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

Ker, 2018, Deep learning applications in medical image analysis, IEEE Access, 6, 9375, 10.1109/ACCESS.2017.2788044 Ting, 2019, Artificial intelligence and deep learning in ophthalmology, Br J Ophthalmol, 103, 167, 10.1136/bjophthalmol-2018-313173 Esteva, 2021, Deep learning-enabled medical computer vision, NPJ Digit Med, 4, 1, 10.1038/s41746-020-00376-2 Ting, 2017, Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes, JAMA, 318, 2211, 10.1001/jama.2017.18152 Gulshan, 2016, Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs, JAMA, 316, 2402, 10.1001/jama.2016.17216 Lee, 2017, Deep-learning based, automated segmentation of macular edema in optical coherence tomography, Biomed Opt Express, 8, 3440, 10.1364/BOE.8.003440 Abràmoff, 2016, Improved automated detection of diabetic retinopathy on a publicly available dataset through integration of deep learning, Invest Ophthalmol Vis Sci, 57, 5200, 10.1167/iovs.16-19964 Li, 2018, Efficacy of a deep learning system for detecting glaucomatous optic neuropathy based on color fundus photographs, Ophthalmology, 125, 1199, 10.1016/j.ophtha.2018.01.023 Burlina, 2017, Automated grading of age-related macular degeneration from color fundus images using deep convolutional neural networks, JAMA Ophthalmol, 135, 1170, 10.1001/jamaophthalmol.2017.3782 Wang, 2020, AAO Taskforce on AI and AAO Medical Information Technology Committee. Big data requirements for artificial intelligence, Curr Opin Ophthalmol, 31, 318, 10.1097/ICU.0000000000000676 Wang, 2019, Deep learning in medicine: promise, progress, and challenges, JAMA Intern Med, 179, 293, 10.1001/jamainternmed.2018.7117 Digital Diagnostics. Indications for use—US. Published May 24, 2021. Available at: https://www.digitaldiagnostics.com/products/eye-disease/indications-for-use-us/; Accessed November 20, 2021. Gabriele, 2011, Optical coherence tomography: history, current status, and laboratory work, Invest Ophthalmol Vis Sci, 52, 2425, 10.1167/iovs.10-6312 Li, 2020, DeepRetina: layer segmentation of retina in OCT images using deep learning, Transl Vis Sci Technol, 9, 61, 10.1167/tvst.9.2.61 Borkovkina, 2020, Real-time retinal layer segmentation of OCT volumes with GPU accelerated inferencing using a compressed, low-latency neural network, Biomed Opt Express, 11, 3968, 10.1364/BOE.395279 Sousa, 2021, Automatic segmentation of retinal layers in OCT images with intermediate age-related macular degeneration using U-Net and DexiNed, PLoS One, 16, 10.1371/journal.pone.0251591 Karimi, 2021, Transfer learning in medical image segmentation: new insights from analysis of the dynamics of model parameters and learned representations, Artif Intell Med, 116, 10.1016/j.artmed.2021.102078 Liu, 2020, Remove appearance shift for ultrasound image segmentation via fast and universal style transfer, 1824 Goodfellow, 2014, Generative adversarial nets., Advances in neural information processing systems, 27, 2672 Romo-Bucheli, 2020, Reducing image variability across OCT devices with unsupervised unpaired learning for improved segmentation of retina, Biomed Opt Express, 11, 346, 10.1364/BOE.379978 Viedma, 2021 Wollmann, 2018, IEEE 15th International Symposium on Biomedical Imaging, 582 Cordts M, Omran M, Ramos S, et al. The Cityscapes dataset for semantic urban scene understanding. Proc Estonian Acad Sci Biol Ecol. Available at: http://openaccess.thecvf.com/content_cvpr_2016/html/Cordts_The_Cityscapes_Dataset_CVPR_2016_paper.html. Accessed November 20, 2021. Ros G, Sellart L, Materzynska J, et al. The SYNTHIA dataset: a large collection of synthetic images for semantic segmentation of urban scenes. Proc Estonian Acad Sci Biol Ecol. Available at: https://www.cv-foundation.org/openaccess/content_cvpr_2016/html/Ros_The_SYNTHIA_Dataset_CVPR_2016_paper.html. Accessed November 20, 2021. Hoffman, 2018, Cycada: cycle-consistent adversarial domain adaptation Chen, 2019, Domain adaptation for semantic segmentation with maximum squares loss, 2090 Yan, 2019, The domain shift problem of medical image segmentation and vendor-adaptation by Unet-GAN, 623 Chiu, 2015, Kernel regression based segmentation of optical coherence tomography images with diabetic macular edema, Biomed Opt Express, 6, 1172, 10.1364/BOE.6.001172 Kim Ronneberger, 2015, U-Net: convolutional Networks for biomedical image segmentation, 234 Ma, 2020, Normalized loss functions for deep learning with noisy labels, 6543 Miller, 2017, Comparison between spectral-domain and swept-source optical coherence tomography angiographic imaging of choroidal neovascularization, Invest Ophthalmol Vis Sci, 58, 1499, 10.1167/iovs.16-20969 Yasaka, 2018, Deep learning and artificial intelligence in radiology: current applications and future directions, PLoS Med, 15, 10.1371/journal.pmed.1002707 Pazos, 2017, Diagnostic accuracy of Spectralis SD OCT automated macular layers segmentation to discriminate normal from early glaucomatous eyes, Ophthalmology, 124, 1218, 10.1016/j.ophtha.2017.03.044 Mehta, 2020, Model-to-data approach for deep learning in optical coherence tomography intraretinal fluid segmentation, JAMA Ophthalmol, 138, 1017, 10.1001/jamaophthalmol.2020.2769 Liefers, 2020, A deep learning model for segmentation of geographic atrophy to study its long-term natural history, Ophthalmology, 127, 1086, 10.1016/j.ophtha.2020.02.009 Van Brummen, 2021, PeriorbitAI: artificial intelligence automation of eyelid and periorbital measurements, Am J Ophthalmol, 230, 285, 10.1016/j.ajo.2021.05.007