Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
125 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
42 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

REAL-Colon: A dataset for developing real-world AI applications in colonoscopy (2403.02163v1)

Published 4 Mar 2024 in eess.IV and cs.CV

Abstract: Detection and diagnosis of colon polyps are key to preventing colorectal cancer. Recent evidence suggests that AI-based computer-aided detection (CADe) and computer-aided diagnosis (CADx) systems can enhance endoscopists' performance and boost colonoscopy effectiveness. However, most available public datasets primarily consist of still images or video clips, often at a down-sampled resolution, and do not accurately represent real-world colonoscopy procedures. We introduce the REAL-Colon (Real-world multi-center Endoscopy Annotated video Library) dataset: a compilation of 2.7M native video frames from sixty full-resolution, real-world colonoscopy recordings across multiple centers. The dataset contains 350k bounding-box annotations, each created under the supervision of expert gastroenterologists. Comprehensive patient clinical data, colonoscopy acquisition information, and polyp histopathological information are also included in each video. With its unprecedented size, quality, and heterogeneity, the REAL-Colon dataset is a unique resource for researchers and developers aiming to advance AI research in colonoscopy. Its openness and transparency facilitate rigorous and reproducible research, fostering the development and benchmarking of more accurate and reliable colonoscopy-related algorithms and models.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (38)
  1. Sung, H. et al. Global cancer statistics 2020: Globocan estimates of incidence and mortality worldwide for 36 cancers in 185 countries. \JournalTitleCA Cancer J. Clin. 71, 209–249 (2021).
  2. Morgan, E. et al. Global burden of colorectal cancer in 2020 and 2040: incidence and mortality estimates from globocan. \JournalTitleGut 72, 338–344 (2023).
  3. Bretthauer, M. et al. Effect of colonoscopy screening on risks of colorectal cancer and related death. \JournalTitleN. Engl. J. Med. 387, 1547–1556 (2022).
  4. Zorzi, M. e. a. Adenoma detection rate and colorectal cancer risk in fecal immunochemical test screening programs: An observational cohort study. \JournalTitleAnn. Intern. Med. 176, 303–310 (2023).
  5. Advances in crc prevention: Screening and surveillance. \JournalTitleGastroenterology 154, 1970–1984 (2018).
  6. Optimizing the quality of colorectal cancer screening worldwide. \JournalTitleGastroenterology 158, 404–417 (2020).
  7. Gorilla in the room: Even experts can miss polyps at colonoscopy and how ai helps complex visual perception tasks. \JournalTitleDig. Liver Dis. 55, 151–153 (2023).
  8. Ahmad, O. F. et al. Artificial intelligence and computer-aided diagnosis in colonoscopy: current evidence and future directions. \JournalTitleLancet Gastroenterol. Hepatol. 4, 71–80 (2019).
  9. Berzin, T. M. e. a. Position statement on priorities for artificial intelligence in gi endoscopy: a report by the asge task force. \JournalTitleGastrointest. Endosc. 92, 951–959 (2020).
  10. Repici, A. e. a. Efficacy of real-time computer-aided detection of colorectal neoplasia in a randomized trial. \JournalTitleGastroenterology 159, 512–520.e7 (2020).
  11. Wallace, M. B. e. a. Impact of artificial intelligence on miss rate of colorectal neoplasia. \JournalTitleGastroenterology (2022).
  12. Spadaccini, M. e. a. Computer-aided detection versus advanced imaging for detection of colorectal neoplasia: a systematic review and network meta-analysis. \JournalTitleLancet Gastroenterol. Hepatol. 6, 793–802 (2021).
  13. Biffi, C. e. a. A novel ai device for real-time optical characterization of colorectal polyps. \JournalTitleNPJ Digit. Med. 5, 84 (2022).
  14. Towards automatic polyp detection with a polyp appearance model. \JournalTitlePattern Recognit. 45, 3166–3182 (2012).
  15. Toward embedded detection of polyps in wce images for early diagnosis of colorectal cancer. \JournalTitleInt. J. Comput. Assist. Radiol. Surg. 9, 283–293 (2014).
