Feature tracking for automated volume of interest stabilization on 4D-OCT images

Max-Heinrich Laves; Andreas Schoob; Lüder A. Kahrs; Tom Pfeiffer; Robert Huber; Tobias Ortmaier

doi:10.1117/12.2255090

Feature tracking for automated volume of interest stabilization on 4D-OCT images

Max-Heinrich Laves, Andreas Schoob, Lüder A. Kahrs, Tom Pfeiffer, Robert Huber, Tobias Ortmaier

Institute of Biomedical Optics

University of Hanover

Abstract

A common representation of volumetric medical image data is the triplanar view (TV), in which the surgeon manually selects slices showing the anatomical structure of interest. In addition to common medical imaging such as MRI or computed tomography, recent advances in the field of optical coherence tomography (OCT) have enabled live processing and volumetric rendering of four-dimensional images of the human body. Due to the region of interest undergoing motion, it is challenging for the surgeon to simultaneously keep track of an object by continuously adjusting the TV to desired slices. To select these slices in subsequent frames automatically, it is necessary to track movements of the volume of interest (VOI). This has not been addressed with respect to 4DOCT images yet. Therefore, this paper evaluates motion tracking by applying state-of-the-art tracking schemes on maximum intensity projections (MIP) of 4D-OCT images. Estimated VOI location is used to conveniently show corresponding slices and to improve the MIPs by calculating thin-slab MIPs. Tracking performances are evaluated on an in-vivo sequence of human skin, captured at 26 volumes per second. Among investigated tracking schemes, our recently presented tracking scheme for soft tissue motion provides highest accuracy with an error of under 2.2 voxels for the first 80 volumes. Object tracking on 4D-OCT images enables its use for sub-epithelial tracking of microvessels for image-guidance.

Original language	English
Title of host publication	Medical Imaging 2017: Image-Guided Procedures, Robotic Interventions, and Modeling
Editors	Baowei Fei, Robert J. Webster
Number of pages	7
Volume	10135
Publisher	SPIE
Publication date	03.03.2017
Pages	101350W-101350W-7
ISBN (Print)	978-151060715-6
DOIs	https://doi.org/10.1117/12.2255090
Publication status	Published - 03.03.2017
Event	Medical Imaging 2017: Image-Guided Procedures, Robotic Interventions, and Modeling - Orlando, United States Duration: 14.02.2017 → 16.02.2017

Research Areas and Centers

Academic Focus: Biomedical Engineering

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1117/12.2255090

Cite this

Laves, M-H., Schoob, A., Kahrs, L. A., Pfeiffer, T., Huber, R., & Ortmaier, T. (2017). Feature tracking for automated volume of interest stabilization on 4D-OCT images. In B. Fei, & R. J. Webster (Eds.), Medical Imaging 2017: Image-Guided Procedures, Robotic Interventions, and Modeling (Vol. 10135, pp. 101350W-101350W-7). (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 10135). SPIE. https://doi.org/10.1117/12.2255090

Laves, Max-Heinrich ; Schoob, Andreas ; Kahrs, Lüder A. et al. / Feature tracking for automated volume of interest stabilization on 4D-OCT images. Medical Imaging 2017: Image-Guided Procedures, Robotic Interventions, and Modeling. editor / Baowei Fei ; Robert J. Webster. Vol. 10135 SPIE, 2017. pp. 101350W-101350W-7 (Progress in Biomedical Optics and Imaging - Proceedings of SPIE).

@inproceedings{5fa346c793a7405c88c810a3b691a4f8,

title = "Feature tracking for automated volume of interest stabilization on 4D-OCT images",

abstract = "A common representation of volumetric medical image data is the triplanar view (TV), in which the surgeon manually selects slices showing the anatomical structure of interest. In addition to common medical imaging such as MRI or computed tomography, recent advances in the field of optical coherence tomography (OCT) have enabled live processing and volumetric rendering of four-dimensional images of the human body. Due to the region of interest undergoing motion, it is challenging for the surgeon to simultaneously keep track of an object by continuously adjusting the TV to desired slices. To select these slices in subsequent frames automatically, it is necessary to track movements of the volume of interest (VOI). This has not been addressed with respect to 4DOCT images yet. Therefore, this paper evaluates motion tracking by applying state-of-the-art tracking schemes on maximum intensity projections (MIP) of 4D-OCT images. Estimated VOI location is used to conveniently show corresponding slices and to improve the MIPs by calculating thin-slab MIPs. Tracking performances are evaluated on an in-vivo sequence of human skin, captured at 26 volumes per second. Among investigated tracking schemes, our recently presented tracking scheme for soft tissue motion provides highest accuracy with an error of under 2.2 voxels for the first 80 volumes. Object tracking on 4D-OCT images enables its use for sub-epithelial tracking of microvessels for image-guidance.",

author = "Max-Heinrich Laves and Andreas Schoob and Kahrs, {L{\"u}der A.} and Tom Pfeiffer and Robert Huber and Tobias Ortmaier",

year = "2017",

month = mar,

day = "3",

doi = "10.1117/12.2255090",

language = "English",

isbn = "978-151060715-6",

volume = "10135",

series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

publisher = "SPIE",

pages = "101350W--101350W--7",

editor = "Fei, {Baowei } and Webster, {Robert J. }",

booktitle = "Medical Imaging 2017: Image-Guided Procedures, Robotic Interventions, and Modeling",

note = "Medical Imaging 2017: Image-Guided Procedures, Robotic Interventions, and Modeling ; Conference date: 14-02-2017 Through 16-02-2017",

