application to Multiple Sclerosis Lesion Detection
• Multi-branch Convolutional Neural Network for Multiple Sclerosis Lesion Segmentation
• RSANet: Recurrent Slice-wise Attention Network for Multiple Sclerosis Lesion Segmentation

Cited by in corpus (4)

• Efficient Folded Attention for 3D Medical Image Reconstruction and Segmentation
• Spatially Covariant Lesion Segmentation
• NeRD: Neural Representation of Distribution for Medical Image Segmentation
• DeDA: Deep Directed Accumulator