Labeled Ophthalmic Ultrasound Dataset
收藏资源简介:
本数据集名为“Labeled Ophthalmic Ultrasound Dataset”,由华北理工大学电气与控制工程学院等机构创建,包含4858张眼科超声图像及其对应的中文报告。数据集收集了2018年沈阳一家眼科医院2417名患者的超声图像、血流信息和检查报告,为保护隐私,患者信息已去标识化。数据集内容包括15种常见眼内疾病的典型影像发现及其解剖位置描述,每张图像展示了三个特定动脉的三种血流指数,共九个参数值。数据集的创建旨在通过融合计算机视觉和自然语言处理技术,开发医疗AI学习算法,特别适用于跨模态医学数据的学习和报告生成,以辅助眼科疾病的诊断和治疗决策。
This dataset, named "Labeled Ophthalmic Ultrasound Dataset", was developed by institutions including the School of Electrical and Control Engineering, North China University of Science and Technology, and other relevant entities. It contains 4,858 ophthalmic ultrasound images and their corresponding Chinese medical reports. The dataset collects ultrasound images, blood flow data, and examination reports from 2,417 patients at an ophthalmic hospital in Shenyang in 2018, with all patient information de-identified to protect privacy. The dataset includes typical imaging findings and anatomical location descriptions for 15 common intraocular diseases. Each image presents three blood flow indices for three specific arteries, resulting in a total of nine parameter values. The dataset was constructed to enable the development of medical AI learning algorithms by integrating computer vision and natural language processing (NLP) technologies, and is specifically designed for cross-modal medical data learning and report generation to support the diagnosis and treatment decision-making of ophthalmic diseases.

- 1A Labeled Ophthalmic Ultrasound Dataset with Medical Report Generation Based on Cross-modal Deep Learning华北理工大学电气与控制工程学院,沈阳理工大学自动化与电气工程学院,中国医科大学第四附属医院眼科 · 2024年



