Training Deep Learning Models to Work on Multiple Devices by Cross-Domain Learning with No Additional Annotations

Wu, Yue; Olvera-Barrios, Abraham; Yanagihara, Ryan T.; Kung, Timothy-Paul H.; Lu, Randy; Leung, Irene; Mishra, Amit V.; Nussinovitch, Hanan; Grimaldi, Gabriela; Blazes, Marian; Lee, Cecilia S.; Egan, Catherine; Tufail, Adnan; Lee, Aaron

doi:10.1016/j.ophtha.2022.09.014

Cited by 8 publications

(6 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The effect of different domains of images on AI performance may be more pronounced for segmentation of optical coherence tomography (OCT) images. There has been an attempt to develop AI models that can perform well on OCT images from different domains of different manufacturers [ 55 ].…”

Section: Resultsmentioning

confidence: 99%

Artificial Intelligence for Diabetic Retinopathy Screening Using Color Retinal Photographs: From Development to Deployment

Grzybowski

Singhanetr²,

Nanegrungsunk

et al. 2023

Ophthalmol Ther

View full text Add to dashboard Cite

Diabetic retinopathy (DR), a leading cause of preventable blindness, is expected to remain a growing health burden worldwide. Screening to detect early sight-threatening lesions of DR can reduce the burden of vision loss; nevertheless, the process requires intensive manual labor and extensive resources to accommodate the increasing number of patients with diabetes. Artificial intelligence (AI) has been shown to be an effective tool which can potentially lower the burden of screening DR and vision loss. In this article, we review the use of AI for DR screening on color retinal photographs in different phases of application, ranging from development to deployment. Early studies of machine learning (ML)-based algorithms using feature extraction to detect DR achieved a high sensitivity but relatively lower specificity. Robust sensitivity and specificity were achieved with the application of deep learning (DL), although ML is still used in some tasks. Public datasets were utilized in retrospective validations of the developmental phases in most algorithms, which require a large number of photographs. Large prospective clinical validation studies led to the approval of DL for autonomous screening of DR although the semi-autonomous approach may be preferable in some real-world settings. There have been few reports on real-world implementations of DL for DR screening. It is possible that AI may improve some real-world indicators for eye care in DR, such as increased screening uptake and referral adherence, but this has not been proven. The challenges in deployment may include workflow issues, such as mydriasis to lower ungradable cases; technical issues, such as integration into electronic health record systems and integration into existing camera systems; ethical issues, such as data privacy and security; acceptance of personnel and patients; and health-economic issues, such as the need to conduct health economic evaluations of using AI in the context of the country. The

show abstract

Section: Resultsmentioning

confidence: 99%

Artificial Intelligence for Diabetic Retinopathy Screening Using Color Retinal Photographs: From Development to Deployment

Grzybowski

Singhanetr²,

Nanegrungsunk

et al. 2023

Ophthalmol Ther

View full text Add to dashboard Cite

show abstract

“…This is partly due to their comparable light source characteristics with half-bandwidth (53.7 nm vs. 50 nm) and wavelength (860 nm vs. 840 nm) and the lack of B-scan averaging. In general, to ensure a wider generalizability, domain shift adaptation approaches [65][66][67] should be pursued. Another limitation is that we restricted our focus to datasets of AMD patients that have been determined as such from the EHR.…”

Section: Discussionmentioning

confidence: 99%

Automated deep learning-based AMD detection and staging in real-world OCT datasets (PINNACLE study report 5)

Leingang,

Riedl,

Mai

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Real-world retinal optical coherence tomography (OCT) scans are available in abundance in primary and secondary eye care centres. They contain a wealth of information to be analyzed in retrospective studies. The associated electronic health records alone are often not enough to generate a high-quality dataset for clinical, statistical, and machine learning analysis. We have developed a deep learning-based age-related macular degeneration (AMD) stage classifier, to efficiently identify the first onset of early/intermediate (iAMD), atrophic (GA), and neovascular (nAMD) stage of AMD in retrospective data. We trained a two-stage convolutional neural network to classify macula-centered 3D volumes from Topcon OCT images into 4 classes: Normal, iAMD, GA and nAMD. In the first stage, a 2D ResNet50 is trained to identify the disease categories on the individual OCT B-scans while in the second stage, four smaller models (ResNets) use the concatenated B-scan-wise output from the first stage to classify the entire OCT volume. Classification uncertainty estimates are generated with Monte-Carlo dropout at inference time. The model was trained on a real-world OCT dataset, 3765 scans of 1849 eyes, and extensively evaluated, where it reached an average ROC-AUC of 0.94 in a real-world test set.

show abstract

“…Furthermore, a recent study used a generative adversarial network called GANSeg to develop an algorithm for segmenting intraretinal fluid and retinal layers in normal and pathological macular OCT images. 35 Remarkably, the model's adaptability allowed it to generalize from training on one device (Heidelberg Spectralis) to other devices (Topcon 1000, Maestro2, Zeiss Plex Elite 9000), all without the need for labeled data from those devices.…”

Section: Sharing Datasets Securelymentioning

confidence: 99%

A Clinician's Guide to Sharing Data for AI in Ophthalmology

Gim,

Wu,

Blazes

et al. 2024

Invest. Ophthalmol. Vis. Sci.

View full text Add to dashboard Cite

Training Deep Learning Models to Work on Multiple Devices by Cross-Domain Learning with No Additional Annotations

Cited by 8 publications

References 32 publications

Artificial Intelligence for Diabetic Retinopathy Screening Using Color Retinal Photographs: From Development to Deployment

Artificial Intelligence for Diabetic Retinopathy Screening Using Color Retinal Photographs: From Development to Deployment

Automated deep learning-based AMD detection and staging in real-world OCT datasets (PINNACLE study report 5)

A Clinician's Guide to Sharing Data for AI in Ophthalmology

Contact Info

Product

Resources

About