RVD: A Handheld Device-Based Fundus Video Dataset for Retinal Vessel Segmentation

We introduce the first video-based retinal vessel dataset (RVD), a collection of 635 smartphone-based videos with detailed vessel annotation. All captured videos have a frame rate of 25 frames per second, with the duration varying between 2 to 30 seconds. The total number of frames in our dataset is over 130,000. These videos are recorded from four clinics, including patients from 50 to 75 years old. More specifically, 264 males and 151 females are included in the collection process. The annotations provided in our dataset span two dimensions: spatial and temporal. In the spatial dimension, we offer three distinct levels of annotations: binary vessel masks, general vein-artery masks, and fine-grained vein-artery masks. Each kind of annotation is tailored to specific clinical purposes. In the temporal dimension, we focus on the optic disk regions of videos where the retinal vessel fluctuation normally occurs. We select and annotate frames with the maximal and minimal pulse widths as well as label the existence of spontaneous retinal venous pulsations (SVP). More detailed information can also be found on our website: https://uq-cvlab.github.io/Retinal-Video-Dataset/ If you find our RVD dataset is useful in your research, please consider cite: @article{MD2023RVD, title={RVD: A Handheld Device-Based Fundus Video Dataset for Retinal Vessel Segmentation}, author={MD WAHIDUZZAMAN KHAN, Hongwei Sheng, Hu Zhang, Heming Du, Sen Wang, Minas Theodore Coroneo, Farshid Hajati, Sahar Shariflou, Michael Kalloniatis, Jack Phu, Ashish Agar, Zi Huang, Mojtaba Golzan, Xin Yu}, journal={arXiv preprint arXiv:2307.06577}, year={2023} }我们首次提出了基于视频的视网膜血管数据集（Retinal Vessel Dataset, RVD），该数据集收录了635条由智能手机采集的视网膜血管视频，并附带详尽的血管标注信息。所有采集得到的视频帧率均为25帧/秒，时长介于2至30秒之间，本数据集总帧数超过13万。这些视频采集自四家临床机构，受试者年龄跨度为50至75岁，其中共纳入264名男性与151名女性受试者。本数据集提供的标注包含两个维度：空间维度与时间维度。在空间维度上，我们提供三类不同层级的标注：二值化血管掩码、动静脉通用掩码以及细粒度动静脉掩码，每一类标注均针对特定的临床应用场景定制。在时间维度上，我们聚焦于视频中视网膜血管波动常出现的视盘区域，选取并标注了具有最大和最小脉宽的帧，并对视网膜自发性静脉搏动（Spontaneous Retinal Venous Pulsations, SVP）的存在与否进行标注。更多详细信息可访问我们的官方网站：https://uq-cvlab.github.io/Retinal-Video-Dataset/。若您的研究中使用本RVD数据集，请引用如下文献： @article{MD2023RVD, title={RVD: A Handheld Device-Based Fundus Video Dataset for Retinal Vessel Segmentation}, author={MD WAHIDUZZAMAN KHAN, Hongwei Sheng, Hu Zhang, Heming Du, Sen Wang, Minas Theodore Coroneo, Farshid Hajati, Sahar Shariflou, Michael Kalloniatis, Jack Phu, Ashish Agar, Zi Huang, Mojtaba Golzan, Xin Yu}, journal={arXiv preprint arXiv:2307.06577}, year={2023} }