Dense Depth Estimation in Monocular Endoscopy With Self-Supervised Learning Methods | IEEE Journals & Magazine | IEEE Xplore

Dense Depth Estimation in Monocular Endoscopy With Self-Supervised Learning Methods


Abstract:

We present a self-supervised approach to training convolutional neural networks for dense depth estimation from monocular endoscopy data without a priori modeling of anat...Show More

Abstract:

We present a self-supervised approach to training convolutional neural networks for dense depth estimation from monocular endoscopy data without a priori modeling of anatomy or shading. Our method only requires monocular endoscopic videos and a multi-view stereo method, e.g., structure from motion, to supervise learning in a sparse manner. Consequently, our method requires neither manual labeling nor patient computed tomography (CT) scan in the training and application phases. In a cross-patient experiment using CT scans as groundtruth, the proposed method achieved submillimeter mean residual error. In a comparison study to recent self-supervised depth estimation methods designed for natural video on in vivo sinus endoscopy data, we demonstrate that the proposed approach outperforms the previous methods by a large margin. The source code for this work is publicly available online at https://github.com/lppllppl920/EndoscopyDepthEstimation-Pytorch.
Published in: IEEE Transactions on Medical Imaging ( Volume: 39, Issue: 5, May 2020)
Page(s): 1438 - 1447
Date of Publication: 01 November 2019

ISSN Information:

PubMed ID: 31689184

Funding Agency:


Contact IEEE to Subscribe

References

References is not available for this document.