Skip to Main content Skip to Navigation
Conference papers

Endoscopic video manifolds.

Selen Atasoy 1 Diana Mateus 1 Joe Lallemand Alexander Meining 2 Guang-Zhong Yang 3 Nassir Navab 1
1 CAMPAR - Computer Aided Medical Procedures & Augmented Reality
2 Klinikum rechts der isar
3 The Hamlyn Centre [London]
Abstract : Postprocedural analysis of gastrointestinal (GI) endoscopic videos is a difficult task because the videos often suffer from a large number of poor-quality frames due to the motion or out-of-focus blur, specular highlights and artefacts caused by turbid fluid inside the GI tract. Clinically, each frame of the video is examined individually by the endoscopic expert due to the lack of a suitable visualisation technique. In this work, we introduce a low dimensional representation of endoscopic videos based on a manifold learning approach. The introduced endoscopic video manifolds (EVMs) enable the clustering of poor-quality frames and grouping of different segments of the GI endoscopic video in an unsupervised manner to facilitate subsequent visual assessment. In this paper, we present two novel inter-frame similarity measures for manifold learning to create structured manifolds from complex endoscopic videos. Our experiments demonstrate that the proposed method yields high precision and recall values for uninformative frame detection (90.91% and 82.90%) and results in well-structured manifolds for scene clustering.
Document type :
Conference papers
Complete list of metadata
https://hal.inria.fr/hal-01690318
Contributor : Diana Mateus <>
Submitted on : Monday, January 22, 2018 - 9:39:46 PM
Last modification on : Tuesday, October 20, 2020 - 6:26:02 PM

Identifiers

  • HAL Id : hal-01690318, version 1
  • PUBMED : 20879345

Citation

Selen Atasoy, Diana Mateus, Joe Lallemand, Alexander Meining, Guang-Zhong Yang, et al.. Endoscopic video manifolds.. International Conference in Medical Imaging and Computer Aided Interventions (MICCAI), Sep 2010, Beijing, China. pp.437-45. ⟨hal-01690318⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

91

 

Contact                    Legal Notice                    Personal Data