SimCol3D - 3D reconstruction during colonoscopy challenge.

Autor: Rau A; Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS) and Department of Computer Science, University College London, London, UK; Stanford University, Stanford, CA, USA. Electronic address: arau@stanford.edu., Bano S; Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS) and Department of Computer Science, University College London, London, UK. Electronic address: sophia.bano@ucl.ac.uk., Jin Y; Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS) and Department of Computer Science, University College London, London, UK; National University of Singapore, Singapore. Electronic address: ymjin@nus.edu.sg., Azagra P; University of Zaragoza, Zaragoza, Spain., Morlana J; University of Zaragoza, Zaragoza, Spain., Kader R; Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS) and Department of Computer Science, University College London, London, UK., Sanderson E; Computer Vision and Machine Learning (CVML) Group, University of Central Lancashire, Preston, UK., Matuszewski BJ; Computer Vision and Machine Learning (CVML) Group, University of Central Lancashire, Preston, UK., Lee JY; Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea., Lee DJ; Korea Advanced Institute of Science and Technology, Daejeon, Republic of Korea., Posner E; Intuitive Surgical, USA., Frank N; Intuitive Surgical, USA., Elangovan V; College of Engineering, Guindy, India., Raviteja S; Indian Institute of Technology Kharagpur, Kharagpur, India., Li Z; Key Laboratory for Biomedical Engineering of Ministry of Education, College of Biomedical Engineering & Instrument Science, Zhejiang University, China., Liu J; Key Laboratory for Biomedical Engineering of Ministry of Education, College of Biomedical Engineering & Instrument Science, Zhejiang University, China., Lalithkumar S; National University of Singapore, Singapore; The Chinese University of Hong Kong, Hong Kong, China., Islam M; Imperial College London, London, UK., Ren H; National University of Singapore, Singapore; The Chinese University of Hong Kong, Hong Kong, China., Lovat LB; Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS) and Department of Computer Science, University College London, London, UK., Montiel JMM; University of Zaragoza, Zaragoza, Spain., Stoyanov D; Wellcome/EPSRC Centre for Interventional and Surgical Sciences (WEISS) and Department of Computer Science, University College London, London, UK.
Jazyk: angličtina
Zdroj: Medical image analysis [Med Image Anal] 2024 Aug; Vol. 96, pp. 103195. Date of Electronic Publication: 2024 May 15.
DOI: 10.1016/j.media.2024.103195
Abstrakt: 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.
Competing Interests: Declaration of competing interest The authors declare the following financial interests/personal relationships which may be considered as potential competing interests: Danail Stoyanov reports financial support was provided by Medtronic plc. Danail Stoyanov reports a relationship with Odin Medical Ltd. that includes: equity or stocks. Laurence Lovat and Rawen Kader report a relationship with Olympus Corporation that includes: consulting or advisory.
(Copyright © 2024. Published by Elsevier B.V.)
Databáze: MEDLINE
Externí odkaz: