Research Article
Volume 12 Issue 8 - 2021
Automated Deep Learning-Based Multi-Class Fluid Segmentation in Swept-Source Optical Coherence Tomography Images
Jonathan D Oakley1*, Simrat K Sodhi2, Daniel B Russakoff1 and Netan Choudhry3,4,5
1Voxeleron LLC, San Francisco, CA, USA
2University of Cambridge, Cambridge, UK
3Vitreous Retina Macula Specialists of Toronto, Etobicoke, ON, Canada
4Department of Ophthalmology and Visual Sciences, University of Toronto, Toronto, ON, Canada
5Cleveland Clinic Canada, Toronto, ON, Canada
*Corresponding Author: Jonathan D Oakley, Voxeleron LLC, San Francisco, CA, USA.
Received: July 04, 2021; Published: July 31, 2021


Background: To evaluate the performance of a deep learning-based, automated, multi-class, macular fluid segmentation algorithm relative to expert annotations in a heterogeneous population of confirmed wet age-related macular degeneration (wAMD) subjects.

Methods: Twenty-two swept-source optical coherence tomography (SS-OCT) volumes of the macula, comprising 5,632 images from 20 subjects with wAMD, were manually annotated by two expert graders. Results were compared using cross-validation (CV) to automated segmentations using a deep learning-based algorithm encoding spatial information about retinal tissue as an additional input to the network. The algorithm delineates fluid regions in the OCT data, differentiating between intra- and sub-retinal fluid (IRF, SRF), as well as fluid resulting from in serous pigment epithelial detachments (PED). Standard metrics for fluid detection and quantification were used to evaluate performance.

Results: The per slice receiver operating characteristic (ROC) area under the curves (AUCs) for each fluid type were 0.900, 0.945 and 0.939 for IRF, SRF and PED, respectively (95% confidence intervals: 0.886 - 0.912, 0.939 - 0.950 and 0.928 - 0.948). Per volume results were 0.944 and 0.876 for IRF and PED (95% confidence intervals: 0.714 - 1.000 and 0.574 - 1.000); SRF was present in all cases. The correlations (R2) of fluid volume between expert graders and the algorithm were 0.992 for IRF, 0.986 for SRF and 0.820 for PED.

Conclusion: Automated, deep learning-based segmentation can accurately quantify different macular fluid types in SS-OCT data and in strong agreement with expert graders.


Keywords: Age-Related Macular Degeneration; Optical Coherence Tomography; Computer Vision; Deep Learning