}

Laves, M-H, Schoob, A, Kahrs, LA, Pfeiffer, T, Huber, R & Ortmaier, T 2017, Feature tracking for automated volume of interest stabilization on 4D-OCT images. in B Fei & RJ Webster (eds), Medical Imaging 2017: Image-Guided Procedures, Robotic Interventions, and Modeling. vol. 10135, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 10135, SPIE, pp. 101350W-101350W-7, Medical Imaging 2017: Image-Guided Procedures, Robotic Interventions, and Modeling, Orlando, Florida, United States, 14.02.17. https://doi.org/10.1117/12.2255090

Feature tracking for automated volume of interest stabilization on 4D-OCT images. / Laves, Max-Heinrich; Schoob, Andreas; Kahrs, Lüder A. et al.
Medical Imaging 2017: Image-Guided Procedures, Robotic Interventions, and Modeling. ed. / Baowei Fei; Robert J. Webster. Vol. 10135 SPIE, 2017. p. 101350W-101350W-7 (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Vol. 10135).

Research output: Chapters in Books/Reports/Conference Proceedings › Conference contribution › peer-review

TY - GEN

T1 - Feature tracking for automated volume of interest stabilization on 4D-OCT images

AU - Laves, Max-Heinrich

AU - Schoob, Andreas

AU - Kahrs, Lüder A.

AU - Pfeiffer, Tom

AU - Huber, Robert

AU - Ortmaier, Tobias

PY - 2017/3/3

Y1 - 2017/3/3

N2 - A common representation of volumetric medical image data is the triplanar view (TV), in which the surgeon manually selects slices showing the anatomical structure of interest. In addition to common medical imaging such as MRI or computed tomography, recent advances in the field of optical coherence tomography (OCT) have enabled live processing and volumetric rendering of four-dimensional images of the human body. Due to the region of interest undergoing motion, it is challenging for the surgeon to simultaneously keep track of an object by continuously adjusting the TV to desired slices. To select these slices in subsequent frames automatically, it is necessary to track movements of the volume of interest (VOI). This has not been addressed with respect to 4DOCT images yet. Therefore, this paper evaluates motion tracking by applying state-of-the-art tracking schemes on maximum intensity projections (MIP) of 4D-OCT images. Estimated VOI location is used to conveniently show corresponding slices and to improve the MIPs by calculating thin-slab MIPs. Tracking performances are evaluated on an in-vivo sequence of human skin, captured at 26 volumes per second. Among investigated tracking schemes, our recently presented tracking scheme for soft tissue motion provides highest accuracy with an error of under 2.2 voxels for the first 80 volumes. Object tracking on 4D-OCT images enables its use for sub-epithelial tracking of microvessels for image-guidance.

AB - A common representation of volumetric medical image data is the triplanar view (TV), in which the surgeon manually selects slices showing the anatomical structure of interest. In addition to common medical imaging such as MRI or computed tomography, recent advances in the field of optical coherence tomography (OCT) have enabled live processing and volumetric rendering of four-dimensional images of the human body. Due to the region of interest undergoing motion, it is challenging for the surgeon to simultaneously keep track of an object by continuously adjusting the TV to desired slices. To select these slices in subsequent frames automatically, it is necessary to track movements of the volume of interest (VOI). This has not been addressed with respect to 4DOCT images yet. Therefore, this paper evaluates motion tracking by applying state-of-the-art tracking schemes on maximum intensity projections (MIP) of 4D-OCT images. Estimated VOI location is used to conveniently show corresponding slices and to improve the MIPs by calculating thin-slab MIPs. Tracking performances are evaluated on an in-vivo sequence of human skin, captured at 26 volumes per second. Among investigated tracking schemes, our recently presented tracking scheme for soft tissue motion provides highest accuracy with an error of under 2.2 voxels for the first 80 volumes. Object tracking on 4D-OCT images enables its use for sub-epithelial tracking of microvessels for image-guidance.

UR - https://www.scopus.com/record/display.uri?eid=2-s2.0-85020420251&origin=inward&txGid=f67a62c241466dfc9250475b126adb4f

U2 - 10.1117/12.2255090

DO - 10.1117/12.2255090

M3 - Conference contribution

SN - 978-151060715-6

VL - 10135

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

SP - 101350W-101350W-7

BT - Medical Imaging 2017: Image-Guided Procedures, Robotic Interventions, and Modeling

A2 - Fei, Baowei

A2 - Webster, Robert J.

PB - SPIE

T2 - Medical Imaging 2017: Image-Guided Procedures, Robotic Interventions, and Modeling

Y2 - 14 February 2017 through 16 February 2017

ER -

Laves M-H, Schoob A, Kahrs LA, Pfeiffer T, Huber R, Ortmaier T. Feature tracking for automated volume of interest stabilization on 4D-OCT images. In Fei B, Webster RJ, editors, Medical Imaging 2017: Image-Guided Procedures, Robotic Interventions, and Modeling. Vol. 10135. SPIE. 2017. p. 101350W-101350W-7. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE). doi: 10.1117/12.2255090

Feature tracking for automated volume of interest stabilization on 4D-OCT images

Abstract

Research Areas and Centers

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this