Answers are grounded in this paper and cite their sources.
This reply clarifies the use of foundation models in clinical tools, highlighting the importance of anonymity in data sources.
This reply addresses Chan et al.'s comments on our previous study, clarifying the use of foundation models (e.g., RETFound), commercial data sources/anonymity, and DeLong test results. We highlight that the SDEDS-fine-tuned RETFound outperforms commercial models and acknowledge the need for further testing, while referencing an early benchmark value.
No takes yet. Share an insight, caveat, or question.
Zhang et al. (2025) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: