ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2107.00583
18
28

Inter Extreme Points Geodesics for End-to-End Weakly Supervised Image Segmentation

1 July 2021
R. Dorent
Samuel Joutard
J. Shapey
A. Kujawa
Marc Modat
Sebastien Ourselin
Tom Kamiel Magda Vercauteren
ArXivPDFHTML
Abstract

We introduce InExtremIS\textit{InExtremIS}InExtremIS, a weakly supervised 3D approach to train a deep image segmentation network using particularly weak train-time annotations: only 6 extreme clicks at the boundary of the objects of interest. Our fully-automatic method is trained end-to-end and does not require any test-time annotations. From the extreme points, 3D bounding boxes are extracted around objects of interest. Then, deep geodesics connecting extreme points are generated to increase the amount of "annotated" voxels within the bounding boxes. Finally, a weakly supervised regularised loss derived from a Conditional Random Field formulation is used to encourage prediction consistency over homogeneous regions. Extensive experiments are performed on a large open dataset for Vestibular Schwannoma segmentation. InExtremIS\textit{InExtremIS}InExtremIS obtained competitive performance, approaching full supervision and outperforming significantly other weakly supervised techniques based on bounding boxes. Moreover, given a fixed annotation time budget, InExtremIS\textit{InExtremIS}InExtremIS outperforms full supervision. Our code and data are available online.

View on arXiv
Comments on this paper