Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

KID Project : an internet-based digital video atlas of capsule endoscopy for research purposes

Koulaouzidis, Anastasios LU ; Iakovidis, Dimitris K ; Yung, Diana E ; Rondonotti, Emanuele ; Kopylov, Uri ; Plevris, John N ; Toth, Ervin LU ; Eliakim, Abraham ; Wurm Johansson, Gabrielle and Marlicz, Wojciech , et al. (2017) In Endoscopy International Open 5(6). p.477-483
Abstract

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.

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... (More)

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.

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.

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 %).

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.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; ; ; ; and , et al. (More)
; ; ; ; ; ; ; ; ; ; ; ; and (Less)
organization
publishing date
type
Contribution to journal
publication status
published
subject
in
Endoscopy International Open
volume
5
issue
6
pages
477 - 483
publisher
Georg Thieme Verlag
external identifiers
  • pmid:28580415
ISSN
2364-3722
DOI
10.1055/s-0043-105488
language
English
LU publication?
yes
id
6abfa1f8-451a-4a7b-8ff7-de62dcd199fd
date added to LUP
2020-05-12 16:36:17
date last changed
2020-05-28 15:49:46
@article{6abfa1f8-451a-4a7b-8ff7-de62dcd199fd,
  abstract     = {{<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.</p><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.</p><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 %).</p><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.</p>}},
  author       = {{Koulaouzidis, Anastasios and Iakovidis, Dimitris K and Yung, Diana E and Rondonotti, Emanuele and Kopylov, Uri and Plevris, John N and Toth, Ervin and Eliakim, Abraham and Wurm Johansson, Gabrielle and Marlicz, Wojciech and Mavrogenis, Georgios and Nemeth, Artur and Thorlacius, Henrik and Tontini, Gian Eugenio}},
  issn         = {{2364-3722}},
  language     = {{eng}},
  number       = {{6}},
  pages        = {{477--483}},
  publisher    = {{Georg Thieme Verlag}},
  series       = {{Endoscopy International Open}},
  title        = {{KID Project : an internet-based digital video atlas of capsule endoscopy for research purposes}},
  url          = {{http://dx.doi.org/10.1055/s-0043-105488}},
  doi          = {{10.1055/s-0043-105488}},
  volume       = {{5}},
  year         = {{2017}},
}