PolypNextLSTM: a lightweight and fast polyp video segmentation network using ConvNext and ConvLSTM.

Journal: International journal of computer assisted radiology and surgery
Published Date: Aug 8, 2024

Abstract

PURPOSE: Commonly employed in polyp segmentation, single-image UNet architectures lack the temporal insight clinicians gain from video data in diagnosing polyps. To mirror clinical practices more faithfully, our proposed solution, PolypNextLSTM, leverages video-based deep learning, harnessing temporal information for superior segmentation performance with least parameter overhead, making it possibly suitable for edge devices.

Authors

  • Debayan Bhattacharya
    Institute of Medical Technology and Intelligent Systems, Hamburg University of Technology, 21073, Hamburg, Germany.
  • Konrad Reuter
    Institute of Medical Technology and Intelligent Systems, Technische Universitaet Hamburg, Hamburg, Germany. konrad.reuter@tuhh.de.
  • Finn Behrendt
    Institute of Medical Technology and Intelligent Systems, Hamburg University of Technology, Hamburg, Germany.
  • Lennart Maack
    Institute of Medical Technology and Intelligent Systems, Technische Universitaet Hamburg, Hamburg, Germany.
  • Sarah Grube
    Institute of Medical Technology and Intelligent Systems, Hamburg University of Technology, Hamburg, Germany. sarah.grube@tuhh.de.
  • Alexander Schlaefer
    Institute of Medical Technology, Hamburg University of Technology, Hamburg, Germany. schlaefer@tuhh.de.

Keywords

External Resources

Popular Topics
Recent Journals