English(EN) DALPHIN: Benchmarking Digital Pathology AI Copilots Against Pathologists on an Open Multicentric Dataset

研究发现：AI助手在数字病理学任务上可媲美病理学家

作者 PulseAugur 编辑部 · [2 个来源] · 2026-05-05 09:15

一项名为DALPHIN的新基准已被开发出来，用于评估数字病理学中的AI助手。该基准包含超过1200张图像，并与31位人类病理学家进行了性能比较。GPT-5和Gemini 2.5 Pro等通用模型，以及一个名为PathChat+的专业助手，在各种诊断任务上接受了测试。 AI

影响为评估AI在特定医学领域的诊断能力树立了新标准，可能指导未来的开发和应用。

排序理由该集群描述了一篇介绍数字病理学AI基准数据集和评估方法的新学术论文。

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

报道来源 [2]

arXiv cs.AI TIER_1 English(EN) · Francesco Ciompi · 2026-05-05 09:15

DALPHIN: Benchmarking Digital Pathology AI Copilots Against Pathologists on an Open Multicentric Dataset

Foundation models with visual question answering capabilities for digital pathology are emerging. Such unprecedented technology requires independent benchmarking to assess its potential in assisting pathologists in routine diagnostics. We created DALPHIN, the first multicentric o…
arXiv cs.CV TIER_1 English(EN) · Carlijn Lems, Sander Moonemans, Nat\'alie Klub\'i\v{c}kov\'a, Biagio Brattoli, Taebum Lee, Seokhwi Kim, Veronica Vilaplana, Laura Pons, Sapir Hochman, Mauricio Eduardo Su\'arez-Franck, Pedro Luis Fernandez, Julius Drachneris, Donatas Petroska, Renaldas Au · 2026-05-06 04:00

DALPHIN: Benchmarking Digital Pathology AI Copilots Against Pathologists on an Open Multicentric Dataset

arXiv:2605.03544v1 Announce Type: new Abstract: Foundation models with visual question answering capabilities for digital pathology are emerging. Such unprecedented technology requires independent benchmarking to assess its potential in assisting pathologists in routine diagnosti…