Prediction of treatment outcome for branch retinal vein occlusion using convolutional neural network-based retinal fluorescein angiography.
Artificial intelligence
Branch retinal vein occlusion
Convolutional neural network
Fundus fluorescence angiography
Journal
Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288
Informations de publication
Date de publication:
28 Aug 2024
28 Aug 2024
Historique:
received:
07
05
2024
accepted:
23
08
2024
medline:
31
8
2024
pubmed:
31
8
2024
entrez:
28
8
2024
Statut:
epublish
Résumé
Deep learning techniques were used in ophthalmology to develop artificial intelligence (AI) models for predicting the short-term effectiveness of anti-VEGF therapy in patients with macular edema secondary to branch retinal vein occlusion (BRVO-ME). 180 BRVO-ME patients underwent pre-treatment FFA scans. After 3 months of ranibizumab injections, CMT measurements were taken at baseline and 1-month intervals. Patients were categorized into good and poor prognosis groups based on macular edema at the 4th month follow-up. FFA-Net, a VGG-based classification network, was trained using FFA images from both groups. Class activation heat maps highlighted important locations. Benchmark models (DesNet-201, MobileNet-V3, ResNet-152, MansNet-75) were compared for training results. Performance metrics included accuracy, sensitivity, specificity, F1 score, and ROC curves. FFA-Net predicted BRVO-ME treatment effect with an accuracy of 88.63% and an F1 score of 0.89, with a sensitivity and specificity of 79.40% and 71.34%, respectively.The AUC of the ROC curve for the FFA-Net model was 0.71. The use of FFA based on deep learning technology has feasibility in predicting the treatment effect of BRVO-ME. The FFA-Net model constructed with the VGG model as the main body has good results in predicting the treatment effect of BRVO-ME. The typing of BRVO in FFA may be an important factor affecting the prognosis.
Identifiants
pubmed: 39198599
doi: 10.1038/s41598-024-71061-7
pii: 10.1038/s41598-024-71061-7
doi:
Substances chimiques
Ranibizumab
ZL1R02VT79
Angiogenesis Inhibitors
0
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
20018Informations de copyright
© 2024. The Author(s).
Références
Stem, M. S. et al. A longitudinal analysis of risk factors associated with central retinal vein occlusion. Ophthalmology 120(2), 362–370 (2013).
doi: 10.1016/j.ophtha.2012.07.080
pubmed: 23177364
Thapa, R. et al. Prevalence, pattern and risk factors of retinal vein occlusion in an elderly population in Nepal: The Bhaktapur retina study. BMC Ophthalmol. 17(1), 162 (2017).
doi: 10.1186/s12886-017-0552-x
pubmed: 28865424
pmcid: 5581447
Noma, H., Yasuda, K. & Shimura, M. Cytokines and the pathogenesis of Macular Edema in branch retinal vein occlusion. J. Ophthalmol. 2019, 5185128 (2019).
doi: 10.1155/2019/5185128
pubmed: 31191997
pmcid: 6525954
Song, P. et al. Global epidemiology of retinal vein occlusion:a systematic review and meta-analysis of prevalence, incidence, and risk factors. J. Glob. Health 9(1), 010427 (2019).
doi: 10.7189/jogh.09.010427
pubmed: 31131101
pmcid: 6513508
Khosravi, A. et al. The prevalence of pre-hypertension and hypertension in an Iranian urban population. High Blood Press Cardiovasc. Prev. 21(2), 127–135 (2014).
doi: 10.1007/s40292-013-0035-y
pubmed: 24272061
Kjeldsen, S. E. Hypertension and cardiovascular risk:general aspects. Pharmacol. Res. 129, 95–99 (2018).
doi: 10.1016/j.phrs.2017.11.003
pubmed: 29127059
Pacella, F. et al. Impact of cardiovascular risk factors on incidence and severity of retinal vein occlusion. Clin. Ter. 171, e534–e538 (2020).
pubmed: 33151253
Dugel, P. U., Bandello, F. & Loewenstein, A. Dexamethasone intravitreal implant in the treatment of diabetic macular edema. Clin. Ophthalmol. 9, 1321–1335 (2015).
