Identification of cecum time-location in a colonoscopy video by deep learning analysis of colonoscope movement

Minwoo Cho; Jee Hyun Kim; Kyoung Sup Hong; Joo Sung Kim; Hyoun-Joong Kong; Sungwan Kim

doi:10.7717/peerj.7256

Identification of cecum time-location in a colonoscopy video by deep learning analysis of colonoscope movement

PeerJ. 2019 Jul 29:7:e7256. doi: 10.7717/peerj.7256. eCollection 2019.

Authors

Minwoo Cho¹, Jee Hyun Kim², Kyoung Sup Hong³, Joo Sung Kim⁴, Hyoun-Joong Kong^#⁵, Sungwan Kim^#⁶

Affiliations

¹ Interdisciplinary Program for Bioengineering, Graduate School, Seoul National University, Seoul, South Korea.
² Department of Gastroenterology, Seoul National University Boramae Medical Center, Seoul, South Korea.
³ Department of Gastroenterology, Mediplex Sejong Hospital, Incheon, South Korea.
⁴ Department of Internal Medicine, Seoul National University College of Medicine, Seoul, South Korea.
⁵ Department of Biomedical Engineering, Chungnam National University College of Medicine, Daejeon, South Korea.
⁶ Department of Biomedical Engineering, Seoul National University College of Medicine, Seoul, South Korea.

^# Contributed equally.

Abstract

Background: Cecal intubation time is an important component for quality colonoscopy. Cecum is the turning point that determines the insertion and withdrawal phase of the colonoscope. For this reason, obtaining information related with location of the cecum in the endoscopic procedure is very useful. Also, it is necessary to detect the direction of colonoscope's movement and time-location of the cecum.

Methods: In order to analysis the direction of scope's movement, the Horn-Schunck algorithm was used to compute the pixel's motion change between consecutive frames. Horn-Schunk-algorithm applied images were trained and tested through convolutional neural network deep learning methods, and classified to the insertion, withdrawal and stop movements. Based on the scope's movement, the graph was drawn with a value of +1 for insertion, -1 for withdrawal, and 0 for stop. We regarded the turning point as a cecum candidate point when the total graph area sum in a certain section recorded the lowest.

Results: A total of 328,927 frame images were obtained from 112 patients. The overall accuracy, drawn from 5-fold cross-validation, was 95.6%. When the value of "t" was 30 s, accuracy of cecum discovery was 96.7%. In order to increase visibility, the movement of the scope was added to summary report of colonoscopy video. Insertion, withdrawal, and stop movements were mapped to each color and expressed with various scale. As the scale increased, the distinction between the insertion phase and the withdrawal phase became clearer.

Conclusion: Information obtained in this study can be utilized as metadata for proficiency assessment. Since insertion and withdrawal are technically different movements, data of scope's movement and phase can be quantified and utilized to express pattern unique to the colonoscopist and to assess proficiency. Also, we hope that the findings of this study can contribute to the informatics field of medical records so that medical charts can be transmitted graphically and effectively in the field of colonoscopy.

Keywords: CNN; Cecal-location; Cecum; Colonoscopy; Deep learning; Summary report.

Associated data

figshare/10.6084/m9.figshare.7937336.v1

Grants and funding

This study was supported by the National Research Foundation of Korea (NRF) funded by the Korean Government (2018M1A3A3A02065779 to Sungwan Kim), and MSIT (Ministry of Science and ICT), Korea, under the ITRC (Information Technology Research Center) support program (IITP-2019-2018-0-01833) supervised by the IITP (Institute for Information & communications Technology Promotion). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.