Current state of artificial intelligence applications in ophthalmology and their potential to influence clinical practice

被引：4

作者：

Shetty, Dasharathraj K. ^{[1
]}

Talasila, Abhiroop ^{[2
]}

Shanbhag, Swapna ^{[3
]}

Patil, Vathsala ^{[4
]}

Hameed, Zeehan ^{[5
]}

Naik, Nithesh ^{[6
]}

Raju, Adithya ^{[7
]}

机构：

[1] Manipal Acad Higher Educ, Manipal Inst Technol, Dept Humanities & Management, Manipal, Karnataka, India

[2] Manipal Acad Higher Educ, Manipal Inst Technol, Dept Comp Sci Engn, Manipal, Karnataka, India

[3] LV Prasad Eye Inst, Cornea & Ocular Surface, Hyderabad, Telangana, India

[4] Manipal Acad Higher Educ, Manipal Coll Dent Sci, Dept Oral Med & Radiol, Manipal, Karnataka, India

[5] Manipal Acad Higher Educ, Kasturba Med Coll, Dept Urol, Manipal, Karnataka, India

[6] Manipal Acad Higher Educ, Manipal Inst Technol, Dept Mech & Mfg Engn, Manipal, Karnataka, India

[7] Univ Stockholm, KTH Royal Inst Technol, Med Engn, Brinellvagen 8, S-11428 Stockholm, Sweden

来源：

COGENT ENGINEERING | 2021年 / 8卷 / 01期

关键词：

Artificial intelligence; machine learning; neural networks; ophthalmology; deep learning; diabetic retinopathy; age-related macular degeneration; diagnosis; diagnostic imaging; image interpretation; DIABETIC-RETINOPATHY; MACULAR DEGENERATION; AUTOMATED DETECTION; ALGORITHM; FEATURES; AMD;

D O I：

10.1080/23311916.2021.1920707

中图分类号：

T [工业技术];

学科分类号：

08 ;

摘要：

Artificial intelligence (AI) has emerged as a major frontier in healthcare and finds broad range of applications. It has the potential to revolutionize current procedures of disease diagnosis and treatment, thus influencing the clinical practice. Artificial intelligence (AI) in ophthalmology, primarily concentrates on diagnostic and treatment pathways for eye conditions such as cataract, glaucoma, age-related macular degeneration (MDA) and diabetic retinopathy (DR). The purpose of this article is to systematically review the existing state of literature on the various AI techniques and its applications in the diagnosis and treatment of eye diseases and conduct an in-depth enquiry to identify the challenges in accurate detection, pre-processing of data, monitoring and assessment through various AI algorithms. The results suggest that all AI models proposed reduce the detection time considerably. The potential limitations and challenges in the development and application play a significant role in clinical practice. There is a need for the development of AI-assisted technologies that shall consider the clinical implications based on experience and guided by patient-centred healthcare principles. The diagnostic models should assist ophthalmologists on making quick and accurate decisions in determining the progression of various ocular diseases.

引用

页数：16

共 46 条

[1] Improved Automated Detection of Diabetic Retinopathy on a Publicly Available Dataset Through Integration of Deep Learning [J].