Methodological Challenges of Deep Learning in Optical Coherence Tomography for Retinal Diseases: A Review

Yanagihara, Ryan T.; Lee, Cecilia S.; Ting, Daniel Shu Wei; Lee, Aaron

doi:10.1167/tvst.9.2.11

Cited by 76 publications

(43 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A recent study emphasized the large amount of OCT data required to train a DL model but did not investigate the feasibility of FSL in OCT imaging [ 40 ]. To address the limitations of traditional DL models, we first performed an experiment to explore the feasibility of FSL in the OCT imaging domain.…”

Section: Discussionmentioning

confidence: 99%

“…The low resolution may affect the classification results of the DL model [ 53 ]. Second, this study does not include a volumetric analysis for OCT. A recent study demonstrated that there is a lack of standardization in the OCT acquisition and analysis protocol [ 40 ]. Future studies should consider the variations in OCT images and devices.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Feasibility study to improve deep learning in OCT diagnosis of rare retinal diseases with few-shot classification

Yoo

Choi

Kim

2021

Med Biol Eng Comput

View full text Add to dashboard Cite

Deep learning (DL) has been successfully applied to the diagnosis of ophthalmic diseases. However, rare diseases are commonly neglected due to insufficient data. Here, we demonstrate that few-shot learning (FSL) using a generative adversarial network (GAN) can improve the applicability of DL in the optical coherence tomography (OCT) diagnosis of rare diseases. Four major classes with a large number of datasets and five rare disease classes with a few-shot dataset are included in this study. Before training the classifier, we constructed GAN models to generate pathological OCT images of each rare disease from normal OCT images. The Inception-v3 architecture was trained using an augmented training dataset, and the final model was validated using an independent test dataset. The synthetic images helped in the extraction of the characteristic features of each rare disease. The proposed DL model demonstrated a significant improvement in the accuracy of the OCT diagnosis of rare retinal diseases and outperformed the traditional DL models, Siamese network, and prototypical network. By increasing the accuracy of diagnosing rare retinal diseases through FSL, clinicians can avoid neglecting rare diseases with DL assistance, thereby reducing diagnosis delay and patient burden.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Feasibility study to improve deep learning in OCT diagnosis of rare retinal diseases with few-shot classification

Yoo

Choi

Kim

2021

Med Biol Eng Comput

View full text Add to dashboard Cite

show abstract

“…Lack of large image datasets from multiple OCT devices, non-standardized imaging or postprocessing protocols between devices, limited graphics processing unit capabilities for exploiting 3D features, and inconsistency in the reporting metrics are major hurdles in enabling AI for OCT analyses. 320,321 Furthermore, machine learning and AI for health must be reproducible to ensure reliable clinical use. Recent evaluations found that machine learning for health fared poorly compared with other areas regarding reproducibility metrics, such as dataset and code accessibility.…”

Section: Oct and Deep Learning Neural Network And Artificial Intelligencementioning

confidence: 99%

Enhanced medical diagnosis for dOCTors: a perspective of optical coherence tomography

et al. 2021

View full text Add to dashboard Cite

Significance: After three decades, more than 75,000 publications, tens of companies being involved in its commercialization, and a global market perspective of about USD 1.5 billion in 2023, optical coherence tomography (OCT) has become one of the fastest successfully translated imaging techniques with substantial clinical and economic impacts and acceptance.Aim: Our perspective focuses on disruptive forward-looking innovations and key technologies to further boost OCT performance and therefore enable significantly enhanced medical diagnosis.Approach: A comprehensive review of state-of-the-art accomplishments in OCT has been performed. Results:The most disruptive future OCT innovations include imaging resolution and speed (single-beam raster scanning versus parallelization) improvement, new implementations for dual modality or even multimodality systems, and using endogenous or exogenous contrast in these hybrid OCT systems targeting molecular and metabolic imaging. Aside from OCT angiography, no other functional or contrast enhancing OCT extension has accomplished comparable clinical and commercial impacts. Some more recently developed extensions, e.g., optical coherence elastography, dynamic contrast OCT, optoretinography, and artificial intelligence enhanced OCT are also considered with high potential for the future. In addition, OCT miniaturization for portable, compact, handheld, and/or cost-effective capsule-based OCT applications, home-OCT, and self-OCT systems based on micro-optic assemblies or photonic integrated circuits will revolutionize new applications and availability in the near future. Finally, clinical translation of OCT including medical device regulatory challenges will continue to be absolutely essential.Conclusions: With its exquisite non-invasive, micrometer resolution depth sectioning capability, OCT has especially revolutionized ophthalmic diagnosis and hence is the fastest adopted imaging technology in the history of ophthalmology. Nonetheless, OCT has not been completely exploited and has substantial growth potential-in academics as well as in industry. This applies not only to the ophthalmic application field, but also especially to the original motivation of OCT to enable optical biopsy, i.e., the in situ imaging of tissue microstructure with a resolution approaching that of histology but without the need for tissue excision.

show abstract

“…The application of deep learning methods to OCT medical images is a recent trend and only few examples of application are available. Ophthalmology being the oldest context of application of OCT, most examples are found in this area, and some others in cardiology and breast cancer [42][43][44][45]. In gastroenterology of the lower track (colon), only one recent work has been identified [46].…”

Section: Introductionmentioning

confidence: 99%

Characterization of Optical Coherence Tomography Images for Colon Lesion Differentiation under Deep Learning

et al. 2021

View full text Add to dashboard Cite

(1) Background: Clinicians demand new tools for early diagnosis and improved detection of colon lesions that are vital for patient prognosis. Optical coherence tomography (OCT) allows microscopical inspection of tissue and might serve as an optical biopsy method that could lead to in-situ diagnosis and treatment decisions; (2) Methods: A database of murine (rat) healthy, hyperplastic and neoplastic colonic samples with more than 94,000 images was acquired. A methodology that includes a data augmentation processing strategy and a deep learning model for automatic classification (benign vs. malignant) of OCT images is presented and validated over this dataset. Comparative evaluation is performed both over individual B-scan images and C-scan volumes; (3) Results: A model was trained and evaluated with the proposed methodology using six different data splits to present statistically significant results. Considering this, 0.9695 (±0.0141) sensitivity and 0.8094 (±0.1524) specificity were obtained when diagnosis was performed over B-scan images. On the other hand, 0.9821 (±0.0197) sensitivity and 0.7865 (±0.205) specificity were achieved when diagnosis was made considering all the images in the whole C-scan volume; (4) Conclusions: The proposed methodology based on deep learning showed great potential for the automatic characterization of colon polyps and future development of the optical biopsy paradigm.

show abstract

Methodological Challenges of Deep Learning in Optical Coherence Tomography for Retinal Diseases: A Review

Cited by 76 publications

References 63 publications

Feasibility study to improve deep learning in OCT diagnosis of rare retinal diseases with few-shot classification

Feasibility study to improve deep learning in OCT diagnosis of rare retinal diseases with few-shot classification

Enhanced medical diagnosis for dOCTors: a perspective of optical coherence tomography

Characterization of Optical Coherence Tomography Images for Colon Lesion Differentiation under Deep Learning

Contact Info

Product

Resources

About