Article Text

Download PDFPDF
Computer-aided detection and abnormality score for the outer retinal layer in optical coherence tomography
  1. Tyler Hyungtaek Rim1,2,
  2. Aaron Yuntai Lee3,
  3. Daniel S Ting1,2,
  4. Kelvin Yi Chong Teo1,2,
  5. Hee Seung Yang1,
  6. Hyeonmin KIM4,
  7. Geunyoung Lee4,
  8. Zhen Ling Teo1,
  9. Alvin Teo Wei Jun1,
  10. Kengo Takahashi5,
  11. Tea Keun Yoo6,
  12. Sung Eun Kim7,
  13. Yasuo Yanagi1,2,5,
  14. Ching-Yu Cheng1,2,
  15. Sung Soo Kim8,
  16. Tien Yin Wong1,2,
  17. Chui Ming Gemmy Cheung1,2
  1. 1Singapore Eye Research Institute, Singapore National Eye Centre, Singapore
  2. 2Ophthalmology and Visual Sciences Academic Clinical Program, Duke-NUS Medical School, Singapore
  3. 3Department of Ophthalmology, University of Washington School of Medicine, Seattle, Washington, USA
  4. 4Medi Whale Inc, Seoul, South Korea
  5. 5Department of Ophthalmology, Asahikawa Medical University, Hokkaido, Japan
  6. 6Department of Ophthalmology, Aerospace Medical Center, Republic of Korea Air Force, Seoul, Korea (the Republic of)
  7. 7Department of Ophthalmology, CHA Bundang Medical Center, CHA University, Seongnam, South Korea
  8. 8Department of Ophthalmology, Institute of Vision Research, Severance Hospital, Yonsei University College of Medicine, Seoul, South Korea
  1. Correspondence to Professor Sung Soo Kim, Opthalmology, Yonsei University College of Medicine, Seodaemun-gu, Korea (the Republic of); semekim{at}yuhs.ac; Professor Chui Ming Gemmy Cheung, Singapore National Eye Centre, 11 third Hospital Avenue, Singapore; gemmy.cheung.c.m{at}singhealth.com.sg

Abstract

Background To develop computer-aided detection (CADe) of ORL abnormalities in the retinal pigmented epithelium, interdigitation zone and ellipsoid zone via optical coherence tomography (OCT).

Methods In this retrospective study, healthy participants with normal ORL, and patients with abnormality of ORL including choroidal neovascularisation (CNV) or retinitis pigmentosa (RP) were included. First, an automatic segmentation deep learning (DL) algorithm, CADe, was developed for the three outer retinal layers using 120 handcraft masks of ORL. This automatic segmentation algorithm generated 4000 segmentations, which included 2000 images with normal ORL and 2000 (1000 CNV and 1000 RP) images with focal or wide defects in ORL. Second, based on the automatically generated segmentation images, a binary classifier (normal vs abnormal) was developed. Results were evaluated by area under the receiver operating characteristic curve (AUC).

Results The DL algorithm achieved an AUC of 0.984 (95% CI 0.976 to 0.993) for individual image evaluation in the internal test set of 797 images. In addition, performance analysis of a publicly available external test set (n=968) had an AUC of 0.957 (95% CI 0.944 to 0.970) and a second clinical external test set (n=1124) had an AUC of 0.978 (95% CI 0.970 to 0.986). Moreover, the CADe highlighted well normal parts of ORL and omitted highlights in abnormal ORLs of CNV and RP.

Conclusion The CADe can use OCT images to segment ORL and differentiate between normal ORL and abnormal ORL. The CADe classifier also performs visualisation and may aid future physician diagnosis and clinical applications.

  • epidemiology
  • imaging
  • retina
  • telemedicine

Data availability statement

Data sharing not applicable due to the violation of patient privacy and the absence of informed consent for data sharing. Data are available on reasonable request. Data from South Korea are available to researchers who meet the criteria for access to confidenctial data: request should be made to Sung Soo Kim, Department of Ophthalmology, Severance Hospital, Yonsei University, Seoul, South Korea (semekim@yuhs.ac). Reqeusts to data from the Singapore Epidemiology of Eye Diseases should be made to Ching-Yu Cheng, Singapore Eye Research Institute, Singapore (chingyu.cheng@duke-nus.edu.sg).

Statistics from Altmetric.com

Data availability statement

Data sharing not applicable due to the violation of patient privacy and the absence of informed consent for data sharing. Data are available on reasonable request. Data from South Korea are available to researchers who meet the criteria for access to confidenctial data: request should be made to Sung Soo Kim, Department of Ophthalmology, Severance Hospital, Yonsei University, Seoul, South Korea (semekim@yuhs.ac). Reqeusts to data from the Singapore Epidemiology of Eye Diseases should be made to Ching-Yu Cheng, Singapore Eye Research Institute, Singapore (chingyu.cheng@duke-nus.edu.sg).

View Full Text

Footnotes

  • THR and AYL contributed equally.

  • Contributors TR, AYL, DST, C-YC, SSK, TYW and CMGC conceptualised the study. TR, AYL, DST, KYCT, HSY, HK, GL, ZLT, AT, KYCT, TKY and SEK reviewed the literature. TR, AYL, DST, KYCT, C-YC, SSK, TYW and CMGC designed the study. TR, AYL, KYCT, KYCT, TKY, SEK, YY, C-YC, SSK, TYW and CMGC collected the data.GL and HK developed the algorithm.TR, AYL, and C-YC analyzed data. All authors contributed to data interpretation. TR, AYL, HSY, ZLT, AT, TYW and CMGC drafted the manuscript. DST, KYCT, YY, C-YC, SSK, TYW and CMGC did the critical revision. All authors read and approved the final report.

  • Funding This study was funded by the National Medical Research Council of Singapore (NMRC/OFLCG/004a/2018; NMRC/CIRG/1488/2018) and of National Eye Institute of the United States (K23EY029246).

  • Competing interests TR was a scientific advisor to a start-up company called Medi-whale. He received stock as a part of the standard compensation package. DST and TYW hold patents on a deep learning system for the detection of retinal diseases and these patents are not directly related to this study. TYW has received consulting fees from Allergan, Bayer, Boehringer-Ingelheim, Genentech, Merk, Novartis, Oxurion, Roche, and Samsung Bioepis. TYW is a cofounder of Plano and EyRiS. DST is a cofounder of EyRiS. Potential conflicts of interests are managed according to institutional policies of the Singapore Health System (SingHealth) and the National University of Singapore. HK and GL are employee of Medi Whale. All other authors declare no competing interests.

  • Provenance and peer review Not commissioned; externally peer reviewed.

  • Supplemental material This content has been supplied by the author(s). It has not been vetted by BMJ Publishing Group Limited (BMJ) and may not have been peer-reviewed. Any opinions or recommendations discussed are solely those of the author(s) and are not endorsed by BMJ. BMJ disclaims all liability and responsibility arising from any reliance placed on the content. Where the content includes any translated material, BMJ does not warrant the accuracy and reliability of the translations (including but not limited to local regulations, clinical guidelines, terminology, drug names and drug dosages), and is not responsible for any error and/or omissions arising from translation and adaptation or otherwise.

Request Permissions

If you wish to reuse any or all of this article please use the link below which will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.