Advancing Medical Representation Learning Through High-Quality Data

doi:10.1007/978-3-032-05169-1_3

2026-01-01

PRE

DOI：10.1007/978-3-032-05169-1_3

原文链接

原文求助

摘要

En 中文

尽管医学视觉-语言数据集的规模日益增长，但数据集质量对模型性能的影响仍需进一步探索。我们介绍Open-PMC，一个来自PubMed Central的高质量医学数据集，包含220万图像-文本对，并补充了图像模态标注、子图以及文本内摘要引用。值得注意的是，文本内引用提供了更丰富的医学上下文，超越了通常出现在标题中的摘要信息。通过大量实验，我们在检索和零样本分类任务中，将Open-PMC与更大规模的数据集进行了基准对比。结果显示，数据集质量（而不仅仅是规模）是驱动性能显著提升的关键因素。我们通过深入分析特征表示来补充这一基准。我们的发现强调了数据整理质量在推动多模态医学人工智能发展中的关键作用。我们发布了Open-PMC数据集，以及预训练模型和代码库。

Keyword:

Multimodal Learning

Representation Learning

Contrastive Learning

Image Decomposition

期刊

MEDICAL IMAGE COMPUTING AND COMPUTER ASSISTED INTERVENTION - MICCAI 2025, PT XIII

IF:

论文数:

被引数:

机构

queens university - canada

学者数:

1.8W

论文数: 1.7W

被引数: 29

Vector Institute for Artificial Intelligence

学者数:

217

论文数: 164

被引数: 4

york university - canada

学者数:

8.3K

论文数: 9.0K

被引数: 10

university of toronto

学者数:

14.8W

论文数: 12.0W

被引数: 165

查看更多机构

引用论文

PMC-CLIP: Contrastive Language-Image Pre-training Using Biomedical Documents

Lecture Notes in Computer Science

IF0

2023-10-01

PREAI

Weixiong Lin; Ziheng Zhao; Xiaoman Zhang; Chaoyi Wu; Ya Zhang; Yanfeng Wang; Weidi Xie

End-to-End Object Detection with Transformers 使用Transformers进行端到端对象检测

Lecture Notes in Computer Science

IF0

2020-11-03

PREAI

Nicolas Carion; Francisco Massa; Gabriel Synnaeve; Nicolas Usunier; Alexander Kirillov; Sergey Zagoruyko

Radiology Objects in COntext (ROCO): A Multimodal Image Dataset

Lecture Notes in Computer Science

IF0

2018-10-17

PREAI

Obioma Pelka; Sven Koitka; Johannes Rückert; Felix Nensa; Christoph M. Friedrich

ImageBind One Embedding Space to Bind Them All

2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

IF0

2023-06-01

OAAI

Rohit Girdhar; Alaaeldin El-Nouby; Zhuang Liu; Mannat Singh; Kalyan Vasudev Alwala; Armand Joulin; Ishan Misra

BIOMEDICA: An Open Biomedical Image-Caption Archive, Dataset, and Vision-Language Models Derived from Scientific Literature

2025 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

IF0

2025-06-10

PREAI

Lozano,Alejandro; Sun,Min Woo; Burgess,James; Chen,Liangyu; Nirschl,Jeffrey J.; Gu,Jeffrey; Lopez,Ivan; Aklilu,Josiah; Rau,Anita; Katzer,Austin Wolfgang; Zhang,Yuhui; Chiu,Collin; Wang,Xiaohan; Song,Alfred Seunghoon; Tibshirani,Robert; Yeung-Levy,Serena

DeepOpht: Medical Report Generation for Retinal Images via Deep Models and Visual Explanation

2021 IEEE Winter Conference on Applications of Computer Vision (WACV)

IF0

2021-01-01

OAAI

Jia-Hong Huang; C.-H. Huck Yang; Fangyu Liu; Meng Tian; Yi-Chieh Liu; Ting-Wei Wu; I-Hung Lin; Kang Wang; Hiromasa Morikawa; Hernghua Chang; Jesper Tegner; Marcel Worring

DocFigure: A Dataset for Scientific Document Figure Classification

2019 International Conference on Document Analysis and Recognition Workshops (ICDARW)

IF0

2019-09-01

PREAI

K. V. Jobin; Ajoy Mondal; C. V. Jawahar

MedICaT: A Dataset of Medical Images, Captions, and Textual References

Findings of the Association for Computational Linguistics: EMNLP 2020

IF0

2020-01-01

OAAI

Sanjay Subramanian; Lucy Lu Wang; Ben Bogin; Sachin Mehta; Madeleine van Zuylen; Sravanthi Parasa; Sameer Singh; Matt Gardner; Hannaneh Hajishirzi