Large scale simulation of labeled intraoperative scenes in unity.
Large scale simulation of labeled intraoperative scenes in unity.
复制标题
DOI：
10.1007/s11548-022-02598-z
复制
发表时间：
2022-05
影响因子：
3
通讯作者：
中科院分区：
文献类型：
--
作者：
使用合成或模拟数据有可能大大提高图像引导手术和其他医疗应用中训练数据的可用性和数量，其中对现实生活中训练数据的访问是有限的。通过使用Unity游戏引擎，可以模拟复杂的术中场景。Unity Perception软件包允许场景内参数的随机化和自动标记，使模拟大型数据集成为一个简单的操作。在这项工作中，该方法已被原型为肝脏分割腹腔镜视频图像。50，000张模拟图像用于训练U-Net，无需任何手动标记。将模拟数据的使用与用950个手动标记的腹腔镜图像训练的模型进行比较。当对来自10名独立患者的数据进行评估时，10例病例中有4例的合成数据优于真实的数据。10例病例的平均DICE评分分别为0.59（合成数据）、0.64（真实的数据）和0.75（合成和真实的数据）。使用这种方法生成的合成数据能够对真实的数据进行有效的推断，平均性能略低于在真实的数据上训练的模型。与仅在真实的数据上进行训练相比，使用模拟数据进行预训练提高了模型性能。
The use of synthetic or simulated data has the potential to greatly improve the availability and volume of training data for image guided surgery and other medical applications, where access to real-life training data is limited. By using the Unity game engine, complex intraoperative scenes can be simulated. The Unity Perception package allows for randomisation of paremeters within the scene, and automatic labelling, to make simulating large data sets a trivial operation. In this work, the approach has been prototyped for liver segmentation from laparoscopic video images. 50,000 simulated images were used to train a U-Net, without the need for any manual labelling. The use of simulated data was compared against a model trained with 950 manually labelled laparoscopic images. When evaluated on data from 10 separate patients, synthetic data outperformed real data in 4 out of 10 cases. Average DICE scores across the 10 cases were 0.59 (synthetic data), 0.64 (real data) and 0.75 (both synthetic and real data). Synthetic data generated using this method is able to make valid inferences on real data, with average performance slightly below models trained on real data. The use of the simulated data for pre-training boosts model performance, when compared with training on real data only.
影响因子：
9.2
作者：
Geiger, A.;Lenz, P.;Urtasun, R.
通讯作者：
Urtasun, R.