Memory-efficient Segmentation of Volumetric High-resolution MicroCT ImagesDownload PDF

05 Dec 2021, 11:00 (edited 22 Jun 2022)MIDL 2022Readers: Everyone
  • Keywords: 3D volumetric image segmentation, high-resolution image segmentation, network design, memory-efficient network.
  • TL;DR: We propose a novel memory-efficient network architecture of 3D high-resolution image segmentation.
  • Abstract: In recent years, 3D convolutional neural networks have become the dominant approach for volumetric medical image segmentation. However, compared to their 2D counterparts, 3D networks introduce substantially more training parameters and higher requirement for the GPU memory. This has become a major limiting factor for designing and training 3D networks for high-resolution volumetric images. In this work, we propose a novel memory-efficient network architecture for 3D high-resolution image segmentation. The network incorporates both global and local features via a two-stage U-net-based cascaded framework and at the first stage, a memory-efficient U-net (meU-net) is developed. The features learnt at the two stages are connected via post-concatenation, which further improves the information flow. The proposed segmentation method is evaluated on an ultra high-resolution microCT dataset with typically 250 million voxels per volume. Experiments show that it outperforms state-of-the-art 3D segmentation methods in terms of both segmentation accuracy and memory efficiency. Our code is publicly available at: https://github.com/Virgil3706/Memory-efficient-U-net
  • Registration: I acknowledge that publication of this at MIDL and in the proceedings requires at least one of the authors to register and present the work during the conference.
  • Authorship: I confirm that I am the author of this work and that it has not been submitted to another publication before.
  • Paper Type: methodological development
  • Primary Subject Area: Segmentation
  • Secondary Subject Area: Application: Other
  • Confidentiality And Author Instructions: I read the call for papers and author instructions. I acknowledge that exceeding the page limit and/or altering the latex template can result in desk rejection.
  • Code And Data: Source Code Url: https://github.com/Virgil3706/Memory-efficient-U-net The microCT fruitfly dataset is a private dataset from a still ongoing biological study, for which restrictions apply and data sharing is not available at the moment.
5 Replies

Loading