A Systematic Review of Deep Learning Applications for Optical Coherence Tomography in Age-Related Macular Degeneration

Paul, Samantha K.; Pan, Ian; Sobol, Warren M.

doi:10.1097/iae.0000000000003535

Cited by 13 publications

(9 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning applications for OCT in AMD have shown tremendous growth over the past several years. They have been reported to achieve high performance in the quantitative analysis of disease including AMD classification, segmentation of retinal layers, assessing for progression, response to treatment in clinical trials, or predicting visual function [45 ▪▪ ,46]. Deep learning models have been formulated to identify both iRORA and cRORA lesions within an OCT B-scan volume, achieving similar sensitivity compared with human graders [47,48].…”

Section: Artificial Intelligencementioning

confidence: 99%

“…An automated deep learning assessment using SD-OCT scans for GA progression was retrospectively utilized to identify disease activity and the effect of pegcetacoplan in GA patients in the FILLY trial (NCT02503332) [51]. Despite these many advances, external validation within these investigations is often seen to be limited, and more prospective studies which demonstrate generalizability and clinical utility are needed [45 ▪▪ ].…”

Section: Artificial Intelligencementioning

confidence: 99%

See 1 more Smart Citation

Identifying geographic atrophy

Clevenger

Rachitskaya

2023

Current Opinion in Ophthalmology

View full text Add to dashboard Cite

Purpose of reviewAge-related macular degeneration (AMD) is one of the leading causes of blindness and can progress to geographic atrophy (GA) in late stages of disease. This review article highlights recent literature which assists in the accurate and timely identification of GA, and monitoring of GA progression. Recent findingsTechnology for diagnosing and monitoring GA has made significant advances in recent years, particularly regarding the use of optical coherence tomography (OCT). Identification of imaging features which may herald the development of GA or its progression is critical. Deep learning applications for OCT in AMD have shown promising growth over the past several years, but more prospective studies are needed to demonstrate generalizability and clinical utility.

show abstract

Section: Artificial Intelligencementioning

confidence: 99%

Section: Artificial Intelligencementioning

confidence: 99%

Identifying geographic atrophy

Clevenger

Rachitskaya

2023

Current Opinion in Ophthalmology

View full text Add to dashboard Cite

show abstract

“…In addition to feature detection and quantification for AMD, DL‐based OCT image analysis has been widely used for AMD classification tasks 16 . Lee et al 17 demonstrated that DL is effective for distinguishing AMD from normal eyes in OCT images.…”

Section: Deep Learning In Octmentioning

confidence: 99%

“…In addition to feature detection and quantification for AMD, DL-based OCT image analysis has been widely used for AMD classification tasks. 16 Lee et al 17 demonstrated that DL is effective for distinguishing AMD from normal eyes in OCT images. Motozawa et al 18 proposed a DL-based model to discriminate wet AMD from dry AMD-a distinction used for precise treatmentusing OCT B-scans.…”

Section: Dl-based Common Eye Diseases Classificationmentioning

confidence: 99%

Deep learning in optical coherence tomography: Where are the gaps?

Ran

Cheung

et al. 2023

Clinical Exper Ophthalmology

View full text Add to dashboard Cite

Optical coherence tomography (OCT) is a non‐invasive optical imaging modality, which provides rapid, high‐resolution and cross‐sectional morphology of macular area and optic nerve head for diagnosis and managing of different eye diseases. However, interpreting OCT images requires experts in both OCT images and eye diseases since many factors such as artefacts and concomitant diseases can affect the accuracy of quantitative measurements made by post‐processing algorithms. Currently, there is a growing interest in applying deep learning (DL) methods to analyse OCT images automatically. This review summarises the trends in DL‐based OCT image analysis in ophthalmology, discusses the current gaps, and provides potential research directions. DL in OCT analysis shows promising performance in several tasks: (1) layers and features segmentation and quantification; (2) disease classification; (3) disease progression and prognosis; and (4) referral triage level prediction. Different studies and trends in the development of DL‐based OCT image analysis are described and the following challenges are identified and described: (1) public OCT data are scarce and scattered; (2) models show performance discrepancies in real‐world settings; (3) models lack of transparency; (4) there is a lack of societal acceptance and regulatory standards; and (5) OCT is still not widely available in underprivileged areas. More work is needed to tackle the challenges and gaps, before DL is further applied in OCT image analysis for clinical use.

show abstract

“…SD-OCT has become a widely used technology among clinicians and researchers, notably in the fields of retina and glaucoma. [1][2][3][4] SD-OCT images are typically read using dedicated viewing software provided by device manufacturers in a portable document format (PDF) or through an output on the OCT machine. This allows for the review of individual patient data in the clinical setting.…”

mentioning

confidence: 99%

OCTess: An Optical Character Recognition Algorithm for Automated Data Extraction of Spectral Domain Optical Coherence Tomography Reports

Balas,

Herman,

Bhambra

et al. 2023

Retina

View full text Add to dashboard Cite

Purpose: Manual extraction of spectral domain optical coherence tomography (SD-OCT) reports is time- and resource-intensive. This study aimed to develop an optical character recognition (OCR) algorithm for automated data extraction from Cirrus SD-OCT macular cube reports. Methods: SD-OCT monocular macular cube reports (n=675) were randomly selected from a single-center database of patients from 2020-2023. Image processing and bounding box operations were performed, and Tesseract (an OCR library) was used to develop the algorithm, OCTess. The algorithm was validated using a separate test dataset. Results: The long short-term memory (LSTM) deep learning version of Tesseract achieved the best performance. After re-verifying all discrepancies between human and algorithmic data extractions, OCTess achieved accuracies of 100.00% and 99.98% in the training (n=125) and testing (n=550) datasets, while the human error rate was 1.11% (98.89% accuracy) and 0.49% (99.51% accuracy) in each, respectively. OCTess extracted data in 3.1 seconds, compared to 94.3 seconds for human evaluators. Conclusion: We developed an OCR and machine learning algorithm that extracts SD-OCT data with near-perfect accuracy, which is more accurate and efficient compared to a human. This algorithm can be used for efficient construction of large-scale SD-OCT datasets for researchers and clinicians.

show abstract

A Systematic Review of Deep Learning Applications for Optical Coherence Tomography in Age-Related Macular Degeneration

Cited by 13 publications

References 41 publications

Identifying geographic atrophy

Identifying geographic atrophy

Deep learning in optical coherence tomography: Where are the gaps?

OCTess: An Optical Character Recognition Algorithm for Automated Data Extraction of Spectral Domain Optical Coherence Tomography Reports

Contact Info

Product

Resources

About