One-shot Learning Landmarks Detection - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Conference Papers Lecture Notes in Computer Science Year : 2021

One-shot Learning Landmarks Detection

Abstract

Landmark detection in medical images is important for many clinical applications. Learning-based landmark detection is successful at solving some problems but it usually requires a large number of annotated datasets for the training stage. In addition, traditional methodsusually fail for the landmark detection of fine objects. In this paper, we tackle the issue of automatic landmark annotation in 3D volumetricimages from a single example based on a one-shot learning method. It involves the iterative training of a shallow convolutional neural network combined with a 3D registration algorithm in order to perform automatic organ localization and landmark matching. We investigated both qualitatively and quantitatively the performance of the proposed approach on clinical temporal bone CT volumes. The results show that our oneshot learning scheme converges well and leads to a good accuracy of the landmark positions.
Fichier principal
Vignette du fichier
Camera_Ready__MICCAI2021_Workshop_Landmarks_Detection.pdf (1.35 Mo) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03024759 , version 1 (26-11-2020)
hal-03024759 , version 2 (11-10-2021)

Identifiers

Cite

Zihao Wang, Clair Vandersteen, Charles Raffaelli, Nicolas Guevara, François Patou, et al.. One-shot Learning Landmarks Detection. MICCAI 2021 - Workshop on Data Augmentation, Labeling, and Imperfections, Oct 2021, strasbourg, France. pp.163-172, ⟨10.1007/978-3-030-88210-5_15⟩. ⟨hal-03024759v2⟩
274 View
592 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More