  1. Anderson GF and Hussey PS. “Population Aging: A Comparison Among Industrialized Countries: Populations around the world are growing older, but the trends are not cause for despair”. Health Affairs3 (2000): 191-203.
  2. Mitchell P., et al. “Age-related macular degeneration”. The Lancet10153 (2018): 1147-1159.
  3. Wong WL., et al. “Global prevalence of age-related macular degeneration and disease burden projection for 2020 and 2040: a systematic review and meta-analysis”. The Lancet Global Health2 (2014): e106-116.
  4. Zhao S., et al. “Protocol of global incidence and progression of age-related macular degeneration: a systematic review”. Medicine10 (2019).
  5. Pennington KL and DeAngelis MM. “Epidemiology of age-related macular degeneration (AMD): associations with cardiovascular disease phenotypes and lipid factors”. Eye and Vision1 (2016): 34.
  6. Lalwani GA., et al. “A variable-dosing regimen with intravitreal ranibizumab for neovascular age-related macular degeneration: year 2 of the PrONTO Study”. American Journal of Ophthalmology1 (2009): 43-58.
  7. El-Emam S., et al. “Correlation of spectral domain optical coherence tomography characteristics with visual acuity in eyes with subfoveal scarring after treatment for wet age-related macular degeneration”. Retina6 (2013): 1249-1257.
  8. Guymer R and Wu Z. “Age‐related macular degeneration (AMD): More than meets the eye. The role of multimodal imaging in today’s management of AMD”. Clinical and Experimental Ophthalmology (2020).
  9. Asrani S., et al. “Artifacts in spectral-domain optical coherence tomography measurements in glaucoma”. JAMA Ophthalmology 4 (2014): 396-402.
  10. Chen JJ and Kardon RH. “Avoiding clinical misinterpretation and artifacts of optical coherence tomography analysis of the optic nerve, retinal nerve fiber layer, and ganglion cell layer”. Journal of Neuro-Ophthalmology 4 (2016): 417.
  11. Schlegl T., et al. “Fully automated detection and quantification of macular fluid in OCT using deep learning”. Ophthalmology4 (2018): 549-558.
  12. Mehta N., et al. “Model-to-Data Approach for Deep Learning in Optical Coherence Tomography Intraretinal Fluid Segmentation”. JAMA Ophthalmology (2020).
  13. Bogunović H., et al. “RETOUCH: The retinal OCT fluid detection and segmentation benchmark and challenge”. IEEE Transactions on Medical Imaging 8 (2019): 1858-1874.
  14. De Fauw J., et al. “Clinically applicable deep learning for diagnosis and referral in retinal disease”. Nature Medicine 9 (2018): 1342-1350.
  15. Bogunović H., et al. “Geodesic graph cut based retinal fluid segmentation in optical coherence tomography”. Proceedings of the Ophthalmic Medical Image Analysis Second International Workshop, OMIA 2015, Held in Conjunction with MICCAI 2015, Munich, Germany 9 (2015): 49-56.
  16. Ronneberger O., et al. “U-net: Convolutional networks for biomedical image segmentation”. In International Conference on Medical Image Computing and Computer-Assisted Intervention 5 (2015): 234-241.
  17. Badrinarayanan V., et al. “Segnet: A deep convolutional encoder-decoder architecture for image segmentation”. IEEE Transactions on Pattern Analysis and Machine Intelligence12 (2017): 2481-2495.
  18. Zeiler MD. “Adadelta: an adaptive learning rate method”. arXiv preprint arXiv (2012).
  19. Maloca PM., et al. “Validation of automated artificial intelligence segmentation of optical coherence tomography images”. PloS one8 (2019): e0220063.
  20. Sogawa T., et al. “Accuracy of a deep convolutional neural network in the detection of myopic macular diseases using swept-source optical coherence tomography”. Plos one4 (2020): e0227240.
  21. Potsaid B., et al. “Ultrahigh Speed and Multiscale Volumetric 1050nm Ophthalmic OCT Imaging at 100,000-400,000 Axial Scans per Second”. Investigative Ophthalmology and Visual Science14 (2011): 1319-1319.
  22. Rashno A., et al. “Fully-automated segmentation of fluid regions in exudative age-related macular degeneration subjects: Kernel graph cut in neutrosophic domain”. PloS one10 (2017): e0186949.
  23. González A., et al. “Automatic cyst detection in OCT retinal images combining region flooding and texture analysis”. In Proceedings of the 26th IEEE International Symposium on Computer-Based Medical Systems 20 (2013): 397-400.
  24. Wilkins GR., et al. “Automated segmentation of intraretinal cystoid fluid in optical coherence tomography”. IEEE Transactions on Biomedical Engineering4 (2012): 1109-1114.
  25. Wang J., et al. “Automated volumetric segmentation of retinal fluid on optical coherence tomography”. Biomedical Optics Express4 (2016): 1577-1589.
  26. Roy AG., et al. “ReLayNet: retinal layer and fluid segmentation of macular optical coherence tomography using fully convolutional networks”. Biomedical Optics Express8 (2017): 3627-3642.
  27. Lee CS., et al. “Deep-learning based, automated segmentation of macular edema in optical coherence tomography”. Biomedical Optics Express7 (2017): 3440-3448.
  28. Roberts PK., et al. “Quantification of Fluid Resolution and Visual Acuity Gain in Patients With Diabetic Macular Edema Using Deep Learning: A Post Hoc Analysis of a Randomized Clinical Trial”. JAMA Ophthalmology (2020).
  29. Lu D., et al. “Deep-learning based multiclass retinal fluid segmentation and detection in optical coherence tomography images using a fully convolutional neural network”. Medical Image Analysis 54 (2019): 100-110.
  30. Moraes G., et al. “Quantitative Analysis of OCT for Neovascular Age-Related Macular Degeneration Using Deep Learning”. Ophthalmology (2020).
  31. Toth CA., et al. “Identification of fluid on optical coherence tomography by treating ophthalmologists versus a reading center in the comparison of age-related macular degeneration treatments trials (CATT)”. Retina 7 (2015): 1303.
Citation: Jonathan D Oakley., et al. “Automated Deep Learning-Based Multi-Class Fluid Segmentation in Swept-Source Optical Coherence Tomography Images”. EC Ophthalmology 12.8 (2021): 24-37.

