Literature DB >> 34249635

Camera-based discomfort detection using multi-channel attention 3D-CNN for hospitalized infants.

Yue Sun1, Jingjing Hu2, Wenjin Wang1, Min He2, Peter H N de With1.   

Abstract

BACKGROUND: Detecting discomfort in infants is an important topic for their well-being and development. In this paper, we present an automatic and continuous video-based system for monitoring and detecting discomfort in infants.
METHODS: The proposed system employs a novel and efficient 3D convolutional neural network (CNN), which achieves an end-to-end solution without the conventional face detection and tracking steps. In the scheme of this study, we thoroughly investigate the video characteristics (e.g., intensity images and motion images) and CNN architectures (e.g., 2D and 3D) for infant discomfort detection. The realized improvements of the 3D-CNN are based on capturing both the motion and the facial expression information of the infants.
RESULTS: The performance of the system is assessed using videos recorded from 24 hospitalized infants by visualizing receiver operating characteristic (ROC) curves and measuring the values of area under the ROC curve (AUC). Additional performance metrics (labeling accuracy) are also calculated. Experimental results show that the proposed system achieves an AUC of 0.99, while the overall labeling accuracy is 0.98.
CONCLUSIONS: These results confirms the robustness by using the 3D-CNN for infant discomfort monitoring and capturing both motion and facial expressions simultaneously. 2021 Quantitative Imaging in Medicine and Surgery. All rights reserved.

Entities:  

Keywords:  3D convolutional neural network (3D-CNN); Infant discomfort; discomfort detection; video health monitoring

Year:  2021        PMID: 34249635      PMCID: PMC8250023          DOI: 10.21037/qims-20-1302

Source DB:  PubMed          Journal:  Quant Imaging Med Surg        ISSN: 2223-4306


  14 in total

1.  3D convolutional neural networks for human action recognition.

Authors:  Shuiwang Ji; Ming Yang; Kai Yu
Journal:  IEEE Trans Pattern Anal Mach Intell       Date:  2013-01       Impact factor: 6.226

2.  Comparison of interpolating methods for image resampling.

Authors:  J Parker; R V Kenyon; D E Troxel
Journal:  IEEE Trans Med Imaging       Date:  1983       Impact factor: 10.048

3.  Gabor Convolutional Networks.

Authors:  Shangzhen Luan; Chen Chen; Baochang Zhang; Jungong Han; Jianzhuang Liu
Journal:  IEEE Trans Image Process       Date:  2018-09       Impact factor: 10.856

4.  Premature Infant Pain Profile: development and initial validation.

Authors:  B Stevens; C Johnston; P Petryshen; A Taddio
Journal:  Clin J Pain       Date:  1996-03       Impact factor: 3.442

5.  The impact of cumulative pain/stress on neurobehavioral development of preterm infants in the NICU.

Authors:  Xiaomei Cong; Jing Wu; Dorothy Vittner; Wanli Xu; Naveed Hussain; Shari Galvin; Megan Fitzsimons; Jacqueline M McGrath; Wendy A Henderson
Journal:  Early Hum Dev       Date:  2017-03-23       Impact factor: 2.079

Review 6.  Neonatal pain and developmental outcomes in children born preterm: a systematic review.

Authors:  Beatriz O Valeri; Liisa Holsti; Maria B M Linhares
Journal:  Clin J Pain       Date:  2015-04       Impact factor: 3.442

7.  Detecting discomfort in infants through facial expressions.

Authors:  Yue Sun; Caifeng Shan; Tao Tan; Tong Tong; Wenjin Wang; Arash Pourtaherian; Peter H N de With
Journal:  Physiol Meas       Date:  2019-12-03       Impact factor: 2.833

8.  Assessing distress in pediatric intensive care environments: the COMFORT scale.

Authors:  B Ambuel; K W Hamlett; C M Marx; J L Blumer
Journal:  J Pediatr Psychol       Date:  1992-02

9.  Multi-PIE.

Authors:  Ralph Gross; Iain Matthews; Jeff Cohn; Takeo Kanade; Simon Baker
Journal:  Proc Int Conf Autom Face Gesture Recognit       Date:  2010-05-01

10.  Automatic and Continuous Discomfort Detection for Premature Infants in a NICU Using Video-Based Motion Analysis.

Authors:  Yue Sun; Peter H N de With; Deedee Kommers; Wenjin Wang; Rohan Joshi; Caifeng Shan; Tao Tan; Ronald M Aarts; Carola van Pul; Peter Andriessen
Journal:  Conf Proc IEEE Eng Med Biol Soc       Date:  2019-07
View more
  1 in total

1.  Artificial Intelligence Based Pain Assessment Technology in Clinical Application of Real-World Neonatal Blood Sampling.

Authors:  Xiaoying Cheng; Huaiyu Zhu; Linli Mei; Feixiang Luo; Xiaofei Chen; Yisheng Zhao; Shuohui Chen; Yun Pan
Journal:  Diagnostics (Basel)       Date:  2022-07-29
  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.