Deep learning-based algorithm for the detection of idiopathic full thickness macular holes in spectral domain optical coherence tomography

Carolina C S Valentim; Anna K Wu; Sophia Yu; Niranchana Manivannan; Qinqin Zhang; Jessica Cao; Weilin Song; Victoria Wang; Hannah Kang; Aneesha Kalur; Amogh I Iyer; Thais Conti; Rishi P Singh; Katherine E Talcott

doi:10.1186/s40942-024-00526-8

Deep learning-based algorithm for the detection of idiopathic full thickness macular holes in spectral domain optical coherence tomography

Int J Retina Vitreous. 2024 Jan 23;10(1):9. doi: 10.1186/s40942-024-00526-8.

Authors

Affiliations

¹ Center for Ophthalmic Bioinformatics, Cole Eye Institute, Cleveland Clinic Foundation, 9500 Euclid Ave. i32, Cleveland, OH, USA.
² Case Western Reserve University School of Medicine, Cleveland, OH, USA.
³ Carl Zeiss Meditec, Inc, Dublin, CA, USA.
⁴ Cole Eye Institute, Cleveland Clinic Foundation, Cleveland, OH, USA.
⁵ Cleveland Clinic Lerner College of Medicine, Cleveland, OH, USA.
⁶ Center for Ophthalmic Bioinformatics, Cole Eye Institute, Cleveland Clinic Foundation, 9500 Euclid Ave. i32, Cleveland, OH, USA. talcotk@ccf.org.

^# Contributed equally.

Abstract

Background: Automated identification of spectral domain optical coherence tomography (SD-OCT) features can improve retina clinic workflow efficiency as they are able to detect pathologic findings. The purpose of this study was to test a deep learning (DL)-based algorithm for the identification of Idiopathic Full Thickness Macular Hole (IFTMH) features and stages of severity in SD-OCT B-scans.

Methods: In this cross-sectional study, subjects solely diagnosed with either IFTMH or Posterior Vitreous Detachment (PVD) were identified excluding secondary causes of macular holes, any concurrent maculopathies, or incomplete records. SD-OCT scans (512 × 128) from all subjects were acquired with CIRRUS^™ HD-OCT (ZEISS, Dublin, CA) and reviewed for quality. In order to establish a ground truth classification, each SD-OCT B-scan was labeled by two trained graders and adjudicated by a retina specialist when applicable. Two test sets were built based on different gold-standard classification methods. The sensitivity, specificity and accuracy of the algorithm to identify IFTMH features in SD-OCT B-scans were determined. Spearman's correlation was run to examine if the algorithm's probability score was associated with the severity stages of IFTMH.

Results: Six hundred and one SD-OCT cube scans from 601 subjects (299 with IFTMH and 302 with PVD) were used. A total of 76,928 individual SD-OCT B-scans were labeled gradable by the algorithm and yielded an accuracy of 88.5% (test set 1, 33,024 B-scans) and 91.4% (test set 2, 43,904 B-scans) in identifying SD-OCT features of IFTMHs. A Spearman's correlation coefficient of 0.15 was achieved between the algorithm's probability score and the stages of the 299 (47 [15.7%] stage 2, 56 [18.7%] stage 3 and 196 [65.6%] stage 4) IFTMHs cubes studied.

Conclusions: The DL-based algorithm was able to accurately detect IFTMHs features on individual SD-OCT B-scans in both test sets. However, there was a low correlation between the algorithm's probability score and IFTMH severity stages. The algorithm may serve as a clinical decision support tool that assists with the identification of IFTMHs. Further training is necessary for the algorithm to identify stages of IFTMHs.

Keywords: Artificial Intelligence; Deep learning; Macular hole; Optical coherence tomography.