Deep-learning-based 2.5D flow field estimation for maximum intensity projections of 4D optical coherence tomography

Show simple item record

dc.identifier.uri http://dx.doi.org/10.15488/10257
dc.identifier.uri https://www.repo.uni-hannover.de/handle/123456789/10330
dc.contributor.author Laves, Max-Heinrich
dc.contributor.author Ihler, Sontje
dc.contributor.author Kahrs, Lüder A.
dc.contributor.author Ortmaier, Tobias
dc.date.accessioned 2020-12-08T15:27:04Z
dc.date.available 2020-12-08T15:27:04Z
dc.date.issued 2019
dc.identifier.citation Laves, M.-H.; Ihler, S.; Kahrs, L.A.; Ortmaier, T.: Deep-learning-based 2.5D flow field estimation for maximum intensity projections of 4D optical coherence tomography. In: Proceedings of SPIE 10951 (2019), 109510R. DOI: https://doi.org/10.1117/12.2512952
dc.description.abstract In microsurgery, lasers have emerged as precise tools for bone ablation. A challenge is automatic control of laser bone ablation with 4D optical coherence tomography (OCT). OCT as high resolution imaging modality provides volumetric images of tissue and foresees information of bone position and orientation (pose) as well as thickness. However, existing approaches for OCT based laser ablation control rely on external tracking systems or invasively ablated artificial landmarks for tracking the pose of the OCT probe relative to the tissue. This can be superseded by estimating the scene flow caused by relative movement between OCT-based laser ablation system and patient. Therefore, this paper deals with 2.5D scene flow estimation of volumetric OCT images for application in laser ablation. We present a semi-supervised convolutional neural network based tracking scheme for subsequent 3D OCT volumes and apply it to a realistic semi-synthetic data set of ex vivo human temporal bone specimen. The scene flow is estimated in a two-stage approach. In the first stage, 2D lateral scene flow is computed on census-transformed en-face arguments-of-maximum intensity projections. Subsequent to this, the projections are warped by predicted lateral flow and 1D depth flow is estimated. The neural network is trained semi-supervised by combining error to ground truth and the reconstruction error of warped images with assumptions of spatial flow smoothness. Quantitative evaluation reveals a mean endpoint error of (4.7 ± 3.5) voxel or (27.5 ± 20.5) μm for scene flow estimation caused by simulated relative movement between the OCT probe and bone. The scene flow estimation for 4D OCT enables its use for markerless tracking of mastoid bone structures for image guidance in general, and automated laser ablation control. © 2019 SPIE. eng
dc.language.iso eng
dc.publisher Bellingham : SPIE
dc.relation.ispartofseries Proceedings of SPIE 10951 (2019)
dc.rights Es gilt deutsches Urheberrecht. Das Dokument darf zum eigenen Gebrauch kostenfrei genutzt, aber nicht im Internet bereitgestellt oder an Außenstehende weitergegeben werden. Dieser Beitrag ist aufgrund einer (DFG-geförderten) Allianz- bzw. Nationallizenz frei zugänglich.
dc.subject Cochlear implantation eng
dc.subject Laser control eng
dc.subject Microsurgery eng
dc.subject Optical flow eng
dc.subject Scene flow eng
dc.subject Tracking eng
dc.subject.ddc 620 | Ingenieurwissenschaften und Maschinenbau ger
dc.title Deep-learning-based 2.5D flow field estimation for maximum intensity projections of 4D optical coherence tomography eng
dc.type conferenceObject
dc.type article
dc.type Text
dc.relation.doi https://doi.org/10.1117/12.2512952
dc.bibliographicCitation.volume 10951
dc.bibliographicCitation.firstPage 109510R
dc.description.version publishedVersion
tib.accessRights frei zug�nglich


Files in this item

This item appears in the following Collection(s):

Show simple item record

 

Search the repository


Browse

My Account

Usage Statistics