Dense Depth Estimation in Monocular Endoscopy with Self-supervised Learning Methods
This work addresses depth estimation in medical endoscopy, which is incremental as it adapts self-supervised techniques to a specific domain without requiring patient CT scans.
The paper tackles dense depth estimation from monocular endoscopy videos using a self-supervised learning method that avoids manual labeling or CT scans, achieving submillimeter mean residual error and outperforming previous methods by a large margin on in vivo sinus endoscopy data.
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.