AngioReport:用于眼底血管造影报告生成的数据集与基线方法
该回顾性研究纳入2019年在泰国Rajavithi医院接受FFA或ICGA的1691例患者(3179只眼),标注55 361张图像,构建了包含24种诊断的眼底血管造影数据集,并开发了基于ResNet101的分类方法和基于Bootstrapping Language-Image Pre-training框架的语言生成方法两种基线方法,使用F1分数和BERTScore评估模型性能。
要点
- 数据集包含来自1691例患者(3179只眼)的55 361张去标识化眼底血管造影图像,标注了异常荧光的类型、位置、形状、大小和模式。
- 数据集涵盖24种诊断,其中黄斑新生血管(32.5%)最常见,其次为无明显异常(21.8%)和干性年龄相关性黄斑变性(10.2%)。
- 基于分类的方法平均得分为7.966,基于语言生成的方法平均得分为7.947。
核心结论
- 研究呈现了迄今为止最大的标注眼底血管造影数据集,以及两种有效的自动报告生成基线方法,为推进人工智能在眼科的应用提供了宝贵基础。
研究设计与样本
- 回顾性研究,纳入2019年1月1日至2019年12月31日在泰国Rajavithi医院接受FFA或ICGA的年龄≥18岁患者,共1691例患者(3179只眼)的55 361张去标识化图像,由视网膜专家标注。
主要发现
- 数据集包括24种诊断状况,黄斑新生血管(32.5%)最常见,其次为无明显异常(21.8%)和干性年龄相关性黄斑变性(10.2%)。
- 大多数眼(81.8%)同时接受了FFA和ICGA检查。
- 高荧光见于75.6%的病例,主要由于渗漏,低荧光见于28.1%的病例。
- 基于分类的方法平均得分为7.966,在识别脉络膜新生血管、高荧光和低荧光区域方面表现更优。
- 基于语言生成的方法平均得分为7.947,在 Impression 识别和高荧光识别方面表现突出。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
PURPOSE: To develop an annotated fundus angiographic dataset, including fundus fluorescein angiography (FFA) and indocyanine green angiography (ICGA), and establish baseline methods for automatic report generation. METHODS: This retrospective study reviewed patients aged ≥18 years who underwent FFA or ICGA at Rajavithi Hospital, Thailand, between 1 January and 31 December 2019. A total of 55 361 de-identified images from 1691 patients (3179 eyes) were annotated by retinal specialists with detailed descriptions of the type, location, shape, size and pattern of abnormal fluorescence. Two baseline methods were developed: (1) a classification-based approach using ResNet101 with class-specific residual attention for multi-label lesion recognition and (2) a language-generation approach using the Bootstrapping Language-Image Pre-training framework, fine-tuned on angiographic images and structured reports. Model performances were evaluated using F1 score and BERTScore. RESULTS: The dataset includes 24 diagnostic conditions, with macular neovascularisation (32.5%) being the most prevalent, followed by unremarkable findings (21.8%) and dry age-related macular degeneration (10.2%). Most eyes (81.8%) underwent both FFA and ICGA. Hyperfluorescence was observed in 75.6% of cases, predominantly due to leakage, while hypofluorescence was present in 28.1%. The classification-based method achieved an average score of 7.966, demonstrating superior performance in recognising choroidal neovascularisation, hyperfluorescent and hypofluorescent areas. The language-generation method achieved a comparable average score of 7.947, excelling in impression recognition and the hyperfluorescence identification. CONCLUSION: We present the largest annotated fundus angiographic dataset to date, along with two effective baseline methods for automatic report generation, offering a valuable foundation for advancing artificial intelligence applications in ophthalmology.
引用
- Xu P, Chotcomwongse P, Zhang W, et al. AngioReport: dataset and baseline methods for fundus angiography report generation. Br J Ophthalmol. 2025. PMID: 40610046. doi:10.1136/bjo-2024-327006
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。