Preface xxv
Abhishek KUMAR, Priya BATTA and J.P. ANANTH

Introduction xxvii
Abhishek KUMAR, Priya BATTA and J.P. ANANTH

Chapter 1. ML-driven Early Detection of Retinal Diseases in Primary Care Settings 1
V.H. KARAMBELKAR and Patil Ashish N.

1.1. Introduction 1
1.2. Burden of retinal diseases and importance of early detection 3
1.3. ML approaches for retinal disease detection 5
1.4. Applications in primary care settings 8
1.5. Validation and clinical implementation studies 11
1.6. Challenges and limitations 13
1.7. Future directions and emerging trends 15
1.8. Conclusion 16
1.9. References 17

Chapter 2. Explainable AI in Ophthalmology: Building Trust in Automated Diagnosis 21
B.S. JOSHI and Jujar Komal M.

2.1. Introduction 21
2.2. Foundations of explainable AI 23
2.3. Applications of XAI in ophthalmology 26
2.4. Challenges in implementing explainable AI in ophthalmology 28
2.5. Future directions and opportunities 30
2.6. Conclusion 34
2.7. References 35

Chapter 3. Federated Learning Approaches for Privacy-Preserving Ophthalmic AI Models 39
Girish Arun GADRE and Pawar Atul NAMDEV

3.1. Introduction 39
3.2. Fundamentals of FL in healthcare 41
3.3. Applications of FL in ophthalmology 44
3.4. Technical challenges in ophthalmic FL 46
3.5. Privacy and security enhancements in ophthalmic FL 50
3.6. The future of FL in ophthalmology and clinical applications 52
3.7. Conclusion 54
3.8. References 54

Chapter 4. AI-Powered Screening for Diabetic Retinopathy in Underserved Populations 57
Anjali PATIL and Kadam Shrikant RANGRAO

4.1. Introduction 57
4.2. Overview of AI in medical imaging 59
4.3. AI-powered DR screening technologies 60
4.4. Applications in underserved populations 64
4.5. Challenges and limitations 66
4.6. Future directions 68
4.7. Conclusion 69
4.8. References 70

Chapter 5. Deep Learning for Multimodal Integration in Retinal Disease Classification 73
Gaurav PARANJPE and Inamdar Sharifnawaj Y.

5.1. Introduction 73
5.2. Retinal diseases: clinical and imaging perspectives 74
5.3. Imaging modalities in retinal disease classification 76
5.4. Deep learning in ophthalmology 78
5.5. Multimodal integration strategies 80
5.6. Challenges and limitations 84
5.7. Emerging trends and future directions 85
5.8. Conclusion 86
5.9. References 87

Chapter 6. Optimizing Ophthalmic Surgery Outcomes Using Predictive ML Algorithms 91
D.B. SHIRKE and Patil Zunjar V.

6.1. Introduction 92
6.2. Overview of ML in ophthalmology 93
6.3. Applications of predictive ML in specific ophthalmic surgeries 96
6.4. Methodological frameworks of predictive ML models 99
6.5. Imaging, EHR and cloud-based integration 100
6.6. Benefits in clinical practice 102
6.7. Challenges and limitations 104
6.8. Future directions 105
6.9. Conclusion 107
6.10. References 107

Chapter 7. The Role of Reinforcement Learning in Adaptive Vision Therapy 111
Sanvedya KADAM and Shinde Patil Girisha SURESH

7.1. Introduction 111
7.2. Overview of adaptive vision therapy 113
7.3. Fundamentals of RL for healthcare applications 114
7.4. RL in adaptive vision therapy: applications and case studies 116
7.5. Challenges and future directions 120
7.6. Conclusion 122
7.7. References 123

Chapter 8. Augmenting Human Expertise: AI Decision Support Systems in Ophthalmology Clinics 127
Prajakta PATIL and Natu Milind A.

8.1. Introduction 128
8.2. Evolution of AI decision support in ophthalmology 129
8.3. Core AI technologies in ophthalmology decision support systems 130
8.4. Clinical applications of AI decision support systems in ophthalmology 132
8.5. AI DSS implementation in ophthalmology clinics 133
8.6. Ethical, legal and privacy concerns in AI DSS for ophthalmology 135
8.7. Challenges and limitations of AI DSS in ophthalmology 138
8.8. Future prospects of AI DSS in ophthalmology 140
8.9. Conclusion 142
8.10. References 142

Chapter 9. Transfer Learning Applications for Rare Ocular Disease Detection 145
Sonali PATIL and Shinde Rutuja P.

9.1. Introduction 145
9.2. Fundamentals of transfer learning in medical imaging 147
9.3. Transfer learning applications in rare ocular disease detection 149
9.4. Challenges and limitations 153
9.5. Future directions and clinical translation 155
9.6. Conclusion 158
9.7. References 158

Chapter 10. Real-Time AI Assistance in Slit-Lamp Examination and Diagnosis 163
Renuka SARWATE and Deshmukh Manoj JANARDHAN

10.1. Introduction 163
10.2. Technological foundations of real-time AI in slit-lamp examination 166
10.3. Clinical applications of real-time AI in slit-lamp examination 168
10.4. Ethical complications and challenges in real-system AI-assisted slit-lamp examination 172
10.5. Future prospects and opportunities of real-time AI-assisted slit-lamp examination 174
10.6. Conclusion 177
10.7. References 178Contents xv

Chapter 11. Unsupervised Learning Techniques for Discovery of Novel Retinal Biomarkers 181
V.H. KARAMBELKAR and Sonake Vanita V.

