基于热成像的非接触式睡眠呼吸暂停检测与分类

doi:10.7523/j.ucas.2023.066

摘要/Abstract

摘要： 睡眠呼吸暂停综合征是一种常见且潜在危害巨大的睡眠疾病，睡眠呼吸暂停的分类检测可为疾病诊断提供重要依据。基于视频的睡眠监测系统因其非接触性，适用于该疾病的普适性筛查，其中热像仪隐私保护性强，近年来开始受到广泛关注。提出一种基于热成像的睡眠呼吸暂停检测与分类方法，通过采集胸腹部运动的时序信息，构建不同生理机制映射下中枢性和阻塞性睡眠呼吸暂停的二维复特征空间，并基于其统计特性提出呼吸努力强度特征与呼吸努力异同度特征，进而实现这2类睡眠呼吸暂停的分类检测。实验结果表明2类睡眠呼吸暂停检测的准确率均超过97.0%，有效克服了视频中观测噪声和冗余信息导致的有效信息难以提取等问题，有望助力于睡眠疾病的实际筛查诊断。

关键词: 睡眠呼吸暂停分类, 胸腹部运动, 热成像, 呼吸努力强度, 呼吸努力异同度

Abstract: Sleep apnea syndrome is a common and potentially harmful sleep disorder, and the classification and detection of sleep apnea can provide an important basis for the diagnosis of the disease. Due to their non-contact nature, video-based sleep monitoring systems are universally applicable for disease screening, among which thermal imaging cameras, with strong privacy protection, have attracted wide attention in recent years. In this paper, we propose a novel sleep apnea detection and classification method using thermal imaging. By obtaining the temporal information of thoracic and abdominal movement, a two-dimensional complex feature space mapping central and obstructive sleep apnea under different physiological mechanisms is constructed. Based on their statistical properties, the respiratory effort intensity feature and the respiratory effort asynchrony feature are proposed to achieve the classification and detection of two types of sleep apnea. Experimental results show that the accuracy of detecting both types of sleep apnea exceeds 97.0%. This work effectively overcomes the problem of difficulty in extracting valid information caused by observation noise and redundant information in videos, and is expected to assist in the actual screening and diagnosis of sleep disorders.

Key words: sleep apnea classification, thoracic and abdominal movement, thermal imaging, respiratory effort intensity, respiratory effort asynchrony

中图分类号:

TP274

廖楚楚, 黄志蓓, 秦飞, 王奕权, 王涛, 童永刚. 基于热成像的非接触式睡眠呼吸暂停检测与分类[J]. 中国科学院大学学报, 2025, 42(4): 538-546.

LIAO Chuchu, HUANG Zhipei, QIN Fei, WANG Yiquan, WANG Tao, TONG Yonggang. Non-contact sleep apnea detection and classification using thermal imaging[J]. Journal of University of Chinese Academy of Sciences, 2025, 42(4): 538-546.

