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

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

58 Downloads (Pure)


We introduce 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 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 outperforms full supervision. Our code and data are available online.
Original languageEnglish
Title of host publicationMedical Image Computing and Computer Assisted Intervention – MICCAI 2021
Publication statusAccepted/In press - 15 Jun 2021


  • Weak Supervision
  • Extreme Points
  • Image Segmentation


Dive into the research topics of 'Inter Extreme Points Geodesics for End-to-End Weakly Supervised Image Segmentation'. Together they form a unique fingerprint.

Cite this