TY - JOUR
T1 - Differentiating Glaucomatous Optic Neuropathy From Non-glaucomatous Optic Neuropathies Using Deep Learning Algorithms
AU - Vali, Mahsa
AU - Mohammadi, Massood
AU - Zarei, Nasim
AU - Samadi, Melika
AU - Atapour-Abarghouei, Amir
AU - Supakontanasan, Wasu
AU - Suwan, Yanin
AU - Subramanian, Prem S.
AU - Miller, Neil R.
AU - Kafieh, Rahele
AU - Aghsaei Fard, Masoud
N1 - Publisher Copyright:
© 2023 Elsevier Inc.
PY - 2023/8
Y1 - 2023/8
N2 - PURPOSE: A deep learning framework to differentiate glaucomatous optic disc changes due to glaucomatous optic neuropathy (GON) from non-glaucomatous optic disc changes due to non-glaucomatous optic neuropathies (NGONs). DESIGN: Cross-sectional study. METHOD: A deep-learning system was trained, validated, and externally tested to classify optic discs as normal, GON, or NGON, using 2183 digital color fundus photographs. A Single-Center data set of 1822 images (660 images of NGON, 676 images of GON, and 486 images of normal optic discs) was used for training and validation, whereas 361 photographs from 4 different data sets were used for external testing. Our algorithm removed the redundant information from the images using an optic disc segmentation (OD-SEG) network, after which we performed transfer learning with various pre-trained networks. Finally, we calculated sensitivity, specificity, F1-score, and precision to show the performance of the discrimination network in the validation and independent external data set. RESULTS: For classification, the algorithm with the best performance for the Single-Center data set was DenseNet121, with a sensitivity of 95.36%, precision of 95.35%, specificity of 92.19%, and F1 score of 95.40%. For the external validation data, the sensitivity and specificity of our network for differentiating GON from NGON were 85.53% and 89.02%, respectively. The glaucoma specialist who diagnosed those cases in masked fashion had a sensitivity of 71.05% and a specificity of 82.21%. CONCLUSIONS: The proposed algorithm for the differentiation of GON from NGON yields results that have a higher sensitivity than those of a glaucoma specialist, and its application for unseen data thus is extremely promising.
AB - PURPOSE: A deep learning framework to differentiate glaucomatous optic disc changes due to glaucomatous optic neuropathy (GON) from non-glaucomatous optic disc changes due to non-glaucomatous optic neuropathies (NGONs). DESIGN: Cross-sectional study. METHOD: A deep-learning system was trained, validated, and externally tested to classify optic discs as normal, GON, or NGON, using 2183 digital color fundus photographs. A Single-Center data set of 1822 images (660 images of NGON, 676 images of GON, and 486 images of normal optic discs) was used for training and validation, whereas 361 photographs from 4 different data sets were used for external testing. Our algorithm removed the redundant information from the images using an optic disc segmentation (OD-SEG) network, after which we performed transfer learning with various pre-trained networks. Finally, we calculated sensitivity, specificity, F1-score, and precision to show the performance of the discrimination network in the validation and independent external data set. RESULTS: For classification, the algorithm with the best performance for the Single-Center data set was DenseNet121, with a sensitivity of 95.36%, precision of 95.35%, specificity of 92.19%, and F1 score of 95.40%. For the external validation data, the sensitivity and specificity of our network for differentiating GON from NGON were 85.53% and 89.02%, respectively. The glaucoma specialist who diagnosed those cases in masked fashion had a sensitivity of 71.05% and a specificity of 82.21%. CONCLUSIONS: The proposed algorithm for the differentiation of GON from NGON yields results that have a higher sensitivity than those of a glaucoma specialist, and its application for unseen data thus is extremely promising.
UR - http://www.scopus.com/inward/record.url?scp=85153078278&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85153078278&partnerID=8YFLogxK
U2 - 10.1016/j.ajo.2023.02.016
DO - 10.1016/j.ajo.2023.02.016
M3 - Article
C2 - 36868341
AN - SCOPUS:85153078278
SN - 0002-9394
VL - 252
SP - 1
EP - 8
JO - American journal of ophthalmology
JF - American journal of ophthalmology
ER -