参考文献

[1] 中国睡眠研究会. 2021年运动与睡眠白皮书[R/OL].(2021)[2023-03-15]. https://www.derucci.com.cn/upload/file/202103/36fad0de-96e6-478d-b38e-5e8d6032dd dd.pdf.
[2] Kryger M H. Diagnosis and management of sleep apnea syndrome[J]. Clinical Cornerstone, 2000, 2(5): 39-44. DOI:10.1016/S1098-3597(00)90039-5.
[3] Leung R S T, Bradley T D. Sleep apnea and cardiovascular disease[J]. American Journal of Respiratory and Critical Care Medicine, 2001, 164(12): 2147-2165. DOI:10.1164/ajrccm.164.12.2107045.
[4] Bassetti C, Aldrich M S. Sleep apnea in acute cerebrovascular diseases: final report on 128 patients[J]. Sleep, 1999, 22(2): 217-223. DOI:10.1093/sleep/22.2.217.
[5] Leger D, Bayon V, Laaban J P, et al. Impact of sleep apnea on economics[J]. Sleep Medicine Reviews, 2012, 16(5): 455-462. DOI:10.1016/j.smrv.2011.10.001.
[6] Baillieul S, Revol B, Jullian-Desayes I, et al. Diagnosis and management of central sleep apnea syndrome[J]. Expert Review of Respiratory Medicine, 2019, 13(6): 545-557. DOI:10.1080/17476348.2019.1604226.
[7] Gottlieb D J, Punjabi N M. Diagnosis and management of obstructive sleep apnea: a review[J]. JAMA, 2020, 323(14): 1389-1400. DOI:10.1001/jama.2020.3514.
[8] Berry R B, Budhiraja R, Gottlieb D J, et al. Rules for scoring respiratory events in sleep: update of the 2007 AASM manual for the scoring of sleep and associated events: deliberations of the sleep apnea definitions task force of the American Academy of Sleep Medicine[J]. Journal of Clinical Sleep Medicine, 2012, 8(5): 597-619. DOI:10.5664/jcsm.2172.
[9] Chinoy E D, Cuellar J A, Huwa K E, et al. Performance of seven consumer sleep-tracking devices compared with polysomnography[J]. Sleep, 2021, 44(5): zsaa291. DOI:10.1093/sleep/zsaa291.
[10] Thomas R J, Mietus J E, Peng C K, et al. Differentiating obstructive from central and complex sleep apnea using an automated electrocardiogram-based method[J]. Sleep, 2007, 30(12): 1756-1769. DOI:10.1093/sleep/30.12.1756.
[11] Zhao X Y, Wang X H, Yang T S, et al. Classification of sleep apnea based on EEG sub-band signal characteristics[J]. Scientific Reports, 2021, 11: 5824. DOI:10.1038/s41598-021-85138-0.
[12] Lin Y Y, Wu H T, Hsu C A, et al. Sleep apnea detection based on thoracic and abdominal movement signals of wearable piezoelectric bands[J]. IEEE Journal of Biomedical and Health Informatics, 2016, 21(6): 1533-1545. DOI:10.1109/JBHI.2016.2636778.
[13] Kagawa M, Tojima H, Matsui T. Non-contact diagnostic system for sleep apnea-hypopnea syndrome based on amplitude and phase analysis of thoracic and abdominal Doppler radars[J]. Medical & Biological Engineering & Computing, 2016, 54(5): 789-798. DOI:10.1007/s11517-015-1370-z.
[14] Zhuang Z X, Wang F X, Yang X, et al. Accurate contactless sleep apnea detection framework with signal processing and machine learning methods[J]. Methods, 2022, 205: 167-178. DOI:10.1016/j.ymeth.2022.06.013.
[15] Almazaydeh L, Elleithy K, Faezipour M, et al. Apnea detection based on respiratory signal classification[J]. Procedia Computer Science, 2013, 21: 310-316. DOI:10.1016/j.procs.2013.09.041.
[16] Alshaer H, Hummel R, Bradley T D. Distinguishing patients with central from obstructive sleep apnea using overnight breath sound recordings[J]. European Respiratory Journal, 2017, 50(suppl 61): OA3204. DOI:10.1183/1393003.congress-2017.OA3204.
[17] Molinaro N, Schena E, Silvestri S, et al. Contactless vital signs monitoring from videos recorded with digital cameras: an overview[J]. Frontiers in Physiology, 2022, 13:801709.DOI:10.3389/fphys.2022.801709.
[18] Luce J M, Culver B H. Respiratory muscle function in health and disease[J]. CHEST, 1982, 81(1): 82-90. DOI:10.1378/chest.81.1.82.
