Wellcome/EPSRC Centre for International and Surgical Sciences (WEISS), University College London, London, UK.
Department of Computer Science, University College London, London, UK.
Int J Comput Assist Radiol Surg. 2022 May;17(5):833-839. doi: 10.1007/s11548-022-02609-z. Epub 2022 Apr 30.
In obstetric ultrasound (US) scanning, the learner's ability to mentally build a three-dimensional (3D) map of the fetus from a two-dimensional (2D) US image represents a major challenge in skill acquisition. We aim to build a US plane localisation system for 3D visualisation, training, and guidance without integrating additional sensors.
We propose a regression convolutional neural network (CNN) using image features to estimate the six-dimensional pose of arbitrarily oriented US planes relative to the fetal brain centre. The network was trained on synthetic images acquired from phantom 3D US volumes and fine-tuned on real scans. Training data was generated by slicing US volumes into imaging planes in Unity at random coordinates and more densely around the standard transventricular (TV) plane.
With phantom data, the median errors are 0.90 mm/1.17[Formula: see text] and 0.44 mm/1.21[Formula: see text] for random planes and planes close to the TV one, respectively. With real data, using a different fetus with the same gestational age (GA), these errors are 11.84 mm/25.17[Formula: see text]. The average inference time is 2.97 ms per plane.
The proposed network reliably localises US planes within the fetal brain in phantom data and successfully generalises pose regression for an unseen fetal brain from a similar GA as in training. Future development will expand the prediction to volumes of the whole fetus and assess its potential for vision-based, freehand US-assisted navigation when acquiring standard fetal planes.
在产科超声（US）扫描中，学习者能够从二维（2D）US 图像中构建胎儿的三维（3D）图谱，这是技能获取的主要挑战。我们旨在建立一个无需集成额外传感器的 3D 可视化、培训和引导的 US 平面定位系统。
我们提出了一种回归卷积神经网络（CNN），使用图像特征来估计任意方向 US 平面相对于胎儿大脑中心的六自由度姿态。该网络在从 3D US 体素获取的合成图像上进行训练，并在真实扫描上进行微调。训练数据是通过在 Unity 中以随机坐标和更靠近标准脑室（TV）平面的方式将 US 体素切成成像平面生成的。
在体模数据中，随机平面和靠近 TV 平面的平面的中位数误差分别为 0.90 毫米/1.17[公式：见正文]和 0.44 毫米/1.21[公式：见正文]。在真实数据中，对于具有相同胎龄（GA）的不同胎儿，这些误差为 11.84 毫米/25.17[公式：见正文]。平均推理时间为每个平面 2.97 毫秒。
该网络在体模数据中可靠地定位了胎儿大脑中的 US 平面，并成功地对训练中类似 GA 的未见过的胎儿大脑进行了姿态回归预测。未来的发展将扩展到整个胎儿体积的预测，并评估其在获取标准胎儿平面时基于视觉的自由手 US 辅助导航的潜力。
