Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford, UK.
Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford, Oxford, UK.
Ultrasound Med Biol. 2024 Jul;50(7):985-993. doi: 10.1016/j.ultrasmedbio.2024.03.006. Epub 2024 May 1.
We present a statistical characterisation of fetal anatomies in obstetric ultrasound video sweeps where the transducer follows a fixed trajectory on the maternal abdomen.
Large-scale, frame-level manual annotations of fetal anatomies (head, spine, abdomen, pelvis, femur) were used to compute common frame-level anatomy detection patterns expected for breech, cephalic, and transverse fetal presentations, with respect to video sweep paths. The patterns, termed statistical heatmaps, quantify the expected anatomies seen in a simple obstetric ultrasound video sweep protocol. In this study, a total of 760 unique manual annotations from 365 unique pregnancies were used.
We provide a qualitative interpretation of the heatmaps assessing the transducer sweep paths with respect to different fetal presentations and suggest ways in which the heatmaps can be applied in computational research (e.g., as a machine learning prior).
The heatmap parameters are freely available to other researchers (https://github.com/agleed/calopus_statistical_heatmaps).
我们提出了一种针对产科超声视频扫描中胎儿解剖结构的统计特征描述，其中换能器沿着母体腹部的固定轨迹移动。
大规模的、基于帧的手动注释胎儿解剖结构（头、脊柱、腹部、骨盆、股骨）用于计算与视频扫描路径相关的臀位、头位和横位胎儿表现的常见帧级解剖结构检测模式。这些模式被称为统计热图，量化了在简单的产科超声视频扫描方案中预期看到的解剖结构。在这项研究中，总共使用了 760 个来自 365 个独特妊娠的独特手动注释。
我们对热图进行了定性解释，评估了换能器扫描路径与不同胎儿表现的关系，并提出了热图在计算研究中的应用方法（例如，作为机器学习先验）。
热图参数可供其他研究人员自由使用（https://github.com/agleed/calopus_statistical_heatmaps）。
