Partial 3D-reconstruction of the colon from monoscopic colonoscopy videos using shape-from-motion and deep learning

Walluscheck S, Wittenberg T, Bruns V, Eixelberger T, Hackner R (2021)

Publication Language: English

Publication Type: Journal article

Publication year: 2021

Journal

Current Directions in Biomedical Engineering De Gruyter

Book Volume: 7

Pages Range: 335-338

Journal Issue: 2

DOI: 10.1515/cdbme-2021-2085

Abstract

For the image-based documentation of a colonoscopy procedure, a 3D-reconstuction of the hollow colon structure from endoscopic video streams is desirable. To obtain this reconstruction, 3D information about the colon has to be extracted from monocular colonoscopy image sequences. This information can be provided by estimating depth through shape-from-motion approaches, using the image information from two successive image frames and the exact knowledge of their disparity. Nevertheless, during a standard colonoscopy the spatial offset between successive frames is continuously changing. Thus, in this work deep convolutional neural networks (DCNNs) are applied in order to obtain piecewise depth maps and point clouds of the colon. These pieces can then be fused for a partial 3D reconstruction.

Authors with CRIS profile

Thomas Wittenberg Chair of Visual Computing (LGDV)

Involved external institutions

Fraunhofer-Institut für Integrierte Schaltungen (IIS) DE Germany (DE)

How to cite

APA:

Walluscheck, S., Wittenberg, T., Bruns, V., Eixelberger, T., & Hackner, R. (2021). Partial 3D-reconstruction of the colon from monoscopic colonoscopy videos using shape-from-motion and deep learning. Current Directions in Biomedical Engineering, 7(2), 335-338. https://doi.org/10.1515/cdbme-2021-2085

MLA:

Walluscheck, Sina, et al. "Partial 3D-reconstruction of the colon from monoscopic colonoscopy videos using shape-from-motion and deep learning." Current Directions in Biomedical Engineering 7.2 (2021): 335-338.

BibTeX: Download