Authors:
Mirko Arnold
1
;
Hugh Mulcahy
2
;
Glen Doherty
2
;
Christopher Steele
3
;
Stephen Patchett
4
;
Anarta Ghosh
1
and
Gerard Lacey
1
Affiliations:
1
Trinity College Dublin, Ireland
;
2
University College Dublin, Ireland
;
3
Letterkenny General Hospital Donegal, Ireland
;
4
Royal College of Surgeons in Ireland, Ireland
Keyword(s):
Medical Computer Vision, Medical Image Applications, Endoscopic Imaging, Vision-based Quality Assessment, Colonoscopy, Machine Learning.
Related
Ontology
Subjects/Areas/Topics:
Applications and Services
;
Computer Vision, Visualization and Computer Graphics
;
Medical Image Applications
Abstract:
The quality of individual colonoscopy procedures is currently assessed by the performing endoscopist. In
light of the recently reported quality issues in colonoscopy screening, there may be significant benefits in
augmenting this form of self-assessment by automatic assistance systems. In this paper, we propose a system
for the assessment of individual colonoscopy procedures, based on image analysis and machine learning. The
system rates the procedures according to criteria of the validated Direct Observation of Procedure and Skill
(DOPS) assessment, developed by the Joint Advisory Group on GI Endoscopy (JAG) in the UK, a system
involving expert assessment of procedures based on an assessment form.