An Intelligent Augmented Reality Training Framework for Neonatal Endotracheal Intubation.
An Intelligent Augmented Reality Training Framework for Neonatal Endotracheal Intubation.
复制标题
DOI：
10.1109/ismar50242.2020.00097
复制
发表时间：
2020-11
期刊：
影响因子：
--
通讯作者：
Hahn J
中科院分区：
文献类型：
--
作者：
Zhao S;Xiao X;Wang Q;Zhang X;Li W;Soghier L;Hahn J
新生儿气管插管（ETI）是一项关键的复苏技能，需要受训者在临床暴露前进行大量的实践。然而，目前的基于人体模型的训练方案是无效的，提供令人满意的实时程序指导准确的评估，由于缺乏透视可视化人体模型。培训效率因专家教员有限而进一步降低，这不可避免地导致受训人员的学习曲线较长。为此，我们提出了一个智能增强现实（AR）培训框架，为学员提供了一个完整的可视化的ETI程序的实时指导和评估。具体而言，所提出的框架是能够捕捉喉镜和人体模型的运动，并提供3D透视可视化渲染到头戴式显示器（HMD）。此外，开发了基于注意力的卷积神经网络（CNN）模型，以从捕获的运动中自动评估ETI性能，并识别对性能评估有显著贡献的运动区域。最后，增强的用户友好的反馈是通过颜色编码的运动轨迹，分类需要更多的实践突出显示的区域，与ETI评分规则可解释的结果交付。我们的机器学习模型的分类准确率为84.6%。
Neonatal Endotracheal Intubation (ETI) is a critical resuscitation skill that requires tremendous practice of trainees before clinical exposure. However, current manikin-based training regimen is ineffective in providing satisfactory real-time procedural guidance for accurate assessment due to the lack of see-through visualization within the manikin. The training efficiency is further reduced by the limited availability of expert instructors, which inevitably results in a long learning curve for trainees. To this end, we propose an intelligent Augmented Reality (AR) training framework that provides trainees with a complete visualization of the ETI procedure for real-time guidance and assessment. Specifically, the proposed framework is capable of capturing the motions of the laryngoscope and the manikin and offer 3D see-through visualization rendered to the head-mounted display (HMD). Furthermore, an attention-based Convolutional Neural Network (CNN) model is developed to automatically assess the ETI performance from the captured motions as well as identify regions of motions that significantly contribute to the performance evaluation. Lastly, augmented user-friendly feedback is delivered with interpretable results with the ETI scoring rubric through the color-coded motion trajectory that classifies highlighted regions that need more practice. The classification accuracy of our machine learning model is 84.6%.
登录
查看更多内容
影响因子：
2.9
作者：
Ghasemloonia, Ahmad;Maddahi, Yaser;Sutherland, Garnette R.
通讯作者：
Sutherland, Garnette R.
影响因子：
8
作者：
Garrido-Jurado, S.;Munoz-Salinas, R.;Marin-Jimenez, M. J.
通讯作者：
Marin-Jimenez, M. J.
影响因子：
2.4
作者：
Carlson, Jestin N.;Das, Samarjit;Yealy, Donald M.
通讯作者：
Yealy, Donald M.
DOI：
10.1007/s11548-019-02039-4
发表时间：
2019-09-01
影响因子：
3
作者：
Fawaz, Hassan Ismail;Forestier, Germain;Muller, Pierre-Alain
通讯作者：
Muller, Pierre-Alain
DOI：
10.1097/sih.0b013e3182415b4d
发表时间：
2012-06-01
影响因子：
2.4
作者：
Delson, Nathan;Sloan, Conan;Hastings, Randolph H.
通讯作者：
Hastings, Randolph H.