PubMed Indexed Article

EC Pharmacology and Toxicology
LC-UV-MS and MS/MS Characterize Glutathione Reactivity with Different Isomers (2,2' and 2,4' vs. 4,4') of Methylene Diphenyl-Diisocyanate.

PMID: 31143884 [PubMed]

PMCID: PMC6536005

EC Pharmacology and Toxicology
Alzheimer's Pathogenesis, Metal-Mediated Redox Stress, and Potential Nanotheranostics.

PMID: 31565701 [PubMed]

PMCID: PMC6764777

EC Neurology
Differences in Rate of Cognitive Decline and Caregiver Burden between Alzheimer's Disease and Vascular Dementia: a Retrospective Study.

PMID: 27747317 [PubMed]

PMCID: PMC5065347

EC Pharmacology and Toxicology
Will Blockchain Technology Transform Healthcare and Biomedical Sciences?

PMID: 31460519 [PubMed]

PMCID: PMC6711478

EC Pharmacology and Toxicology
Is it a Prime Time for AI-powered Virtual Drug Screening?

PMID: 30215059 [PubMed]

PMCID: PMC6133253

EC Psychology and Psychiatry
Analysis of Evidence for the Combination of Pro-dopamine Regulator (KB220PAM) and Naltrexone to Prevent Opioid Use Disorder Relapse.

PMID: 30417173 [PubMed]

PMCID: PMC6226033

EC Anaesthesia
Arrest Under Anesthesia - What was the Culprit? A Case Report.

PMID: 30264037 [PubMed]

PMCID: PMC6155992

EC Orthopaedics
Distraction Implantation. A New Technique in Total Joint Arthroplasty and Direct Skeletal Attachment.

PMID: 30198026 [PubMed]

PMCID: PMC6124505

EC Pulmonology and Respiratory Medicine
Prevalence and factors associated with self-reported chronic obstructive pulmonary disease among adults aged 40-79: the National Health and Nutrition Examination Survey (NHANES) 2007-2012.

PMID: 30294723 [PubMed]

PMCID: PMC6169793

EC Dental Science
Important Dental Fiber-Reinforced Composite Molding Compound Breakthroughs

PMID: 29285526 [PubMed]

PMCID: PMC5743211

EC Microbiology
Prevalence of Intestinal Parasites Among HIV Infected and HIV Uninfected Patients Treated at the 1o De Maio Health Centre in Maputo, Mozambique

PMID: 29911204 [PubMed]

PMCID: PMC5999047

EC Microbiology
Macrophages and the Viral Dissemination Super Highway

PMID: 26949751 [PubMed]

PMCID: PMC4774560

EC Microbiology
The Microbiome, Antibiotics, and Health of the Pediatric Population.

PMID: 27390782 [PubMed]

PMCID: PMC4933318

EC Microbiology
Reactive Oxygen Species in HIV Infection

PMID: 28580453 [PubMed]

PMCID: PMC5450819

EC Microbiology
A Review of the CD4 T Cell Contribution to Lung Infection, Inflammation and Repair with a Focus on Wheeze and Asthma in the Pediatric Population

PMID: 26280024 [PubMed]

PMCID: PMC4533840

EC Neurology
Identifying Key Symptoms Differentiating Myalgic Encephalomyelitis and Chronic Fatigue Syndrome from Multiple Sclerosis

PMID: 28066845 [PubMed]

PMCID: PMC5214344

EC Pharmacology and Toxicology
Paradigm Shift is the Normal State of Pharmacology

PMID: 28936490 [PubMed]

PMCID: PMC5604476

EC Neurology
Examining those Meeting IOM Criteria Versus IOM Plus Fibromyalgia

PMID: 28713879 [PubMed]

PMCID: PMC5510658

EC Neurology
Unilateral Frontosphenoid Craniosynostosis: Case Report and a Review of the Literature

PMID: 28133641 [PubMed]

PMCID: PMC5267489

EC Ophthalmology
OCT-Angiography for Non-Invasive Monitoring of Neuronal and Vascular Structure in Mouse Retina: Implication for Characterization of Retinal Neurovascular Coupling

PMID: 29333536 [PubMed]

PMCID: PMC5766278

EC Neurology
Longer Duration of Downslope Treadmill Walking Induces Depression of H-Reflexes Measured during Standing and Walking.

