Materal-Fetal Ultrasound Video Dataset for End-to-end Intrapartum Biometry and Multi-task Learning

Intrapartum biometry is of vital significance in monitoring labor progress. However, the realization of AI-based end-to-end intrapartum biometry and labor progress assessment requires intrapartum ultrasound video datasets with multi - category annotations, and currently, there is no such public dataset available. To bridge this gap, we have publicly released, for the first time, a multi-center, multi-device, and multi-category labeled intrapartum ultrasound dataset. This dataset comprises 774 videos / 68,106 images, along with corresponding standard plane classification labels, multi-class segmentation labels of pubic symphysis and fetal head, and two ultrasound parameter labels that characterize labor progress. This dataset can facilitate research on multi-task learning methods and the development of end-to-end automated approaches, especially in the automation of obstetric processes and auxiliary decision - making.产时生物测量学（Intrapartum biometry）在产程监测中具有至关重要的临床意义。然而，要实现基于人工智能的端到端产时生物测量与产程评估，亟需具备多类别标注的产时超声视频数据集，但目前尚无此类公开数据集可供使用。为填补这一研究空白，我们首次公开发布了一项多中心、多设备、多类别标注的产时超声数据集。该数据集包含774段视频与68106张图像，并配套有对应的标准平面分类标注、耻骨联合与胎头的多类别分割标注，以及两项用于表征产程进展的超声参数标注。本数据集可推动多任务学习方法的研究与端到端自动化方案的开发，尤其有助于产科流程自动化与辅助决策系统的研发。