KID Project: an internet-based digital video atlas of capsule endoscopy for research purposes
-
- Anastasios Koulaouzidis
- Centre for Liver and Digestive Disorders, The Royal Infirmary of Edinburgh, Edinburgh, UK
-
- Dimitris Iakovidis
- University of Thessaly, Department of Computer Science and Biomedical Informatics, Volos, Thessaly, Greece
-
- Diana Yung
- Centre for Liver and Digestive Disorders, The Royal Infirmary of Edinburgh, Edinburgh, UK
-
- Emanuele Rondonotti
- Gastroenterology Unit, Valduce Hospital, Como, Italy
-
- Uri Kopylov
- Department of Gastroenterology, Sheba Medical Center, Tel Hashomer, and Sackler School of Medicine, Tel Aviv University, Tel-Aviv, Israel
-
- John Plevris
- Centre for Liver and Digestive Disorders, The Royal Infirmary of Edinburgh, Edinburgh, UK
-
- Ervin Toth
- Department of Gastroenterology, Skåne University Hospital, Lund University, Malmö, Sweden
-
- Abraham Eliakim
- Department of Gastroenterology, Sheba Medical Center, Tel Hashomer, and Sackler School of Medicine, Tel Aviv University, Tel-Aviv, Israel
-
- Gabrielle Wurm Johansson
- Department of Gastroenterology, Skåne University Hospital, Lund University, Malmö, Sweden
-
- Wojciech Marlicz
- Department of Gastroenterology, Pomeranian Medical University, Szezecin, Poland
-
- Georgios Mavrogenis
- Gastroenterology and Endoscopy Center of Mytilene, Mytilene, Lesvos, Greece
-
- Artur Nemeth
- Department of Gastroenterology, Skåne University Hospital, Lund University, Malmö, Sweden
-
- Henrik Thorlacius
- Department of Clinical Sciences, Lund University, Malmö, Sweden
-
- Gian Tontini
- Gastroenterology and Digestive Endoscopy Unit, IRCCS Policlinico San Donato, Milan, Italy
説明
<jats:title>Abstract</jats:title><jats:p> Background and aims Capsule endoscopy (CE) has revolutionized small-bowel (SB) investigation. Computational methods can enhance diagnostic yield (DY); however, incorporating machine learning algorithms (MLAs) into CE reading is difficult as large amounts of image annotations are required for training. Current databases lack graphic annotations of pathologies and cannot be used. A novel database, KID, aims to provide a reference for research and development of medical decision support systems (MDSS) for CE.</jats:p><jats:p> Methods Open-source software was used for the KID database. Clinicians contribute anonymized, annotated CE images and videos. Graphic annotations are supported by an open-access annotation tool (Ratsnake). We detail an experiment based on the KID database, examining differences in SB lesion measurement between human readers and a MLA. The Jaccard Index (JI) was used to evaluate similarity between annotations by the MLA and human readers.</jats:p><jats:p> Results The MLA performed best in measuring lymphangiectasias with a JI of 81 ± 6 %. The other lesion types were: angioectasias (JI 64 ± 11 %), aphthae (JI 64 ± 8 %), chylous cysts (JI 70 ± 14 %), polypoid lesions (JI 75 ± 21 %), and ulcers (JI 56 ± 9 %).</jats:p><jats:p> Conclusion MLA can perform as well as human readers in the measurement of SB angioectasias in white light (WL). Automated lesion measurement is therefore feasible. KID is currently the only open-source CE database developed specifically to aid development of MDSS. Our experiment demonstrates this potential.</jats:p>
収録刊行物
-
- Endoscopy International Open
-
Endoscopy International Open 05 (06), E477-E483, 2017-05-31
Georg Thieme Verlag KG