Quantitative Evaluation of Endoscopic SLAM Methods: EndoSLAM Dataset

Deep learning techniques hold promise to improve dense topography reconstruction and pose estimation, as well as simultaneous localization and mapping (SLAM). However, currently available datasets do not support effective quantitative benchmarking. With this paper, we introduce a comprehensive endoscopic SLAM dataset containing both capsule and standard endoscopy recordings. A Panda robotic arm, two different commercially available high precision 3D scanners, two different commercially available capsule endoscopes with different camera properties and two different conventional endoscopy cameras were employed to collect data from eight ex-vivo porcine gastrointestinal (GI)-tract organs. In total, 35 sub-datasets are provided: 18 sub-datasets for colon, 12 sub-datasets for stomach and five sub-datasets for small intestine, while four of these contain polyp-mimicking elevations carried out by an expert gastroenterologist. To exemplify the use-case, SC-SfMLearner was comprehensively benchmarked. The codes and the link for the dataset are publicly available at this https URL. A video demonstrating the experimental setup and procedure is available at this https URL.

[1]  Mubarak Shah,et al.  Shape from shading using linear approximation , 1994, Image Vis. Comput..

[2]  T. Yano,et al.  Vascular, polypoid, and other lesions of the small bowel. , 2009, Best practice & research. Clinical gastroenterology.

[3]  E. Redondo-Cerezo,et al.  Wireless capsule endoscopy: perspectives beyond gastrointestinal bleeding. , 2014, World journal of gastroenterology.

[4]  Helder Araújo,et al.  A fully dense and globally consistent 3D map reconstruction approach for GI tract to enhance therapeutic relevance of the endoscopic capsule robot , 2017, ArXiv.

[5]  Edward L. Giovannucci,et al.  Global Burden of 5 Major Types Of Gastrointestinal Cancer. , 2020, Gastroenterology.

[6]  Weihua Li,et al.  An Effective Localization Method for Robotic Endoscopic Capsules Using Multiple Positron Emission Markers , 2014, IEEE Transactions on Robotics.

[7]  Aymeric Histace,et al.  Comparative Validation of Polyp Detection Methods in Video Colonoscopy: Results From the MICCAI 2015 Endoscopic Vision Challenge , 2017, IEEE Transactions on Medical Imaging.

[8]  T. Shah,et al.  Development of a Tracking Algorithm for an In-Vivo RF Capsule Prototype , 2006, 2006 International Conference on Electrical and Computer Engineering.

[9]  Hann Woei Ho,et al.  Distance and velocity estimation using optical flow from a monocular camera , 2017 .

[10]  Won Ho Kim,et al.  Comparison of the diagnostic yield of "MiroCam" and "PillCam SB" capsule endoscopy. , 2012, Hepato-gastroenterology.

[11]  Yasin Almalioglu,et al.  Unsupervised Odometry and Depth Learning for Endoscopic Capsule Robots , 2018, 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

[12]  Berthold K. P. Horn,et al.  Closed-form solution of absolute orientation using unit quaternions , 1987 .

[13]  Chunhua Shen,et al.  Unsupervised Scale-consistent Depth and Ego-motion Learning from Monocular Video , 2019, NeurIPS.

[14]  Elena De Momi,et al.  Learning-based classification of informative laryngoscopic frames , 2018, Comput. Methods Programs Biomed..

[15]  Nick Barnes,et al.  A Robust Docking Strategy for a Mobile Robot Using Flow Field Divergence , 2006, IEEE Transactions on Robotics.

[16]  Matthew A. Brown,et al.  Automatic Panoramic Image Stitching using Invariant Features , 2007, International Journal of Computer Vision.

[17]  Marc Pollefeys,et al.  Real-time velocity estimation based on optical flow and disparity matching , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[18]  Guang-Zhong Yang,et al.  Self-Supervised Siamese Learning on Stereo Image Pairs for Depth Estimation in Robotic Surgery , 2017, ArXiv.

[19]  Andrew J. Davison,et al.  A benchmark for RGB-D visual odometry, 3D reconstruction and SLAM , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[20]  Dimitris K. Iakovidis,et al.  Video-based measurements for wireless capsule endoscope tracking , 2014 .

[21]  Helder Araújo,et al.  Deep EndoVO: A recurrent convolutional neural network (RCNN) based visual odometry approach for endoscopic capsule robots , 2017, Neurocomputing.

[22]  P. Dario,et al.  Frontiers of robotic endoscopic capsules: a review , 2016, Journal of Micro-Bio Robotics.

