Attentional Generative Multimodal Network for Neonatal Postoperative Pain Estimation.
Attentional Generative Multimodal Network for Neonatal Postoperative Pain Estimation.
复制标题
用于新生儿术后疼痛估计的注意力生成多模态网络。
DOI：
10.1007/978-3-031-16437-8_72
复制
发表时间：
2022
期刊：
影响因子：
--
通讯作者：
Sun,Yu
中科院分区：
文献类型：
--
作者：
Salekin,MdSirajus;Zamzmi,Ghada;Goldgof,Dmitry;Mouton,PeterR;Anand,KanwaljeetJS;Ashmeade,Terri;Prescott,Stephanie;Huang,Yangxin;Sun,Yu
基于人工智能（AI）的方法允许基于对感觉信号（包括面部表情、身体动作和哭泣频率）的细微变化的连续监测和处理来自动评估疼痛强度。目前，有一个大的和不断增长的需要，扩大目前的基于人工智能的方法来评估术后疼痛的新生儿重症监护病房（NICU）。与临床上的急性程序性疼痛不同，NICU中的新生儿术后镇静后出现疼痛，通常需要插管，并具有不同的能量储备以显示强烈的疼痛反应。在这里，我们提出了一种新的多模式的方法，设计，开发和验证的新生儿术后疼痛评估具有挑战性的新生儿重症监护室设置。我们的方法包括一个强大的网络，能够有效地重建丢失的模态（例如，由于插管而模糊的面部表情），使用具有用于学习关节特征的生成模型的无监督时空特征学习。我们的方法产生的最终疼痛评分沿着强度使用注意力跨模态特征融合。使用来自NICU中术后新生儿的实验数据集，与最先进的方法相比，我们的疼痛评估方法实现了上级的性能（AUC 0.906，准确度0.820）。
Artificial Intelligence (AI)-based methods allow for automatic assessment of pain intensity based on continuous monitoring and processing of subtle changes in sensory signals, including facial expression, body movements, and crying frequency. Currently, there is a large and growing need for expanding current AI-based approaches to the assessment of postoperative pain in the neonatal intensive care unit (NICU). In contrast to acute procedural pain in the clinic, the NICU has neonates emerging from postoperative sedation, usually intubated, and with variable energy reserves for manifesting forceful pain responses. Here, we present a novel multi-modal approach designed, developed, and validated for assessment of neonatal postoperative pain in the challenging NICU setting. Our approach includes a robust network capable of efficient reconstruction of missing modalities (e.g., obscured facial expression due to intubation) using an unsupervised spatio-temporal feature learning with a generative model for learning the joint features. Our approach generates the final pain score along with the intensity using an attentional cross-modal feature fusion. Using experimental dataset from postoperative neonates in the NICU, our pain assessment approach achieves superior performance (AUC 0.906, accuracy 0.820) as compared to the state-of-the-art approaches.