TY - JOUR
T1 - Quantification of Nonperfusion Area in Montaged Widefield OCT Angiography Using Deep Learning in Diabetic Retinopathy
AU - Guo, Yukun
AU - Hormel, Tristan T.
AU - Gao, Liqin
AU - You, Qisheng
AU - Wang, Bingjie
AU - Flaxel, Christina J.
AU - Bailey, Steven T.
AU - Choi, Dongseok
AU - Huang, David
AU - Hwang, Thomas S.
AU - Jia, Yali
N1 - Publisher Copyright:
© 2021 American Academy of Ophthalmology
PY - 2021/6
Y1 - 2021/6
N2 - Purpose: To examine the efficacy of a deep learning-based algorithm to quantify the nonperfusion area (NPA) on montaged widefield OCT angiography (OCTA) for assessment of diabetic retinopathy (DR) severity. Design: Cross-sectional study. Participants: One hundred thirty-seven participants with a full range of DR severity and 26 healthy participants. Methods: A deep learning-based algorithm was developed for detecting and quantifying NPA in the superficial vascular complex on widefield OCTA comprising 3 horizontally montaged 6 × 6-mm OCTA scans from the nasal, macular, and temporal regions. We trained the algorithm on 978 volumetric OCTA scans from all participants using 5-fold cross-validation. The algorithm can distinguish NPA from shadow artifacts. The F1 score evaluated segmentation accuracy. The area under the receiver operating characteristic curve and sensitivity with specificity fixed at 95% quantified network performance to distinguish patients with diabetes from healthy control participants, referable DR from nonreferable DR (nonproliferative DR [NPDR] less than moderate severity), and severe DR (severe NPDR, proliferative DR, or DR with edema) from nonsevere DR (mild to moderate NPDR). Main Outcome Measures: Widefield OCTA NPA, visual acuity (VA), and DR severities. Results: Automatically segmented NPA showed high agreement with the manually delineated ground truth, with a mean ± standard deviation F1 score of 0.78 ± 0.05 in nasal, 0.82 ± 0.07 in macular, and 0.78 ± 0.05 in temporal scans. The extrafoveal avascular area (EAA) in the macular scan showed the best sensitivity at 54% for differentiating those with diabetes from healthy control participants, whereas montaged widefield OCTA scan showed significantly higher sensitivity than macular scans (P < 0.0001, McNemar's test) for detecting eyes with DR at 66%, referable DR at 63%, and severe DR at 62%. Montaged widefield OCTA showed the highest correlation (Spearman ρ = 0.74; P < 0.0001) between EAA and DR severity. The macular scan showed the strongest negative correlation (Pearson ρ = –0.42; P < 0.0001) between EAA and best-corrected VA. Conclusions: A deep learning-based algorithm for montaged widefield OCTA can detect NPA accurately and can improve the detection of clinically important DR.
AB - Purpose: To examine the efficacy of a deep learning-based algorithm to quantify the nonperfusion area (NPA) on montaged widefield OCT angiography (OCTA) for assessment of diabetic retinopathy (DR) severity. Design: Cross-sectional study. Participants: One hundred thirty-seven participants with a full range of DR severity and 26 healthy participants. Methods: A deep learning-based algorithm was developed for detecting and quantifying NPA in the superficial vascular complex on widefield OCTA comprising 3 horizontally montaged 6 × 6-mm OCTA scans from the nasal, macular, and temporal regions. We trained the algorithm on 978 volumetric OCTA scans from all participants using 5-fold cross-validation. The algorithm can distinguish NPA from shadow artifacts. The F1 score evaluated segmentation accuracy. The area under the receiver operating characteristic curve and sensitivity with specificity fixed at 95% quantified network performance to distinguish patients with diabetes from healthy control participants, referable DR from nonreferable DR (nonproliferative DR [NPDR] less than moderate severity), and severe DR (severe NPDR, proliferative DR, or DR with edema) from nonsevere DR (mild to moderate NPDR). Main Outcome Measures: Widefield OCTA NPA, visual acuity (VA), and DR severities. Results: Automatically segmented NPA showed high agreement with the manually delineated ground truth, with a mean ± standard deviation F1 score of 0.78 ± 0.05 in nasal, 0.82 ± 0.07 in macular, and 0.78 ± 0.05 in temporal scans. The extrafoveal avascular area (EAA) in the macular scan showed the best sensitivity at 54% for differentiating those with diabetes from healthy control participants, whereas montaged widefield OCTA scan showed significantly higher sensitivity than macular scans (P < 0.0001, McNemar's test) for detecting eyes with DR at 66%, referable DR at 63%, and severe DR at 62%. Montaged widefield OCTA showed the highest correlation (Spearman ρ = 0.74; P < 0.0001) between EAA and DR severity. The macular scan showed the strongest negative correlation (Pearson ρ = –0.42; P < 0.0001) between EAA and best-corrected VA. Conclusions: A deep learning-based algorithm for montaged widefield OCTA can detect NPA accurately and can improve the detection of clinically important DR.
KW - Deep learning
KW - Diabetic retinopathy
KW - Nonperfusion area
KW - Widefield OCTA
UR - http://www.scopus.com/inward/record.url?scp=85116154767&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85116154767&partnerID=8YFLogxK
U2 - 10.1016/j.xops.2021.100027
DO - 10.1016/j.xops.2021.100027
M3 - Article
AN - SCOPUS:85116154767
SN - 2666-9145
VL - 1
JO - Ophthalmology Science
JF - Ophthalmology Science
IS - 2
M1 - 100027
ER -