11.1. Introduction 181
11.2. Unsupervised learning methodologies for retinal imaging 183
11.3. Applications of unsupervised learning in retinal biomarker discovery 186
11.4. Challenges and limitations 190
11.5. Future directions 192
11.6. Conclusion 194
11.7. References 195

Chapter 12. Developing Robust AI Models Against Bias in Ophthalmic Datasets 199
B.S. JOSHI and Naikawadi Swapnil SANJAY

12.1. Introduction 199
12.2. Sources of bias in ophthalmic datasets 201
12.3. Approaches to bias detection and quantification 204
12.4. Strategies for mitigating bias in ophthalmic AI models 206
12.5. Clinical and ethical implications 209
12.6. Future directions 211
12.7. Conclusion 212
12.8. References 213

Chapter 13. Self-Supervised Learning for Retinal Image Feature Extraction in Low-Label Settings 217
Girish Arun GADRE and Patil Monika VIRENDRA

13.1. Introduction 218
13.2. Principles of SSL in medical imaging 219
13.3. Retinal image feature extraction by methods of SSL 221
13.4. Applications of SSL in retinal image analysis 225
13.5. Challenges, limitations and future directions 227
13.6. Conclusion 230
13.7. References 231

Chapter 14. ML-Enhanced OCT Image Segmentation for Glaucoma Progression Monitoring 235
Anjali PATIL and Patil Milin D.

14.1. Introduction 235
14.2. OCT in glaucoma diagnosis and monitoring 237
14.3. Principles of ML for medical image segmentation 239
14.4. ML-enhanced OCT segmentation: techniques and architectures 241
14.5. Applications in glaucoma progression monitoring 245
14.6. Challenges and limitations 247
14.7. Future directions 249
14.8. Conclusion 251
14.9. References 251

Chapter 15. Predictive Modeling of Myopia Progression in Children Using AI 255
Gaurav PARANJPE and Petkar Rajendra VASANTRAO

15.1. Introduction 255
15.2. Epidemiology and burden of childhood myopia 257
15.3. Risk factors in myopia progression 258
15.4. Traditional prediction methods and limitations 261
15.5. AI in ophthalmology 262
15.6. AI techniques for predictive modeling of myopia 263
15.7. Applications of AI models in predicting myopia progression 266
15.8. Intervention with clinical decision-making and personalized care 267
15.9. Challenges and limitations of AI-based prediction 269
15.10. Future directions in AI-driven myopia prediction 270
15.11. Conclusion 271
15.12. References 272

Chapter 16. Combining Genomics and Imaging Data in Ophthalmology Using Multimodal AI 275
D.B. SHIRKE and Garagate Amruta K.

16.1. Introduction to multimodal AI in ophthalmology 276
16.2. Genomics in ophthalmology 277
16.3. Advances in ophthalmic imaging for AI applications 280
16.4. Integration of genomics and imaging data using multimodal AI 282
16.5. Challenges, limitations and future directions 285
16.6. Conclusion 288
16.7. References 288

Chapter 17. Benchmarking Ophthalmology AI Models: Challenges in Dataset Standardization 293
Sanvedya KADAM and Bardol Shabana M.

17.1. Introduction 293
17.2. The role of AI in ophthalmology 295
17.3. Current practices in dataset development 297
17.4. Challenges in dataset standardization 299
17.5. Benchmarking ophthalmology AI models 303
17.6. Recent initiatives toward standardization 305
17.7. Regulatory and ethical considerations 306
17.8. Conclusion 308
17.9. References 308

Chapter 18. NLP for Clinical Note Analysis in Ophthalmic Practice 313
Prajakta PATIL and Kadam Shweta A.

18.1. Introduction 313
18.2. Evolution of NLP in healthcare and relevance to ophthalmology 315
18.3. Challenges of clinical note analysis in ophthalmology 317
18.4. Applications of NLP in ophthalmology 320
18.5. Emerging trends in ophthalmic NLP 323
18.6. Ethical, privacy and practical considerations 325
18.7. Future directions 326
18.8. Conclusion 328
18.9. References 329

Chapter 19. Using ML to Analyze Eye Movement Patterns in Neurological and Psychiatric Diagnosis 333
Sonali PATIL and Kale Amruta B.

19.1. Introduction 333Contents xxiii
19.2. The window of mental activity of the brain is the eye movement 335
19.3. Eye-tracking technologies and data acquisition 338
19.4. Machine learning for eye movement analysis 340
19.5. Applications in neurological disorders 343
19.6. Applications in psychiatric disorders 344
19.7. Challenges and limitations 346
19.8. Future directions 347
19.9. Conclusion 348
19.10. References 349

Chapter 20. AI for Personalized Drug Response Prediction in Age-related Macular Degeneration 353
Renuka SARWATE and Patil Ashish N.

20.1. Introduction 354
20.2. AI in ophthalmology: a brief overview 355
20.3. Pathophysiology of AMD and drug response variability 356
20.4. Current therapeutic landscape in AMD 358
20.5. Personalized medicine in ophthalmology 359
20.6. AI approaches for drug response prediction in AMD 360
20.7. Challenges in data, bias and model generalizability 364
20.8. The actual purpose of AI 365
20.9. Future directions 366
20.10. Conclusion 367
20.11. References 368

List of Authors 371
Index 375