doi: 10.2147/OPTH.S79948
pubmed: 26213460
pmcid: 4509543
Currie, G. et al. Machine learning and deep learning in medical imaging: Intelligent imaging. J. Med. Imaging Radiat. Sci. 50(4), 477–487 (2019).
doi: 10.1016/j.jmir.2019.09.005
pubmed: 31601480
Anwar, S. M. et al. Medical image analysis using convolutional neural networks: A review. J. Med. Syst. 42(11), 226 (2018).
doi: 10.1007/s10916-018-1088-1
pubmed: 30298337
Shaban, M. et al. A convolutional neural network for the screening and staging of diabetic retinopathy. PLoS One 15(6), e0233514 (2020).
doi: 10.1371/journal.pone.0233514
pubmed: 32569310
pmcid: 7307769
Albahli, S. & Ahmad Hassan Yar, G. N. Automated detection of diabetic retinopathy using custom convolutional neural network. J. X-Ray Sci. Technol. 30(2), 275–291 (2022).
Zhang, G. et al. Hypermixed convolutional neural network for retinal vein occlusion classification. Dis. Markers 2022, 1730501 (2022).
doi: 10.1155/2022/1730501
pubmed: 36408465
pmcid: 9674409
Miao, J. et al. Deep learning models for segmenting non-perfusion area of color fundus photographs in patients with branch retinal vein occlusion. Front. Med. (Lausanne) 9, 794045 (2022).
doi: 10.3389/fmed.2022.794045
pubmed: 35847781
Chen, Q. et al. Artificial intelligence can assist with diagnosing retinal vein occlusion. Int. J. Ophthalmol. 14(12), 1895–1902 (2021).
doi: 10.18240/ijo.2021.12.13
pubmed: 34926205
pmcid: 8640772
Ren, X. et al. Artificial intelligence to distinguish retinal vein occlusion patients using color fundus photographs. Eye (Lond) 37(10), 2026–2032 (2023).
doi: 10.1038/s41433-022-02239-4
pubmed: 36302974
Wang, S. H., Khan, M. A. & Zhang, Y. D. VISPNN: VGG-inspired stochastic pooling neural network. Comput. Mater Contin. 70(2), 3081–3097 (2022).
pubmed: 35615529
Daniel, J. et al. VGG-UNet/VGG-SegNet supported automatic segmentation of endoplasmic reticulum network in fluorescence microscopy images. Scanning 2022, 7733860 (2022).
doi: 10.1155/2022/7733860
pubmed: 35800206
pmcid: 9200602
Eberle, O. et al. Building and interpreting deep similarity models. IEEE Trans. Pattern Anal. Mach. Intell. 44(3), 1149–1161 (2022).
doi: 10.1109/TPAMI.2020.3020738
pubmed: 32870784
Rashno, E., Akbari, A. & Nasersharif, B. Uncertainty handling in convolutional neural networks. Neural Comput. Appl. 34(19), 16753–16769 (2022).
doi: 10.1007/s00521-022-07313-2
pubmed: 35756151
pmcid: 9206226
Yang J, Lai S, Wang X, et al. Diversity-Learning Block: Conquer Feature Homogenization of Multibranch. IEEE Trans Neural Netw Learn Syst.
Yoo, T. K. et al. The possibility of the combination of OCT and fundus images for improving the diagnostic accuracy of deep learning for age-related macular degeneration: a preliminary experiment. Med. Biol. Eng. Comput. 57(3), 677–687 (2019).
doi: 10.1007/s11517-018-1915-z
pubmed: 30349958
Sengupta, A. et al. Going deeper in spiking neural networks: VGG and residual architectures. Front Neurosci. 13, 95 (2019).
doi: 10.3389/fnins.2019.00095
pubmed: 30899212
pmcid: 6416793
Branch Vein Occlusion Study Group. Argon laser scatter photocoagulation for prevention of neovascularization and vitreous hemorrhage in branch vein occlusion. A randomized clinical trial. Arch Ophthalmol. 104(1), 34–41 (1986).