Convolutional neural networks for neonatal pain assessment

被引：17

作者：

Zamzmi G. ^{[1
]}

Paul R. ^{[1
]}

Salekin M.S. ^{[1
]}

Goldgof D. ^{[1
]}

Kasturi R. ^{[1
]}

Ho T. ^{[2
]}

Sun Y. ^{[1
]}

机构：

[1] Department of Computer Science and Engineering, University of South Florida, Tampa, 33620, FL

[2] Morsani College of Medicine Pediatrics Department, University of South Florida, Tampa, 33620, FL

来源：

IEEE Transactions on Biometrics, Behavior, and Identity Science | 2019年 / 1卷 / 03期

关键词：

clinical applications; Convolutional neural network; facial expression analysis; pain assessment;

D O I：

10.1109/TBIOM.2019.2918619

中图分类号：

学科分类号：

摘要：

The current standard for assessing neonatal pain is discontinuous and inconsistent because it depends highly on the observers bias. These drawbacks can result in delayed intervention and inconsistent treatment of pain. Convolutional neural networks (CNNs) have gained much popularity in the last decades due to the wide range of its successful applications in medical image analysis, object and emotion recognition. In this paper, we investigated the use of a novel lightweight neonatal convolutional neural network as well as other popular CNN architectures for assessing neonatal pain. We experimented with various image augmentation techniques and evaluated the CNN architectures using two real-world datasets [COPE and neonatal pain assessment dataset (NPAD)] collected from neonates while being hospitalized in the intensive care unit. The experimental results demonstrate the superiority and efficiency of the novel network in assessing neonatal pain. They also suggest that the automatic recognition of neonatal pain using CNN networks is a viable and more efficient alternative to the current assessment standard. © 2019 IEEE.

引用

页码：192 / 200

页数：8

共 35 条

[1]

Marchant A., Neonates do not feel pain': A critical review of the evidence, Biosci. Horizons Int. J. Student Res., 7, pp. 1-9, (2014)

[2]

Cruz M.D., Fernandes A.M., Oliveira C.R., Epidemiology of painful procedures performed in neonates: A systematic review of observational studies, Eur. J. Pain, 20, 4, pp. 489-498, (2016)

[3]

Field T., Preterm newborn pain research review, Infant Behav. Develop., 49, pp. 141-150, (2017)

[4]

Zamzmi G., Kasturi R., Goldgof D., Zhi R., Ashmeade T., Sun Y., A review of automated pain assessment in infants: Features, classification tasks, and databases, IEEE Rev. Biomed. Eng., 11, pp. 77-96, (2017)

[5]

Nanni L., Brahnam S., Lumini A., A local approach based on a local binary patterns variant texture descriptor for classifying pain states, Expert Syst. Appl., 37, 12, pp. 7888-7894, (2010)

[6]

Brahnam S., Chuang C.-F., Shih F.Y., Slack M.R., Machine recognition and representation of neonatal facial displays of acute pain, Artif. Intell. Med., 36, 3, pp. 211-222, (2006)

[7]

Mansor M.N., Rejab M.N., A computational model of the infant pain impressions with Gaussian and nearest mean classifier, Proc. IEEE Int. Conf. Control Syst. Comput. Eng, pp. 249-253, (2013)

[8]

Rahman Z.-U., Jobson D.J., Woodell G.A., Multi-scale retinex for color image enhancement, Proc. 3rd IEEE Int. Conf. Image Process., 3, pp. 1003-1006, (1996)

[9]

Celona L., Manoni L., Neonatal facial pain assessment combining hand-crafted and deep features, Proc. Int. Conf. Image Anal. Process, pp. 197-204, (2017)

[10]

Zamzami G., Ruiz G., Goldgof D., Kasturi R., Sun Y., Ashmeade T., Pain assessment in infants: Towards spotting pain expression based on infants' facial strain, Proc. 11th IEEE Int. Conf. Workshops Autom. Face Gesture Recognit. (FG), 5, pp. 1-5, (2015)

← 1 2 3 4 →