Rau, Anita;
Bhattarai, Binod;
Agapito, Lourdes;
Stoyanov, Danail;
(2023)
Task-Guided Domain Gap Reduction for Monocular Depth Prediction in Endoscopy.
In: Bhattarai, Binod and Ali, Sharib and Rau, Anita and Nguyen, Anh and Namburete, Ana and Caramalau, Razvan and Stoyanov, Danail, (eds.)
Data Engineering in Medical Imaging: DEMI 2023.
(pp. pp. 111-122).
Springer: Cham, Switzerland.
Preview |
Text
Task-Guided Domain Gap Reduction for Monocular Depth Prediction in Endoscopy.pdf - Accepted Version Download (5MB) | Preview |
Abstract
Colorectal cancer remains one of the deadliest cancers in the world. In recent years computer-aided methods have aimed to enhance cancer screening and improve the quality and availability of colonoscopies by automatizing sub-tasks. One such task is predicting depth from monocular video frames, which can assist endoscopic navigation. As ground truth depth from standard in-vivo colonoscopy remains unobtainable due to hardware constraints, two approaches have aimed to circumvent the need for real training data: supervised methods trained on labeled synthetic data and self-supervised models trained on unlabeled real data. However, self-supervised methods depend on unreliable loss functions that struggle with edges, self-occlusion, and lighting inconsistency. Methods trained on synthetic data can provide accurate depth for synthetic geometries but do not use any geometric supervisory signal from real data and overfit to synthetic anatomies and properties. This work proposes a novel approach to leverage labeled synthetic and unlabeled real data. While previous domain adaptation methods indiscriminately enforce the distributions of both input data modalities to coincide, we focus on the end task, depth prediction, and translate only essential information between the input domains. Our approach results in more resilient and accurate depth maps of real colonoscopy sequences. The project is available here: https://github.com/anitarau/Domain-Gap-Reduction-Endoscopy.
| Type: | Proceedings paper |
|---|---|
| Title: | Task-Guided Domain Gap Reduction for Monocular Depth Prediction in Endoscopy |
| Event: | MICCAI Workshop on Data Engineering in Medical Imaging: DEMI 2023 |
| ISBN-13: | 978-3-031-44991-8 |
| Open access status: | An open access version is available from UCL Discovery |
| DOI: | 10.1007/978-3-031-44992-5_11 |
| Publisher version: | http://dx.doi.org/10.1007/978-3-031-44992-5_11 |
| Language: | English |
| Additional information: | This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions. |
| Keywords: | Depth prediction; Domain adaptation; Self-supervision; Endoscopy |
| UCL classification: | UCL UCL > Provost and Vice Provost Offices > UCL BEAMS UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10185004 |
Archive Staff Only
 |
View Item |
