Adjusting the Ground Truth Annotations for Connectivity-Based Learning to Delineate

Doruk Oner, Mateusz Koziński, Lenoardo Citraro, Pascal Fua

Research output: Contribution to journalArticlepeer-review

Abstract

Deep learning-based approaches to delineating 3D structure depend on accurate annotations to train the networks. Yet in practice, people, no matter how conscientious, have trouble precisely delineating in 3D and on a large scale, in part because the data is often hard to interpret visually and in part because the 3D interfaces are awkward to use. In this paper, we introduce a method that explicitly accounts for annotation inaccuracies. To this end, we treat the annotations as active contour models that can deform themselves while preserving their topology. This enables us to jointly train the network and correct potential errors in the original annotations. The result is an approach that boosts performance of deep networks trained with potentially inaccurate annotations
Original languageEnglish
Pages (from-to)3675-3685
Number of pages11
JournalIEEE Transactions on Medical Imaging
Volume41
Issue number12
DOIs
Publication statusPublished - 1 Dec 2022

Keywords

  • Active contours
  • deep learning
  • delineation
  • neurons
  • snakes
  • vessels

ASJC Scopus subject areas

  • Software
  • Radiological and Ultrasound Technology
  • Electrical and Electronic Engineering
  • Computer Science Applications

Fingerprint

Dive into the research topics of 'Adjusting the Ground Truth Annotations for Connectivity-Based Learning to Delineate'. Together they form a unique fingerprint.

Cite this