研究人员推出了PubMed-Ophtha，这是一个包含从科学文献中提取的超过10万对眼科图像-字幕的新数据集。该数据集旨在解决医学领域训练视觉语言模型高质量数据稀缺的问题。提取过程包括对PDF中的图进行详细分解、对成像模态进行标注以及复杂的基于LLM的字幕分割，在检测和提取任务中实现了高精度。 AI
影响 提供了一个大规模、标注过的数据集，以加速眼科领域专业视觉语言模型的发展。
排序理由 该集群描述了为研究目的发布的新数据集和相关模型。
AI 生成摘要 · Google Gemini · 来自 5 个来源。 我们如何撰写摘要 →
arXiv:2605.06173v1 Announce Type: new Abstract: Diabetic Retinopathy (DR) is a leading cause of preventable blindness among working-age adults worldwide, yet most automated screening systems are limited to image-level classification and lack clinically structured reporting. We pr…
Diabetic Retinopathy (DR) is a leading cause of preventable blindness among working-age adults worldwide, yet most automated screening systems are limited to image-level classification and lack clinically structured reporting. We propose Retina-RAG, a low-cost modular framework t…
arXiv:2605.02720v1 Announce Type: new Abstract: Vision-language models hold considerable promise for ophthalmology, but their development depends on large-scale, high-quality image-text datasets that remain scarce. We present PubMed-Ophtha, a hierarchical dataset of 102,023 ophth…
arXiv:2604.18134v2 Announce Type: replace Abstract: Recent advancements in self-supervised learning have led to powerful surgical vision encoders capable of spatiotemporal understanding. However, extending these visual foundations to multi-modal reasoning tasks is severely bottle…
Vision-language models hold considerable promise for ophthalmology, but their development depends on large-scale, high-quality image-text datasets that remain scarce. We present PubMed-Ophtha, a hierarchical dataset of 102,023 ophthalmological image-caption pairs extracted from 1…