TUHH Open Research
Help
  • Log In
    New user? Click here to register.Have you forgotten your password?
  • English
  • Deutsch
  • Communities & Collections
  • Publications
  • Research Data
  • People
  • Institutions
  • Projects
  • Statistics
  1. Home
  2. TUHH
  3. Publications
  4. PolypNextLSTM: a lightweight and fast polyp video segmentation network using ConvNext and ConvLSTM
 
Options

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

Citation Link: https://doi.org/10.15480/882.13576
Publikationstyp
Journal Article
Date Issued
2024-08-08
Sprache
English
Author(s)
Bhattacharya, Debayan  
Medizintechnische und Intelligente Systeme E-1  
Reuter, Konrad  
Behrendt, Finn  
Medizintechnische und Intelligente Systeme E-1  
Maack, Lennart  
Medizintechnische und Intelligente Systeme E-1  
Grube, Sarah  orcid-logo
Medizintechnische und Intelligente Systeme E-1  
Schlaefer, Alexander  
Medizintechnische und Intelligente Systeme E-1  
TORE-DOI
10.15480/882.13576
TORE-URI
https://hdl.handle.net/11420/49827
Journal
International journal of computer assisted radiology and surgery  
Volume
19
Issue
10
Start Page
2111
End Page
2119
Citation
International Journal of Computer Assisted Radiology and Surgery: 19 (10): 2111-2119 (2024)
Publisher DOI
10.1007/s11548-024-03244-6
Scopus ID
2-s2.0-85194505013
Publisher
Springer
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. Methods: PolypNextLSTM employs a UNet-like structure with ConvNext-Tiny as its backbone, strategically omitting the last two layers to reduce parameter overhead. Our temporal fusion module, a Convolutional Long Short Term Memory (ConvLSTM), effectively exploits temporal features. Our primary novelty lies in PolypNextLSTM, which stands out as the leanest in parameters and the fastest model, surpassing the performance of five state-of-the-art image and video-based deep learning models. The evaluation of the SUN-SEG dataset spans easy-to-detect and hard-to-detect polyp scenarios, along with videos containing challenging artefacts like fast motion and occlusion. Results: Comparison against 5 image-based and 5 video-based models demonstrates PolypNextLSTM’s superiority, achieving a Dice score of 0.7898 on the hard-to-detect polyp test set, surpassing image-based PraNet (0.7519) and video-based PNS+ (0.7486). Notably, our model excels in videos featuring complex artefacts such as ghosting and occlusion. Conclusion: PolypNextLSTM, integrating pruned ConvNext-Tiny with ConvLSTM for temporal fusion, not only exhibits superior segmentation performance but also maintains the highest frames per speed among evaluated models. Code can be found here: https://github.com/mtec-tuhh/PolypNextLSTM.
Subjects
CNN
Polyp
Segmentation
Video
MLE@TUHH
DDC Class
004: Computer Sciences
610: Medicine, Health
519: Applied Mathematics, Probabilities
Funding(s)
Projekt DEAL  
Lizenz
https://creativecommons.org/licenses/by/4.0/
Loading...
Thumbnail Image
Name

s11548-024-03244-6.pdf

Type

Main Article

Size

1.36 MB

Format

Adobe PDF

TUHH
Weiterführende Links
  • Contact
  • Send Feedback
  • Cookie settings
  • Privacy policy
  • Impress
DSpace Software

Built with DSpace-CRIS software - Extension maintained and optimized by 4Science
Design by effective webwork GmbH

  • Deutsche NationalbibliothekDeutsche Nationalbibliothek
  • ORCiD Member OrganizationORCiD Member Organization
  • DataCiteDataCite
  • Re3DataRe3Data
  • OpenDOAROpenDOAR
  • OpenAireOpenAire
  • BASE Bielefeld Academic Search EngineBASE Bielefeld Academic Search Engine
Feedback