2. Introduction
Artificial Intelligence (AI), refers to software that
can mimic cognitive functions such as learning
and problem solving.
Accomplishes tasks by processing and recognizing
patterns in large amounts of data.*
To Augment Not
Replace
*Kapoor R, Walters SP, Al-Aswad LA. The current state of artificial intelligence in ophthalmology. Surv Ophthalmol.
2019;64(2):233-240. doi:10.1016/j.survophthal.2018.09.002
3. TYPES OF AI
Simple Automated Detectors: identifies the presence or absence of
features
This rule-based algorithm assesses features and ultimately yields an
outcome (e.g. diagnosis) based on the patterns identified
Machine Learning: more advanced form of AI: the input into machine learning
a training dataset
(starts without knowledge and becomes intelligent)
Deep Learning:
(Mimics learning process of the human
brain)
4. Introduction
• Artificial intelligence (AI) has made
significant advancements in the
field of ophthalmology
• Has the potential to revolutionize
various aspects of eye care
5. Artificial Intelligence in Ophthalmology
HOW IT WORKS
Image Analysis
Treatment
Recommendatio
ns
Disease Risk
Prediction:
Data Integration
and Decision
Support:
Research and
Drug Discovery
Dose
Optimization
Akkara JD, Kuriakose A. Role of artificial intelligence and machine learning in ophthalmology. Kerala J
6. AI in Retina
2018
Diabetic Retinopathy (DR)
Retinopathy Of Prematurity (ROP)
Age-related Macular Degeneration (AMD)
7. AI in Diabetic Retinopathy
2018
• AI algorithms
• Analyze retinal images
• Identify signs of diabetic
retinopathy, such as
microaneurysms, hemorrhages,
and exudates.
• Screen large populations more
efficiently
• Enable early diagnosis and
intervention.
Abràmoff MD, Lavin PT, Birch M, Shah N, Folk JC. Pivotal trial
of an autonomous AI-based diagnostic system for detection of
diabetic retinopathy in primary care offices. NPJ Digit Med.
2018;1:39. doi:10.1038/s41746-018-0040-6
8. AI in Age-RelatedMacular Degeneration (AMD)
• AI algorithms can analyze : retinal images and
optical coherence tomography (OCT) scans
• Detects and classify different stages of AMD.
• Assists ophthalmologists in making accurate
diagnoses and monitoring disease progression.
Russakoff DB, Lamin A, Oakley JD, Dubis AM, Sivaprasad S. Deep Learning for Prediction of AMD Progression: A Pilot
Study. Invest Ophthalmol Vis Sci. 2019;60(2):712-722.
9. AI in Age-RelatedMacular Degeneration (AMD)
• i-ROPDL systemcan distinguish features
such as plus disease and is
comparable or better than expert
diagnosis
Brown JM, Campbell JP, Beers A, et al. Automated Diagnosis of Plus Disease in Retinopathy of Prematurity Using Deep
Convolutional Neural Networks. JAMA Ophthalmol. 2018;136(7):803-810. doi:10.1001/jamaophthalmol.2018.1934
10. AI in Glaucoma
• Glaucoma diagnosis and progression
monitoring
• Algorithms can analyze visual field
tests, optic nerve images, and oct scans
• Aid in early detection and personalized
treatment planning.
• Muhammad et al. developed a deep
learning algorithm that accurately
identifies glaucoma suspects, allowing
for more timely management
Muhammad H, Fuchs TJ, De Cuir N, et al. Hybrid Deep
Learning on Single Wide-field Optical Coherence
tomography Scans Accurately Classifies Glaucoma Suspects. J
11. AI in CATARACT:
The advent of AI can potentially transform the management of cataract in terms of assessment
and monitoring, IOL calculation, intraoperative feedback, and postoperative care.
• Detect and grade cataracts
• Resnet(residual neural network) to identify
referable cataracts
• Adequately guide plans for surgical
intervention
• Anticipate the likelihood of posterior
capsular opacification
• Calculating intraocular lens power(HILL-RBF
Akkara. Role of artificial intelligence and machine learning in
ophthalmology.
Liu X, Jiang J, Zhang K, et al. Localization and diagnosis
12. AI in Ocular Oncology
• Anticipate the course of periocular
reconstruction during surgical treatment of
basal cell carcinoma.
• Predict disease outcomes for choroidal
melanoma.
• Multispectral imaging system for the
detection of ocular surface squamous
neoplasia.
Akkara. Role of artificial intelligence and machine learning in
ophthalmology.
Habibalahi A, Bala C, Allende A, Anwer AG, Goldys EM. Novel
13. AI in Surgical Planning and Guidance
• Assist ophthalmic surgeons
• Provide preoperative planning
• Intraoperative guidance
• Determine optimal surgical approach
• Predict outcomes
• Offer guidance during surgical procedures
like cataract surgery or refractive surgery
Brummen A, Owen J, et al. Artificial intelligence automation of
eyelid and periorbital measurements. Investigative
14. AI in Teleophthalmology
• AI-powered teleophthalmology platforms
• Allows remote diagnosis and monitoring of eye
conditions.
• Patients can capture retinal images or perform
visual field tests at home, which are then
analyzed by AI algorithms.
• This enables access to eye care in underserved
areas and facilitates timely management of
eye diseases.
15. LIMITATIONS
• Data Bias: “garbage in, garbage out”
phenomenon
• Limited Generalization
• Lack of Explainability
• Regulatory and Ethical Considerations
• Cost and Infrastructure
16. Conclusion
• AI has transformative impact
• Algorithms have been designed for image
analysis, disease diagnosis, risk
prediction, treatment recommendations,
and surgical guidance
• May require significant investments in
terms of computational resources,
infrastructure, and training
• Need for responsible development,
validation, and ethical implementation
17. Thank you
Artifi cial I
ntelligenceispoised totransform thefi eld of
ophthalmology, revolutionizing diagnosis, treatment, and
patient care.
Byembracingthistechnology, we can improve outcomes,reduce
costs,and providebettereyecareforall.
Editor's Notes
Potential Applications of Artificial Intelligence in Ophthalmology
if the initial dataset presented to the machine is inadequate, then the predictions generated by the AI tool will be inaccurate. In some situations, output recommendations by AI tools may be simply incorrect.
Erroneous predictions by AI algorithms can bring up the issue of liability for physicians.
By complementing the role of physicians, AI has the potential to significantly improve patient care by increasing efficiency and outcomes as it becomes incorporated into clinical practice in the near future.