Deep learning-based algorithm for the detection of idiopathic full thickness macular holes in spectral domain optical coherence tomography
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 identificati...
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2024-01-01
|
| Series: | International Journal of Retina and Vitreous |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40942-024-00526-8 |
| _version_ | 1827329011594821632 |
|---|---|
| author | 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 |
| author_facet | 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 |
| author_sort | Carolina C. S. Valentim |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-07T15:27:44Z |
| format | Article |
| id | doaj.art-5c9f90328cf747ae95092ddcc695acc2 |
| institution | Directory Open Access Journal |
| issn | 2056-9920 |
| language | English |
| last_indexed | 2024-03-07T15:27:44Z |
| publishDate | 2024-01-01 |
| publisher | BMC |
| record_format | Article |
| series | International Journal of Retina and Vitreous |
| spelling | doaj.art-5c9f90328cf747ae95092ddcc695acc22024-03-05T16:37:45ZengBMCInternational Journal of Retina and Vitreous2056-99202024-01-011011710.1186/s40942-024-00526-8Deep learning-based algorithm for the detection of idiopathic full thickness macular holes in spectral domain optical coherence tomographyCarolina C. S. Valentim0Anna K. Wu1Sophia Yu2Niranchana Manivannan3Qinqin Zhang4Jessica Cao5Weilin Song6Victoria Wang7Hannah Kang8Aneesha Kalur9Amogh I. Iyer10Thais Conti11Rishi P. Singh12Katherine E. Talcott13Center for Ophthalmic Bioinformatics, Cole Eye Institute, Cleveland Clinic FoundationCenter for Ophthalmic Bioinformatics, Cole Eye Institute, Cleveland Clinic FoundationCarl Zeiss Meditec, IncCarl Zeiss Meditec, IncCarl Zeiss Meditec, IncCole Eye Institute, Cleveland Clinic FoundationCleveland Clinic Lerner College of MedicineCase Western Reserve University School of MedicineCase Western Reserve University School of MedicineCenter for Ophthalmic Bioinformatics, Cole Eye Institute, Cleveland Clinic FoundationCenter for Ophthalmic Bioinformatics, Cole Eye Institute, Cleveland Clinic FoundationCenter for Ophthalmic Bioinformatics, Cole Eye Institute, Cleveland Clinic FoundationCenter for Ophthalmic Bioinformatics, Cole Eye Institute, Cleveland Clinic FoundationCenter for Ophthalmic Bioinformatics, Cole Eye Institute, Cleveland Clinic FoundationAbstract 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.https://doi.org/10.1186/s40942-024-00526-8Artificial IntelligenceDeep learningMacular holeOptical coherence tomography |
| spellingShingle | 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 Deep learning-based algorithm for the detection of idiopathic full thickness macular holes in spectral domain optical coherence tomography International Journal of Retina and Vitreous Artificial Intelligence Deep learning Macular hole Optical coherence tomography |
| title | Deep learning-based algorithm for the detection of idiopathic full thickness macular holes in spectral domain optical coherence tomography |
| title_full | Deep learning-based algorithm for the detection of idiopathic full thickness macular holes in spectral domain optical coherence tomography |
| title_fullStr | Deep learning-based algorithm for the detection of idiopathic full thickness macular holes in spectral domain optical coherence tomography |
| title_full_unstemmed | Deep learning-based algorithm for the detection of idiopathic full thickness macular holes in spectral domain optical coherence tomography |
| title_short | Deep learning-based algorithm for the detection of idiopathic full thickness macular holes in spectral domain optical coherence tomography |
| title_sort | deep learning based algorithm for the detection of idiopathic full thickness macular holes in spectral domain optical coherence tomography |
| topic | Artificial Intelligence Deep learning Macular hole Optical coherence tomography |
| url | https://doi.org/10.1186/s40942-024-00526-8 |
| work_keys_str_mv | AT carolinacsvalentim deeplearningbasedalgorithmforthedetectionofidiopathicfullthicknessmacularholesinspectraldomainopticalcoherencetomography AT annakwu deeplearningbasedalgorithmforthedetectionofidiopathicfullthicknessmacularholesinspectraldomainopticalcoherencetomography AT sophiayu deeplearningbasedalgorithmforthedetectionofidiopathicfullthicknessmacularholesinspectraldomainopticalcoherencetomography AT niranchanamanivannan deeplearningbasedalgorithmforthedetectionofidiopathicfullthicknessmacularholesinspectraldomainopticalcoherencetomography AT qinqinzhang deeplearningbasedalgorithmforthedetectionofidiopathicfullthicknessmacularholesinspectraldomainopticalcoherencetomography AT jessicacao deeplearningbasedalgorithmforthedetectionofidiopathicfullthicknessmacularholesinspectraldomainopticalcoherencetomography AT weilinsong deeplearningbasedalgorithmforthedetectionofidiopathicfullthicknessmacularholesinspectraldomainopticalcoherencetomography AT victoriawang deeplearningbasedalgorithmforthedetectionofidiopathicfullthicknessmacularholesinspectraldomainopticalcoherencetomography AT hannahkang deeplearningbasedalgorithmforthedetectionofidiopathicfullthicknessmacularholesinspectraldomainopticalcoherencetomography AT aneeshakalur deeplearningbasedalgorithmforthedetectionofidiopathicfullthicknessmacularholesinspectraldomainopticalcoherencetomography AT amoghiiyer deeplearningbasedalgorithmforthedetectionofidiopathicfullthicknessmacularholesinspectraldomainopticalcoherencetomography AT thaisconti deeplearningbasedalgorithmforthedetectionofidiopathicfullthicknessmacularholesinspectraldomainopticalcoherencetomography AT rishipsingh deeplearningbasedalgorithmforthedetectionofidiopathicfullthicknessmacularholesinspectraldomainopticalcoherencetomography AT katherineetalcott deeplearningbasedalgorithmforthedetectionofidiopathicfullthicknessmacularholesinspectraldomainopticalcoherencetomography |