Download PDF
CC BY-NC-ND 4.0 · Endosc Int Open 2018; 06(08): E1044-E1050
DOI: 10.1055/a-0627-7136
Original article
Owner and Copyright © Georg Thieme Verlag KG 2018

Assessment of bowel cleansing quality in colon capsule endoscopy using machine learning: a pilot study

Maria Magdalena Buijs
1   Department of Surgery, Odense University Hospital, Svendborg, Denmark
2   Institute of Clinical Research, University of Southern Denmark, Odense, Denmark
,
Mohammed Hossain Ramezani
3   Mads Clausen Institute, University of Southern Denmark, Sønderborg, Denmark
,
Jürgen Herp
4   Applied Statistical Signal Processing Group, Embodied Systems for Robotics and Learning, Faculty of Engineering, University of Southern Denmark, Denmark
,
Rasmus Kroijer
1   Department of Surgery, Odense University Hospital, Svendborg, Denmark
2   Institute of Clinical Research, University of Southern Denmark, Odense, Denmark
,
Morten Kobaek-Larsen
2   Institute of Clinical Research, University of Southern Denmark, Odense, Denmark
,
Gunnar Baatrup
1   Department of Surgery, Odense University Hospital, Svendborg, Denmark
2   Institute of Clinical Research, University of Southern Denmark, Odense, Denmark
,
Esmaeil S. Nadimi
4   Applied Statistical Signal Processing Group, Embodied Systems for Robotics and Learning, Faculty of Engineering, University of Southern Denmark, Denmark
› Author Affiliations
Further Information

Publication History

Publication Date:
10 August 2018 (online)

Also available at
   Permissions and Reprints

Abstract

Background and study aims The aim of this study was to develop a machine learning-based model to classify bowel cleansing quality and to test this model in comparison to a pixel analysis model and assessments by four colon capsule endoscopy (CCE) readers.

Methods A pixel analysis and a machine learning-based model with four cleanliness classes (unacceptable, poor, fair and good) were developed to classify CCE videos. Cleansing assessments by four CCE readers in 41 videos from a previous study were compared to the results both models yielded in this pilot study.

Results The machine learning-based model classified 47 % of the videos in agreement with the averaged classification by CCE readers, as compared to 32 % by the pixel analysis model. A difference of more than one class was detected in 12 % of the videos by the machine learning-based model and in 32 % by the pixel analysis model, as the latter tended to overestimate cleansing quality. A specific analysis of unacceptable videos found that the pixel analysis model classified almost all of them as fair or good, whereas the machine learning-based model identified five out of 11 videos in agreement with at least one CCE reader as unacceptable.

Conclusions The machine learning-based model was superior to the pixel analysis in classifying bowel cleansing quality, due to a higher sensitivity to unacceptable and poor cleansing quality. The machine learning-based model can be further improved by coming to a consensus on how to classify cleanliness of a complete CCE video, by means of an expert panel.

 

  • References

  • 1 Spada C, Pasha SF, Gross SA. et al. Accuracy of first- and second-generation colon capsules in endoscopic detection of colorectal polyps: a systematic review and meta-analysis. Clin Gastroenterol Hepatol 2016; 14: 1533-1543.e8
    CrossrefPubMedSearch in Google Scholar
  • 2 Johnson DA, Barkun AN, Cohen LB. et al. Optimizing adequacy of bowel cleansing for colonoscopy: recommendations from the US Multi-Society Task Force on Colorectal Cancer. Am J Gastroenterol 2014; 109: 1528-1545
    CrossrefPubMedSearch in Google Scholar
  • 3 Leighton JA, Rex DK. A grading scale to evaluate colon cleansing for the PillCam COLON capsule: a reliability study. Endoscopy 2011; 43: 123-127
    Thieme ConnectPubMedSearch in Google Scholar
  • 4 Calderwood AH, Jacobson BC. Comprehensive validation of the Boston Bowel Preparation Scale. Gastrointest Endosc 2010; 72: 686-692
    CrossrefPubMedSearch in Google Scholar
  • 5 Aronchick CA LW, Wright SH, DuFrayne F. et al. Validation of an instrument to assess colon cleansing [abstract]. Am J Gastroenterol 1999; 94: 2667
    PubMedSearch in Google Scholar
  • 6 Rostom A, Jolicoeur E. Validation of a new scale for the assessment of bowel preparation quality. Gastrointest Endosc 2004; 59: 482-486
    CrossrefPubMedSearch in Google Scholar
  • 7 Halphen M, Heresbach D, Gruss HJ. et al. Validation of the Harefield Cleansing Scale: a tool for the evaluation of bowel cleansing quality in both research and clinical practice. Gastrointest Endosc 2013; 78: 121-131
    CrossrefPubMedSearch in Google Scholar
  • 8 Gerard DP, Foster DB, Raiser MW. et al. Validation of a new bowel preparation scale for measuring colon cleansing for colonoscopy: the chicago bowel preparation scale. Clin Transl Gastroenterol 2013; 4: e43
    CrossrefPubMedSearch in Google Scholar
  • 9 Parmar R, Martel M, Rostom A. et al. Validated Scales for colon cleansing: a systematic review. Am J Gastroenterol 2016; 111: 197-204
    CrossrefPubMedSearch in Google Scholar
  • 10 Rosa-Rizzotto E, Dupuis A, Guido E. et al. Clean colon software program (CCSP), proposal of a standardized method to quantify colon cleansing during colonoscopy: preliminary results. Endosc Int Open 2015; 3: E501-E507
    Thieme ConnectPubMedSearch in Google Scholar
  • 11 Kobaek-Larsen M, Kroijer R, Dyrvig AK. et al. Back-to-back colon capsule endoscopy and optical colonoscopy in colorectal cancer screening individuals. Colorectal Dis 2018; 20: 479-485
    CrossrefPubMedSearch in Google Scholar
  • 12 Ben-Horin S, Bar-Meir S, Avidan B. The impact of colon cleanliness assessment on endoscopistsʼ recommendations for follow-up colonoscopy. Am J Gastroenterol 2007; 102: 2680-2685
    CrossrefPubMedSearch in Google Scholar