LambdaUNet: 2.5D Stroke Lesion Segmentation of Diffusion-weighted MR Images

Diffusion-weighted (DW) magnetic resonance imaging is essential for the diagnosis and treatment of ischemic stroke. DW images (DWIs) are usually acquired in multi-slice settings where lesion areas in two consecutive 2D slices are highly discontinuous due to large slice thickness and sometimes even slice gaps. Therefore, although DWIs contain rich 3D information, they cannot be treated as regular 3D or 2D images. Instead, DWIs are somewhere in-between (or 2.5D) due to the volumetric nature but inter-slice discontinuities. Thus, it is not ideal to apply most existing segmentation methods as they are designed for either 2D or 3D images. To tackle this problem, we propose a new neural network architecture tailored for segmenting highly discontinuous 2.5D data such as DWIs. Our network, termed LambdaUNet, extends UNet by replacing convolutional layers with our proposed Lambda+ layers. In particular, Lambda+ layers transform both intra-slice and inter-slice context around a pixel into linear functions, called lambdas, which are then applied to the pixel to produce informative 2.5D features. LambdaUNet is simple yet effective in combining sparse inter-slice information from adjacent slices while also capturing dense contextual features within a single slice. Experiments on a unique clinical dataset demonstrate that LambdaUNet outperforms existing 3D/2D image segmentation methods including recent variants of UNet.

This version of the article has been accepted for publication, after peer review (when applicable) and is subject to Springer Nature’s AM terms of use, but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: https://doi.org/10.1007/978-3-030-87193-2_69

Files

Metadata

Work Title LambdaUNet: 2.5D Stroke Lesion Segmentation of Diffusion-weighted MR Images
Access
Open Access
Creators
  1. Yanglan Ou
  2. Ye Yuan
  3. Xiaolei Huang
  4. Kelvin Wong
  5. John Volpi
  6. James Z. Wang
  7. Stephen T. C. Wong
Keyword
  1. Stroke
  2. Lesion segmentation
  3. Inter- and Intra-slice context
  4. 2.5-Dimensional Images
License In Copyright (Rights Reserved)
Work Type Article
Publisher
  1. Springer International Publishing
Publication Date 2021
Publisher Identifier (DOI)
  1. 10.1007/978-3-030-87193-2_69
Source
  1. Medical Image Computing and Computer Assisted Intervention – MICCAI 2021
  2. Lecture Notes in Computer Science
Deposited July 19, 2022

Versions

Analytics

Collections

This resource is currently not in any collection.

Work History

Version 1
published

  • Created
  • Added ou-1.pdf
  • Added Creator Yanglan Ou
  • Added Creator Ye Yuan
  • Added Creator Xiaolei Huang
  • Added Creator Kelvin Wong
  • Added Creator John Volpi
  • Added Creator James Z. Wang
  • Added Creator Stephen T. C. Wong
  • Published
  • Updated Keyword Show Changes
    Keyword
    • Stroke, Lesion segmentation, Inter- and Intra-slice context, 2.5-Dimensional Images
  • Updated Work Title Show Changes
    Work Title
    • LambdaUNet: 2.5D Stroke Lesion Segmentation of Diffusion-weighted MR Images
    • ! LambdaUNet: 2.5D Stroke Lesion Segmentation of Diffusion-weighted MR Images
  • Updated Work Title Show Changes
    Work Title
    • ! LambdaUNet: 2.5D Stroke Lesion Segmentation of Diffusion-weighted MR Images
    • LambdaUNet: 2.5D Stroke Lesion Segmentation of Diffusion-weighted MR Images
  • Updated