Ophthalmology
PulseAugur coverage of Ophthalmology — every cluster mentioning Ophthalmology across labs, papers, and developer communities, ranked by signal.
1 天有情绪数据
-
新基准增强眼科视觉问答的临床可解释性
研究人员开发了FundusGround，一个用于眼科视觉问答（VQA）的新基准，该基准强调临床可解释性和证据定位。该基准包含超过10,000张眼底图像，并使用ETDRS网格对病灶进行精细标注和空间定位，以确保临床相关性。该数据集支持生成超过72,000个问题，实验表明，纳入病灶级别的证据可以提高医学VQA系统的模型准确性和透明度。
-
Survey reviews representation learning for retinal OCT image analysis
This paper surveys representation learning methods applied to Optical Coherence Tomography (OCT) images in ophthalmology. It reviews techniques from early deep learning to current foundation models and vision-language s…
-
New method improves medical segmentation model calibration using ordinal learning
Researchers have developed a new method to improve the calibration of medical image segmentation models, particularly when multiple expert annotations show significant disagreement. The approach reformulates multi-rater…