[23]  Dimitris K. Iakovidis,et al.  KID Project: an internet-based digital video atlas of capsule endoscopy for research purposes , 2017, Endoscopy International Open.

[24]  Daniel Mirota,et al.  A System for Video-Based Navigation for Endoscopic Endonasal Skull Base Surgery , 2012, IEEE Transactions on Medical Imaging.

[25]  Roger Y. Tsai,et al.  A new technique for fully autonomous and efficient 3D robotics hand/eye calibration , 1988, IEEE Trans. Robotics Autom..

[26]  Nima Tajbakhsh,et al.  Automated Polyp Detection in Colonoscopy Videos Using Shape and Context Information , 2016, IEEE Transactions on Medical Imaging.

[27]  Faisal Mahmood,et al.  Deep learning and conditional random fields‐based depth estimation and topographical reconstruction from conventional endoscopy , 2017, Medical Image Anal..

[28]  Fernando Vilariño,et al.  Towards automatic polyp detection with a polyp appearance model , 2012, Pattern Recognit..

[29]  Richard J. Chen,et al.  SLAM Endoscopy enhanced by adversarial depth prediction , 2019, ArXiv.

[30]  Guang-Zhong Yang,et al.  Simultaneous Stereoscope Localization and Soft-Tissue Mapping for Minimal Invasive Surgery , 2006, MICCAI.

[31]  J. M. M. Montiel,et al.  Visual SLAM for Handheld Monocular Endoscope , 2014, IEEE Transactions on Medical Imaging.

[32]  Metin Sitti,et al.  A 5-D Localization Method for a Magnetically Manipulated Untethered Robot Using a 2-D Array of Hall-Effect Sensors , 2016, IEEE/ASME Transactions on Mechatronics.

[33]  Mathias Lux,et al.  HyperKvasir, a comprehensive multi-class image and video dataset for gastrointestinal endoscopy , 2020, Scientific data.

[34]  Lisandro J. Puglisi.  On the Velocity and Acceleration Estimation from Discrete Time-Position Signal of Linear Encoders , 2015 .

[35]  Guangjun Liu,et al.  On velocity estimation using position measurements , 2002, Proceedings of the 2002 American Control Conference (IEEE Cat. No.CH37301).

[36]  Weihua Li,et al.  A Review of Localization Systems for Robotic Endoscopic Capsules , 2012, IEEE Transactions on Biomedical Engineering.

[37]  Nilanjan Dey,et al.  Wireless Capsule Gastrointestinal Endoscopy: Direction-of-Arrival Estimation Based Localization Survey , 2017, IEEE Reviews in Biomedical Engineering.

[38]  Aymeric Histace,et al.  Towards embedded detection of polyps in WCE images for early diagnosis of colorectal cancer , 2016 .

[39]  Howie Choset,et al.  Intelligent Surgical Robots with Situational Awareness , 2015 .

[40]  Sara Moccia,et al.  EndoAbS dataset: Endoscopic abdominal stereo image dataset for benchmarking 3D stereo reconstruction algorithms , 2018, The international journal of medical robotics + computer assisted surgery : MRCAS.

[41]  Yu Sun,et al.  Simultaneous Tracking, 3D Reconstruction and Deforming Point Detection for Stereoscope Guided Surgery , 2013, AE-CAI.

[42]  Michael Riegler,et al.  KVASIR: A Multi-Class Image Dataset for Computer Aided Gastrointestinal Disease Detection , 2017, MMSys.

[43]  Zhengyou Zhang,et al.  Flexible camera calibration by viewing a plane from unknown orientations , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[44]  Takeo Kanade,et al.  An Iterative Image Registration Technique with an Application to Stereo Vision , 1981, IJCAI.

[45]  Fernando Vilariño,et al.  WM-DOVA maps for accurate polyp highlighting in colonoscopy: Validation vs. saliency maps from physicians , 2015, Comput. Medical Imaging Graph..

[46]  Helder Araújo,et al.  A non-rigid map fusion-based direct SLAM method for endoscopic capsule robots , 2017, International Journal of Intelligent Robotics and Applications.

[47]  Guang-Zhong Yang,et al.  Online tracking and retargeting with applications to optical biopsy in gastrointestinal endoscopic examinations , 2016, Medical Image Anal..

[48]  Faisal Mahmood,et al.  Unsupervised Reverse Domain Adaptation for Synthetic Medical Images via Adversarial Training , 2017, IEEE Transactions on Medical Imaging.