Isfahan University of Medical Sciences

Science Communicator Platform

Stay connected! Follow us on X network (Twitter):
Share this content! On (X network) By
Addressing Inter-Device Variations in Optical Coherence Tomography Angiography: Will Image-To-Image Translation Systems Help? Publisher



Nouri H1, 2 ; Nasri R3 ; Abtahi SH1, 4
Authors
Show Affiliations
Authors Affiliations
  1. 1. Ophthalmic Research Center, Research Institute for Ophthalmology and Vision Science, Shahid Beheshti University of Medical Sciences, Tehran, Iran
  2. 2. School of Medicine, Isfahan University of Medical Sciences, Isfahan, Iran
  3. 3. School of Engineering, University of Isfahan, Isfahan, Iran
  4. 4. Department of Ophthalmology, Torfe Medical Center, Shahid Beheshti University of Medical Sciences, Tehran, Iran

Source: International Journal of Retina and Vitreous Published:2023


Abstract

Background: Optical coherence tomography angiography (OCTA) is an innovative technology providing visual and quantitative data on retinal microvasculature in a non-invasive manner. Main body: Due to variations in the technical specifications of different OCTA devices, there are significant inter-device differences in OCTA data, which can limit their comparability and generalizability. These variations can also result in a domain shift problem that may interfere with applicability of machine learning models on data obtained from different OCTA machines. One possible approach to address this issue may be unsupervised deep image-to-image translation leveraging systems such as Cycle-Consistent Generative Adversarial Networks (Cycle-GANs) and Denoising Diffusion Probabilistic Models (DDPMs). Through training on unpaired images from different device domains, Cycle-GANs and DDPMs may enable cross-domain translation of images. They have been successfully applied in various medical imaging tasks, including segmentation, denoising, and cross-modality image-to-image translation. In this commentary, we briefly describe how Cycle-GANs and DDPMs operate, and review the recent experiments with these models on medical and ocular imaging data. We then discuss the benefits of applying such techniques for inter-device translation of OCTA data and the potential challenges ahead. Conclusion: Retinal imaging technologies and deep learning-based domain adaptation techniques are rapidly evolving. We suggest exploring the potential of image-to-image translation methods in improving the comparability of OCTA data from different centers or devices. This may facilitate more efficient analysis of heterogeneous data and broader applicability of machine learning models trained on limited datasets in this field. © 2023, Brazilian Retina and Vitreous Society.
Related Docs
View other Related Docs
1. Optical Coherence Tomography Angiography in Diabetic Retinopathy: A Major Review, Survey of Ophthalmology (2024)
2. A Dual-Discriminator Fourier Acquisitive Gan for Generating Retinal Optical Coherence Tomography Images, IEEE Transactions on Instrumentation and Measurement (2022)
3. Retinal Optical Coherence Tomography Image Analysis by a Restricted Boltzmann Machine, Biomedical Optics Express (2022)
4. Retinal Optical Coherence Tomography Image Classification With Label Smoothing Generative Adversarial Network, Neurocomputing (2020)
5. Intra-Retinal Layer Segmentation of Optical Coherence Tomography Using 3D Fully Convolutional Networks, Proceedings - International Conference on Image Processing, ICIP (2018)
6. Automatic Diagnosis of Abnormal Macula in Retinal Optical Coherence Tomography Images Using Wavelet-Based Convolutional Neural Network Features and Random Forests Classifier, Journal of Biomedical Optics (2018)
7. Discrimination of Multiple Sclerosis Using Scanning Laser Ophthalmoscopy Images With Autoencoder-Based Feature Extraction, Multiple Sclerosis and Related Disorders (2024)
8. A New Convolutional Neural Network Based on Combination of Circlets and Wavelets for Macular Oct Classification, Scientific Reports (2023)
Experts (# of related papers)
View all Related Experts
Hossein Rabbani (18)
Raheleh Kafieh (12)
Other Related Docs
9. A New Computer-Aided Diagnosis Tool Based on Deep Learning Methods for Automatic Detection of Retinal Disorders From Oct Images, International Ophthalmology (2024)
10. Three-Dimensional Optical Coherence Tomography Image Denoising Through Multi-Input Fully-Convolutional Networks, Computers in Biology and Medicine (2019)
11. Automatic Classification of Retinal Optical Coherence Tomography Images With Layer Guided Convolutional Neural Network, IEEE Signal Processing Letters (2019)
12. Dual-Tree Complex Wavelet Input Transform for Cyst Segmentation in Oct Images Based on a Deep Learning Framework, Photonics (2023)
13. Wavelet Scattering Transform Application in Classification of Retinal Abnormalities Using Oct Images, Scientific Reports (2023)
14. Intra-Retinal Layer Segmentation of 3D Optical Coherence Tomography Using Coarse Grained Diffusion Map, Medical Image Analysis (2013)
15. Slo-Net: Enhancing Multiple Sclerosis Diagnosis Beyond Optical Coherence Tomography Using Infrared Reflectance Scanning Laser Ophthalmoscopy Images, Translational Vision Science and Technology (2024)
16. Enhanced Atrial Fibrillation (Af) Detection Via Data Augmentation With Diffusion Model, 2023 13th International Conference on Computer and Knowledge Engineering, ICCKE 2023 (2023)
17. Synthetic Oct Data in Challenging Conditions: Three-Dimensional Oct and Presence of Abnormalities, Medical and Biological Engineering and Computing (2022)
18. Intra-Retinal Layer Segmentation of Optical Coherence Tomography Using Diffusion Map, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings (2013)
19. A Lightweight Mimic Convolutional Auto-Encoder for Denoising Retinal Optical Coherence Tomography Images, IEEE Transactions on Instrumentation and Measurement (2021)
20. Automatic Classification of Macular Diseases From Oct Images Using Cnn Guided With Edge Convolutional Layer, Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society, EMBS (2022)
21. Loss-Modified Transformer-Based U-Net for Accurate Segmentation of Fluids in Optical Coherence Tomography Images of Retinal Diseases, Journal of Medical Signals and Sensors (2023)
22. Attention to Lesion: Lesion-Aware Convolutional Neural Network for Retinal Optical Coherence Tomography Image Classification, IEEE Transactions on Medical Imaging (2019)
23. Synthetic Oct Data Generation to Enhance the Performance of Diagnostic Models for Neurodegenerative Diseases, Translational Vision Science and Technology (2022)
24. Introduction to Optical Coherence Tomography, Atlas of Ocular Optical Coherence Tomograph, Second Edition (2023)
25. Application of Deep Dictionary Learning and Predefined Filters for Classification of Retinal Optical Coherence Tomography Images, IEEE Access (2025)