  16. Bernal, J. e. a. Wm-dova maps for accurate polyp highlighting in colonoscopy: Validation vs. saliency maps from physicians. \JournalTitleComput. Med. Imaging Graph. 43, 99–111 (2015).
  17. Automated polyp detection in colonoscopy videos using shape and context information. \JournalTitleIEEE Trans. Med. Imaging 35, 630–644 (2015).
  18. Angermann, Q. et al. Towards real-time polyp detection in colonoscopy videos: Adapting still frame-based methodologies for video sequences analysis. In Proc. 4th Int. Workshop CARE and 6th Int. Workshop CLIP, MICCAI 2017, 29–41 (Springer, 2017).
  19. Mesejo, P. et al. Computer-aided classification of gastrointestinal lesions in regular colonoscopy. \JournalTitleIEEE Trans. Med. Imaging 35, 2051–2063 (2016).
  20. Jha, D. et al. Kvasir-seg: A segmented polyp dataset. In Proc. 26th Int. Conf. MultiMedia Modeling, MMM 2020, 451–462 (2020).
  21. Sánchez-Peralta, L. F. et al. Piccolo white-light and narrow-band imaging colonoscopic dataset: a performance comparative of models and datasets. \JournalTitleAppl. Sci. 10, 8501 (2020).
  22. Li, K. et al. Colonoscopy polyp detection and classification: Dataset creation and comparative evaluations. \JournalTitlePLoS ONE 16, e0255809 (2021).
  23. Misawa, M. et al. Development of a computer-aided detection system for colonoscopy and a publicly accessible large colonoscopy video database (with video). \JournalTitleGastrointest. Endosc. 93, 960–967 (2021).
  24. Ldpolypvideo benchmark: a large-scale colonoscopy video dataset of diverse polyps. In Proc. 24th Int. Conf. Med. Image Comput. Comput. Assist. Intervent., MICCAI 2021, 387–396 (2021).
  25. Ali, S. et al. A multi-centre polyp detection and segmentation dataset for generalisability assessment. \JournalTitleSci. Data 10, 75 (2023).
  26. Negative samples for improving object detection—a case study in ai-assisted colonoscopy for polyp detection. \JournalTitleDiagnostics 13, 966 (2023).
  27. Reverberi, C. et al. Experimental evidence of effective human-ai collaboration in medical decision-making. \JournalTitleSci. Rep. 12, 14952 (2022).
  28. Ali, S. et al. Assessing generalisability of deep learning-based polyp detection and segmentation methods through a computer vision challenge. \JournalTitleSci. Rep. 14, 2032 (2024).
  29. Bernal, J. et al. Comparative validation of polyp detection methods in video colonoscopy: results from the miccai 2015 endoscopic vision challenge. \JournalTitleIEEE Trans. Med. Imaging 36, 1231–1249 (2017).
  30. Jha, D. et al. Medico multimedia task at mediaeval 2020: Automatic polyp segmentation. \JournalTitlearXiv preprint arXiv:2012.15244 (2020).
  31. Hicks, S. et al. Medico multimedia task at mediaeval 2021: Transparency in medical image segmentation. In Proceedings of MediaEval 2021 CEUR Workshop (2021).
  32. Hicks, S. et al. Medai: Transparency in medical image segmentation. \JournalTitleNordic Machine Intelligence 1, 1–4 (2021).
  33. Artificial intelligence allows leaving-in-situ colorectal polyps. \JournalTitleClin. Gastroenterol. Hepatol. 20, 2505–2513.e4 (2022).
  34. Participants in the Paris Workshop. The Paris endoscopic classification of superficial neoplastic lesions: esophagus, stomach, and colon. \JournalTitleGastrointestinal Endoscopy 58, S3–S43 (2003).
  35. Schlemper, R. J. et al. The Vienna classification of gastrointestinal epithelial neoplasia. \JournalTitleGut 47, 251–255 (2000).
  36. Biffi, C. et al. Real-colon dataset. \JournalTitleFigshare+ https://doi.org/10.25452/figshare.plus.22202866.v2 (2024).
  37. Lin, T.-Y. et al. Microsoft coco: Common objects in context. In Proc. 13th Eur. Conf. Comput. Vision, ECCV 2014, 740–755 (2014).
  38. Liu, W. et al. Ssd: Single shot multibox detector. In Proc. 14th Eur. Conf. Comput. Vision, ECCV 2016, 21–37 (2016).
Citations (6)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
Github Logo Streamline Icon: https://streamlinehq.com

GitHub

  1. GitHub - cosmoimd/real-colon-dataset: Helper function for working with the REAL-Colon Dataset (29 stars)