Transfer Learning Based Prediction Model for Obstructive Sleep Apnea from Facial Depth Maps
Keywords:
Obstructive sleep apnea, VGG-19, deep learning.Abstract
Stress levels are rising at an alarming rate today as a direct result of the increased level of competition in both the educational and professional spheres. This stress is a contributing factor in the development of a wide variety of ailments, including obstructive sleep apnea. Relaxation of the tongue and the muscles that line the airway may cause obstructive sleep apnea (OSA), which occurs when there is a recurring blockage in the airway during sleep. Snoring, difficulty sleeping because of choking or gasping for breath, and waking up feeling exhausted are typical symptoms of obstructive sleep apnea (OSA). The OSA diagnosis is time-consuming and expensive, both financially and in terms of lost productivity. Because of this, a significant number of patients continue to go untreated and are uninformed of the nature of their illness. Through a depth map of human face scans, the application of deep learning algorithms is employed to identify the condition. In comparison to a standard 2-D colour picture, the depth map offers much more information on the morphology of the face. The traditional machine learning models did not succeed in producing the best possible results in terms of prediction and classification accuracy. Following the extraction of deep face map features using the proposed VGG-19 method and the subsequent training of both the algorithm and a module that was learned on the IMAGENET dataset, transfer learning is used to train the algorithm on OSA facial pictures. The deep learning algorithm known as VGG-19 is trained with the use of the photos from the 3D face scan. In order to predict OSA from fresh test photos, a trained model of VGG-19 is used.
Downloads
References
D. R. Hillman and L. C. Lack, “Public health implications of sleep loss: the community
burden,” Med J Aust, vol. 199, no. 8, pp. S7–S10, 2013.
J. C. Lam, S. Sharma, B. Lam et al., “Obstructive sleep apnoea: definitions, epidemiology &
natural history,” Indian Journal of Medical Research, vol. 131, no. 2, p. 165, 2010.
“Obstructive sleep apnoea (osa; sleep apnea) information,” Jul 2018. [Online]. Available:
https://www.myvmc.com/diseases/obstructivesleep-apnoea-osa-sleep-apnea
K. Kee, M. T. Naughton et al., “Sleep apnoea-a general practice approach,” Australian family
physician, vol. 38, no. 5, p. 284, 2009.
B. Lam, M. Ip, E. Tench, and C. Ryan, “Craniofacial profile in asian and white subjects with
obstructive sleep apnoea,” Thorax, vol. 60, no. 6, pp. 504–510, 2005.
J. E. Barrera, C. Y. Pau, V.-I. Forest, A. B. Holbrook, and G. R. Popelka, “Anatomic measures
of upper airway structures in obstructive sleep apnea,” World journal of otorhinolaryngologyhead and neck surgery, vol. 3, no. 2, pp. 85–91, 2017.
R. J. Schwab, M. Pasirstein, R. Pierson, A. Mackley, R. Hachadoorian, R. Arens, G. Maislin,
and A. I. Pack, “Identification of upper airway anatomic risk factors for obstructive sleep apnea
with volumetric magnetic resonance imaging,” American journal of respiratory and critical care
medicine, vol. 168, no. 5, pp. 522–530, 2003.
Lowe, J. A. Fleetham, S. Adachi, and C. F. Ryan, “Cephalometric and computed tomographic
predictors of obstructive sleep apnea severity,” American Journal of Orthodontics and
Dentofacial Orthopedics, vol. 107, no. 6, pp. 589–595, 1995.
T. Vidigal, L. Oliveira, T. Moura, F. Haddad, K. Sutherland, P. Cistulli, R. Schwab, A. Pack,
U. Magalang, S. Leinwand et al., “Can intra-oral and facial photos predict osa in the general
and clinical population?” Sleep Medicine, vol. 40, p. e339, 2017.
R. W. Lee, K. Sutherland, A. S. Chan, B. Zeng, R. R. Grunstein, M. A. Darendeliler,
R. J. Schwab, and P. A. Cistulli, “Relationship between surface facial dimensions and upper
airway structures in obstructive sleep apnea,” Sleep, vol. 33, no. 9, pp. 1249–1254, 2010.
