Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
Review
. 2024 Sep 18;14(1):21829.
doi: 10.1038/s41598-024-72752-x.

A comparative evaluation of deep learning approaches for ophthalmology

Affiliations
Review

A comparative evaluation of deep learning approaches for ophthalmology

Glenn Linde et al. Sci Rep. .

Abstract

There is a growing number of publicly available ophthalmic imaging datasets and open-source code for Machine Learning algorithms. This allows ophthalmic researchers and practitioners to independently perform various deep-learning tasks. With the advancement in artificial intelligence (AI) and in the field of imaging, the choice of the most appropriate AI architecture for different tasks will vary greatly. The best-performing AI-dataset combination will depend on the specific problem that needs to be solved and the type of data available. The article discusses different machine learning models and deep learning architectures currently used for various ophthalmic imaging modalities and for different machine learning tasks. It also proposes the most appropriate models based on accuracy and other important factors such as training time, the ability to deploy the model on clinical devices/smartphones, heatmaps that enhance the self-explanatory nature of classification decisions, and the ability to train/adapt on small image datasets to determine if further data collection is worthwhile. The article extensively reviews the existing state-of-the-art AI methods focused on useful machine-learning applications for ophthalmology. It estimates their performance and viability through training and evaluating architectures with different public and private image datasets of different modalities, such as full-color retinal images, OCT images, and 3D OCT scans. The article is expected to benefit the readers by enriching their knowledge of artificial intelligence applied to ophthalmology.

Keywords: Artificial intelligence; Deep learning; Diabetic retinopathy; Fundus imaging; Ophthalmoscopy.

PubMed Disclaimer

Conflict of interest statement

The authors declare NO competing interests.

Figures

Fig. 1
Fig. 1
Accuracy of each architecture for each dataset for multiclass problem (> 90% dark, > 80% medium otherwise light).
Fig. 2
Fig. 2
Original ACRIMA glaucoma image and the heatmap generated from EfficientNet.
Fig. 3
Fig. 3
Heatmap generated for InceptionV3-trained models using guided backpropagation.
Fig. 4
Fig. 4
Grading classifier accuracy of each CNN architecture on different datasets ( > 90% dark, > 80% medium otherwise light).
Fig. 5
Fig. 5
Heatgrid showing the accuracy of each CNN architecture for different OCT datasets (> 90% dark, > 80% medium otherwise light).
Fig. 6
Fig. 6
3D OCT volume.
Fig. 7
Fig. 7
Accuracy of different architectures on EIA2020 dataset (> 90% dark, > 80% medium otherwise light).
Fig. 8
Fig. 8
A single slice from the 3D OCT volume with the corresponding slices displayed in 3D.

References

    1. Adam, B., & Kaveh, M. The rise of artificial intelligence in healthcare applications. In: Artificial Intelligence in healthcare 25–60 (Elsevier, 2020).
    1. Saria, S. Not all ai is created equal: Strategies for safe and effective adoption. NEJM Catal. Innov. Care Deliv.3(2), https://catalyst.nejm.org/doi/full/10.1056/CAT.22.0075 (2022). - DOI
    1. Decide-ai: New reporting guidelines to bridge the development-to-implementation gap in clinical artificial intelligence. Nat. Med.27(2), 186–187 (2021). - PubMed
    1. Liu, X. et al. Reporting guidelines for clinical trial reports for interventions involving artificial intelligence: The consort-ai extension. Lancet Digit. Health2(10), e537–e548 (2020). - PMC - PubMed
    1. Food and Drug Administration and others, Proposed regulatory framework for modifications to artificial intelligence/machine learning (ai/ml)-based software as a medical device (samd) (2019).

MeSH terms

LinkOut - more resources