SimCol3D -- 3D Reconstruction during Colonoscopy Challenge
arXiv:2307.11261 · doi:10.1016/j.media.2024.103195
Abstract
Colorectal cancer is one of the most common cancers in the world. While colonoscopy is an effective screening technique, navigating an endoscope through the colon to detect polyps is challenging. A 3D map of the observed surfaces could enhance the identification of unscreened colon tissue and serve as a training platform. However, reconstructing the colon from video footage remains difficult. Learning-based approaches hold promise as robust alternatives, but necessitate extensive datasets. Establishing a benchmark dataset, the 2022 EndoVis sub-challenge SimCol3D aimed to facilitate data-driven depth and pose prediction during colonoscopy. The challenge was hosted as part of MICCAI 2022 in Singapore. Six teams from around the world and representatives from academia and industry participated in the three sub-challenges: synthetic depth prediction, synthetic pose prediction, and real pose prediction. This paper describes the challenge, the submitted methods, and their results. We show that depth prediction from synthetic colonoscopy images is robustly solvable, while pose estimation remains an open research question.
References in corpus (9)
- PVT v2: Improved Baselines with Pyramid Vision Transformer
- Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fields
- Surgical Data Science: Enabling Next-Generation Surgery
- A deep learning framework for quality assessment and restoration in video endoscopy
- Global-Local Path Networks for Monocular Depth Estimation with Vertical CutDepth
- EndoMapper dataset of complete calibrated endoscopy procedures
- Augmenting Colonoscopy using Extended and Directional CycleGAN for Lossy Image Translation
- NeW CRFs: Neural Window Fully-connected CRFs for Monocular Depth Estimation
- Bimodal Camera Pose Prediction for Endoscopy