February 12, 2024npj Digital MedicineOpen Access

Translating color fundus photography to indocyanine green angiography using deep-learning for age-related macular degeneration screening

View Full Paper

Ask AI

Bookmark

Authors

RCRuoyu ChenHong Kong Polytechnic University WZWeiyi ZhangHong Kong Polytechnic University SFSong FanAnhui Medical University

Discussion

Member takes

Overview

External validation demonstrates enhanced age-related macular degeneration classification in retinal imaging, indicating viable non-invasive screening utility.

Key Points

Classification accuracy increased to an area under the ROC curve of 0.97 on 13,887 external images, demonstrating strong detection of age-related macular degeneration.
Generative adversarial networks translated non-invasive color fundus photography into synthetic indocyanine green angiography, trained across 99,002 paired clinical images.
Cross-modal translation supports scalable screening for age-related macular degeneration, but prospective real-world validation is warranted before routine clinical adoption.

Cite This Study

Chen et al. (2024) studied this question.

synapsesocial.com/papers/68e796dbb6db643587707b28 https://doi.org/10.1038/s41746-024-01018-7

View Full Paper

Ask AI

Bookmark

February 12, 2024npj Digital MedicineOpen Access

Translating color fundus photography to indocyanine green angiography using deep-learning for age-related macular degeneration screening

View Full Paper

Ask AI

Bookmark

Authors

RCRuoyu ChenHong Kong Polytechnic University WZWeiyi ZhangHong Kong Polytechnic University SFSong FanAnhui Medical University

Discussion

Member takes

Overview

External validation demonstrates enhanced age-related macular degeneration classification in retinal imaging, indicating viable non-invasive screening utility.

Key Points

Classification accuracy increased to an area under the ROC curve of 0.97 on 13,887 external images, demonstrating strong detection of age-related macular degeneration.
Generative adversarial networks translated non-invasive color fundus photography into synthetic indocyanine green angiography, trained across 99,002 paired clinical images.
Cross-modal translation supports scalable screening for age-related macular degeneration, but prospective real-world validation is warranted before routine clinical adoption.

Cite This Study

Chen et al. (2024) studied this question.

synapsesocial.com/papers/68e796dbb6db643587707b28 https://doi.org/10.1038/s41746-024-01018-7

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark