State-of-the-Art of Deep Learning in Multidisciplinary Optical Coherence Tomography Applications

被引：1

作者：

Kalupahana, Deshan ^{[1
]}

Kahatapitiya, Nipun Shantha ^{[1
]}

Kamalathasan, Dilakshan ^{[1
]}

Wijesinghe, Ruchire Eranga ^{[2
,3
]}

Silva, Bhagya Nathali ^{[3
,4
]}

Wijenayake, Udaya ^{[1
]}

机构：

[1] Univ Sri Jayewardenepura, Fac Engn, Dept Comp Engn, Nugegoda 10250, Sri Lanka

[2] Sri Lanka Inst Informat Technol, Fac Engn, Dept Elect & Elect Engn, Malabe 10115, Sri Lanka

[3] Sri Lanka Inst Informat Technol, Ctr Excellence Informat Elect & Transmiss CIET, Malabe 10115, Sri Lanka

[4] Sri Lanka Inst Informat Technol, Fac Comp, Dept Informat Technol, Malabe 10115, Sri Lanka

来源：

IEEE ACCESS | 2024年 / 12卷

关键词：

Deep learning; Optical coherence tomography; Imaging; Ophthalmology; Image analysis; Reinforcement learning; Artificial neural networks; Unsupervised learning; Retina; Optical imaging; Classification; deep learning; enhancement; generation; optical coherence tomography; segmentation; DIABETIC MACULAR EDEMA; AUTOMATIC SEGMENTATION; NEURAL-NETWORK; IMAGE-ENHANCEMENT; OCT IMAGES; CLASSIFICATION; DEGENERATION; BOUNDARIES; ALGORITHM; DISEASE;

D O I：

10.1109/ACCESS.2024.3492389

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

Optical Coherence Tomography (OCT) emerged as a technology for the detection of retinal disease. Owing to its excellent performance and ability to provide in-vivo high-resolution images, the popularity increased dramatically across various application domains. Consequently, OCT has been widely used in other branches of medical applications, i.e., oncology and otolaryngology, industry, and agriculture. Despite its widespread use, OCT image analysis is an inherently subjective, laborious, and time-intensive task that requires expertise. Deep Learning (DL) stands as the current state-of-the-art method for image analysis. Hence, several research groups have directed their efforts toward incorporating DL algorithms with OCT imaging to reduce the time as well as the subjectivity. This article comprehensively reviews the principal technological advancements in DL methods applied across various OCT applications. Additionally, it explores the latest trends in developing DL methods for OCT, highlights their limitations, and discusses future opportunities in a comprehensive manner.

引用

页码：164462 / 164490

页数：29

共 191 条

[51] Retinal optical coherence tomography image enhancement via deep learning [J].

Halupka, Kerry J. ;

Antony, Bhavna J. ;

Lee, Matthew H. ;

Lucy, Katie A. ;

Rai, Ravneet S. ;

Ishikawa, Hiroshi ;

Wollstein, Gadi ;

Schuman, Joel S. ;

Garnavi, Rahil .

BIOMEDICAL OPTICS EXPRESS, 2018, 9 (12) :6205-6221

[52]

Hammoudeh A., 2018, Tech. Rep.

[53] Effect of patch size and network architecture on a convolutional neural network approach for automatic segmentation of OCT retinal layers [J].

Hamwood, Jared ;

Alonso-Caneiro, David ;

Read, Scott A. ;

Vincent, Stephen J. ;

Collins, Michael J. .

BIOMEDICAL OPTICS EXPRESS, 2018, 9 (07) :3049-3066

[54] Analysis of AI-Based Single-View 3D Reconstruction Methods for an Industrial Application [J].

Hartung, Julia ;

Dold, Patricia M. ;

Jahn, Andreas ;

Heizmann, Michael .

SENSORS, 2022, 22 (17)

[55]

Hassan A, 2022, Aswan University Journal of Sciences and Technology, V2, P11, DOI [10.21608/aujst.2022.259887, 10.21608/aujst.2022.259887, DOI 10.21608/AUJST.2022.259887]

[56] Choroid Segmentation of Retinal OCT Images Based on CNN Classifier and l2-lq Fitter [J].