PMID: 31032493 [PubMed]

PMCID: PMC6483108

EC Microbiology
Onchocerciasis in Mozambique: An Unknown Condition for Health Professionals.

PMID: 30957099 [PubMed]

PMCID: PMC6448571

EC Nutrition
Food Insecurity among Households with and without Podoconiosis in East and West Gojjam, Ethiopia.

PMID: 30101228 [PubMed]

PMCID: PMC6086333

EC Ophthalmology
REVIEW. +2 to +3 D. Reading Glasses to Prevent Myopia.

PMID: 31080964 [PubMed]

PMCID: PMC6508883

EC Gynaecology
Biomechanical Mapping of the Female Pelvic Floor: Uterine Prolapse Versus Normal Conditions.

PMID: 31093608 [PubMed]

PMCID: PMC6513001

EC Dental Science
Fiber-Reinforced Composites: A Breakthrough in Practical Clinical Applications with Advanced Wear Resistance for Dental Materials.

PMID: 31552397 [PubMed]

PMCID: PMC6758937

EC Microbiology
Neurocysticercosis in Child Bearing Women: An Overlooked Condition in Mozambique and a Potentially Missed Diagnosis in Women Presenting with Eclampsia.

PMID: 31681909 [PubMed]

PMCID: PMC6824723

EC Microbiology
Molecular Detection of Leptospira spp. in Rodents Trapped in the Mozambique Island City, Nampula Province, Mozambique.

PMID: 31681910 [PubMed]

PMCID: PMC6824726

EC Neurology
Endoplasmic Reticulum-Mitochondrial Cross-Talk in Neurodegenerative and Eye Diseases.

PMID: 31528859 [PubMed]

PMCID: PMC6746603

EC Psychology and Psychiatry
Can Chronic Consumption of Caffeine by Increasing D2/D3 Receptors Offer Benefit to Carriers of the DRD2 A1 Allele in Cocaine Abuse?

PMID: 31276119 [PubMed]

PMCID: PMC6604646

EC Anaesthesia
Real Time Locating Systems and sustainability of Perioperative Efficiency of Anesthesiologists.

PMID: 31406965 [PubMed]

PMCID: PMC6690616

EC Pharmacology and Toxicology
A Pilot STEM Curriculum Designed to Teach High School Students Concepts in Biochemical Engineering and Pharmacology.

PMID: 31517314 [PubMed]

PMCID: PMC6741290

EC Pharmacology and Toxicology
Toxic Mechanisms Underlying Motor Activity Changes Induced by a Mixture of Lead, Arsenic and Manganese.

PMID: 31633124 [PubMed]

PMCID: PMC6800226

EC Neurology
Research Volunteers' Attitudes Toward Chronic Fatigue Syndrome and Myalgic Encephalomyelitis.

PMID: 29662969 [PubMed]

PMCID: PMC5898812

EC Pharmacology and Toxicology
Hyperbaric Oxygen Therapy for Alzheimer's Disease.

PMID: 30215058 [PubMed]

PMCID: PMC6133268

News and Events

February Issue Release

We always feel pleasure to share our updates with you all. Here, notifying you that we have successfully released the February issue of respective journals and the latest articles can be viewed on the current issue pages.

Submission Deadline for Upcoming Issue

ECronicon delightfully welcomes all the authors around the globe for effective collaboration with an article submission for the upcoming issue of respective journals. Submissions are accepted on/before February 17, 2023.

Certificate of Publication

ECronicon honors with a "Publication Certificate" to the corresponding author by including the names of co-authors as a token of appreciation for publishing the work with our respective journals.

Best Article of the Issue

Editors of respective journals will always be very much interested in electing one Best Article after each issue release. The authors of the selected article will be honored with a "Best Article of the Issue" certificate.

Certifying for Review

ECronicon certifies the Editors for their first review done towards the assigned article of the respective journals.

Latest Articles

The latest articles will be updated immediately on the articles in press page of the respective journals.