E.-K. Pae, A. A. Lowe, and J. A. Fleetham, “Shape of the face and tongue in obstructive
sleep apnea patientsstatistical analysis of coordinate data,” Clinical orthodontics and research,
vol. 2, no. 1, pp. 10–18, 1999.
R. W. Lee, A. S. Chan, R. R. Grunstein, and P. A. Cistulli, “Craniofacial phenotyping
in obstructive sleep apneaa novel quantitative photographic approach,” Sleep, vol. 32, no. 1,
pp. 37–45, 2009.
R. W. Lee, P. Petocz, T. Prvan, A. S. Chan, R. R. Grunstein, and P. A. Cistulli,
“Prediction of obstructive sleep apnea with craniofacial photographic analysis,” Sleep, vol. 32,
no. 1, pp. 46–52, 2009.
F. Espinoza-Cuadros, R. Fernandez-Pozo, D. T. Toledano, J. D. Alc ´ azar- ´ Ram´ırez,
E. Lopez-Gonzalo, and L. A. Hern ´ andez-G ´ omez, “Speech sig- ´ nal and facial image
processing for obstructive sleep apnea assessment,” Computational and mathematical methods
in medicine, vol. 2015, 2015.
H. Nosrati, N. Sadr, and P. de Chazal, “Apnoea-hypopnoea index estimation using
craniofacial photographic measurements,” in Computing in Cardiology Conference (CinC),
IEEE, 2016, pp. 1033–1036.
T. Balaei, K. Sutherland, P. A. Cistulli, and P. de Chazal, “Automatic detection of
obstructive sleep apnea using facial images,” in Biomedical Imaging (ISBI 2017), 2017 IEEE
th International Symposium on. IEEE, 2017, pp. 215–218.
S. M. Islam, M. S. Goonewardene, and M. Farella, “A review on three-dimensional
facial averaging for the assessment of orthodontic disorders,” in Innovations and Advances in
Computing, Informatics, Systems Sciences, Networking and Engineering. Springer, 2015, pp.
–397.
J. Moss, “The use of three-dimensional imaging in orthodontics,” The European
Journal of Orthodontics, vol. 28, no. 5, pp. 416–425, 2006.
S. M. Banabilh, A. Suzina, S. Dinsuhaimi, A. Samsudin, and G. Singh, “Craniofacial
obesity in patients with obstructive sleep apnea,” Sleep and Breathing, vol. 13, no. 1, pp. 19–
, 2009.
“Artec eva.” [Online]. Available: https://www.artec3d.com/portable-3dscanners/arteceva
“Meshlab.” [Online]. Available: http://www.meshlab.net
O. M. Parkhi, A. Vedaldi, A. Zisserman et al., “Deep face recognition.” in BMVC, vol.
, no. 3, 2015, p. 6.
Masi, S. Rawls, G. Medioni, and P. Natarajan, “Pose-Aware Face Recognition in the
Wild,” in CVPR, 2016.
Krizhevsky, I. Sutskever, and G. E. Hinton, “Imagenet classification with deep
convolutional neural networks,” in Advances in neural information processing systems, 2012,
pp. 1097–1105.
Chatfield, K. Simonyan, A. Vedaldi, and A. Zisserman, “Return of the devil in the
details: Delving deep into convolutional nets,” arXiv preprint arXiv:1405.3531, 2014.
Downloads
Published
Issue
Section
License
You are free to:
- Share — copy and redistribute the material in any medium or format for any purpose, even commercially.
- Adapt — remix, transform, and build upon the material for any purpose, even commercially.
- The licensor cannot revoke these freedoms as long as you follow the license terms.
Under the following terms:
- Attribution — You must give appropriate credit , provide a link to the license, and indicate if changes were made . You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
- No additional restrictions — You may not apply legal terms or technological measures that legally restrict others from doing anything the license permits.
Notices:
You do not have to comply with the license for elements of the material in the public domain or where your use is permitted by an applicable exception or limitation .
No warranties are given. The license may not give you all of the permissions necessary for your intended use. For example, other rights such as publicity, privacy, or moral rights may limit how you use the material.