[19] Varady P, Bongar S, Benyo Z. Detection of airway obstructions and sleep apnea by analyzing the phase relation of respiration movement signals[J]. IEEE Transactions on Instrumentation and Measurement, 2003, 52(1): 2-6. DOI:10.1109/TIM.2003.809095.
[20] Al-Angari H M, Sahakian A V. Automated recognition of obstructive sleep apnea syndrome using support vector machine classifier[J]. IEEE Transactions on Information Technology in Biomedicine, 2012, 16(3): 463-468. DOI:10.1109/TITB.2012.2185809.
[21] Ammar H, Lashkar S. Obstructive sleep apnea diagnosis based on a statistical analysis of the optical flow in video recordings[C]//2016 International Symposium on Signal, Image, Video and Communications (ISIVC). November 21-23, 2016, Tunis, Tunisia. IEEE, 2016: 18-23. DOI:10.1109/ISIVC.2016.7893955.
[22] Zhu K Y, Yadollahi A, Taati B. Non-contact apnea-hypopnea index estimation using near infrared video[C]//2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). July 23-27, 2019, Berlin, Germany. IEEE, 2016: 792-795. DOI:10.1109/EMBC.2019.8857711.
[23] Lorato I, Stuijk S, Meftah M, et al. Camera-Based on-line short cessation of breathing detection[C]//2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW). Seoul, Korea (South): IEEE, 2019: 1656-1663[2022-07-17]. https://ieeexplore.ieee.org/document/9022052/. DOI:10.1109/ICCVW.2019.00205.
[24] Akbarian S, Ghahjaverestan N M, Yadollahi A, et al. Distinguishing obstructive versus central apneas in infrared video of sleep using deep learning: validation study[J]. Journal of Medical Internet Research, 2020, 22(5): e17252. DOI:10.2196/17252.
[25] Wang Y L, Hu M H, Zhou Y W, et al. Unobtrusive and automatic classification of multiple People’s abnormal respiratory patterns in real time using deep neural network and depth camera[J]. IEEE Internet of Things Journal, 2020, 7(9): 8559-8571. DOI:10.1109/JIOT.2020.2991456.
[26] Scebba G, Da Poian G, Karlen W. Multispectral video fusion for non-contact monitoring of respiratory rate and apnea[J]. IEEE Transactions on Biomedical Engineering, 2021, 68(1): 350-359. DOI:10.1109/TBME.2020.2993649.
[27] Yang R S, Zhang L D, Wang Y L, et al. Automatic detection of obstructive sleep apnea based on multimodal imaging system and binary code alignment[C]//Zhai G, Zhou J, Yang H, et al. Digital TV and Wireless Multimedia Communications. Singapore: Springer, 2022: 108-119. DOI:10.1007/978-981-19-2266-4_9.
[28] Yang C, Cheung G, Stankovic V, et al. Sleep apnea detection via depth video and audio feature learning[J]. IEEE Transactions on Multimedia, 2017, 19(4): 822-835. DOI:10.1109/TMM.2016.2626969.
[29] Otsu N. A threshold selection method from gray-level histograms[J]. IEEE Transactions on Systems, Man, and Cybernetics, 1979, 9(1): 62-66. DOI: 10.1109/TSMC.1979.4310076.
[30] Farnebäck G. Two-frame motion estimation based on polynomial expansion[M]//Bigun J, Gustavsson T. Image Analysis. Berlin, Heidelberg: Springer Berlin Heidelberg, 2003: 363-370. DOI: 10.1007/3-540-45103-x_50.
[31] Prisk G K, Hammer J, Newth C J L. Techniques for measurement of thoracoabdominal asynchrony[J]. Pediatric Pulmonology, 2002, 34(6): 462-472. DOI:10.1002/ppul.10204.
[32] Kopaczka M, Özkan Ö, Merhof D. Face tracking and respiratory signal analysis for the detection of sleep apnea in thermal infrared videos with head movement[C]//Battiato S, Farinella G M, Leo M, et al. New Trends in Image Analysis and Processing-ICIAP 2017. Cham: Springer International Publishing, 2017: 163-170. DOI:10.1007/978-3-319-70742-6_15.
[33] White D P. Pathogenesis of obstructive and central sleep apnea[J]. American Journal of Respiratory and Critical Care Medicine, 2005, 172(11): 1363-1370. DOI:10.1164/rccm.200412-1631SO.