, fundus

Kelvin Zhenghao Li1,2,3, Tuyet Thao Nguyen1,4, Heather E Moss1,5

  • 1Department of Ophthalmology, Stanford University, Palo Alto, CA, United States.

Frontiers in digital health
|September 10, 2025
PubMed
概括

视觉语言模型 (VLMs) 可以在 fundus 照片中比偶然更好地识别光盘胀,但性能因模型而异. 快速复杂性并没有持续提高诊断准确性,这表明可能需要专门的VLM.

相关概念视频