E2ENet: Dynamic Sparse Feature Fusion for Accurate and Efficient 3D Medical Image Segmentation

Boqian Wu*, Qiao Xiao, Shiwei Liu, Lu Yin, Mykola Pechenizkiy, Decebal Constantin Mocanu, Maurice van Keulen, Elena Mocanu

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

12 Downloads (Pure)

Abstract

Deep neural networks have evolved as the leading approach in 3D medical image segmentation due to their outstanding performance. However, the ever-increasing model size and computation cost of deep neural networks have become the primary barrier to deploying them on real-world resource-limited hardware. In pursuit of improving performance and efficiency, we propose a 3D medical image segmentation model, named Efficient to Efficient Network (E2ENet), incorporating two parametrically and computationally efficient designs: the Dynamic Sparse Feature Fusion (DSFF) mechanism, which adaptively learns to fuse informative multi-scale features while reducing redundancy, and Restricted depth-shift in 3D convolution, which leverages the 3D spatial information while keeping the model and computational complexity as 2D-based methods. We conduct extensive experiments on BTCV, AMOS-CT, and Brain Tumor Segmentation Challenge, demonstrating that E2ENet consistently achieves a superior trade-off between accuracy and efficiency than prior arts across various resource constraints. E2ENet achieves comparable accuracy on the large-scale challenge AMOS-CT, while saving over 68% parameter count and 29% FLOPs in the inference phase compared with the previous best-performing method. Our code has been made available at: https://github.com/boqian333/E2ENet-Medical.
Original languageEnglish
Title of host publication38th Annual Conference on Neural Information Processing Systems, NeurIPS 2024
PublisherMLResearchPress
Publication statusPublished - 2024
Event38th Annual Conference on Neural Information Processing Systems, NeurIPS 2024 - Vancouver, Canada
Duration: 9 Dec 202415 Dec 2024
Conference number: 38
https://neurips.cc/Conferences/2024

Conference

Conference38th Annual Conference on Neural Information Processing Systems, NeurIPS 2024
Abbreviated titleNeurIPS 2024
Country/TerritoryCanada
CityVancouver
Period9/12/2415/12/24
Internet address

Keywords

  • Medical image segmentation
  • Sparse Training
  • Feature fusion

Fingerprint

Dive into the research topics of 'E2ENet: Dynamic Sparse Feature Fusion for Accurate and Efficient 3D Medical Image Segmentation'. Together they form a unique fingerprint.

Cite this