A Survey Study of the 3D Facial Landmark Detection Techniques Used as a Screening Tool for Diagnosis of the Obstructive Sleep Apnea Syndrome
![](/bundles/mdpisciprofileslink/img/unknown-user.png)
Round 1
Reviewer 1 Report
Comments and Suggestions for AuthorsThank you for your study. I have listed down my major and some minor concerns. I sincerely hope that this would provide the necessary inputs to further improve this manuscript.
1. Please check the spelling and other grammatical mistakes present throughout the paper.
2. Please reduce the similar sentences and redundant information.
3. Please increase the figure descriptions in the article.
4. Please increase the figure resolutions in the article.
5. The data sets should be more detailed and reference should be made in the data set section.
6. Also mention some future research directions in the conclusion section.
7. Create a discussion section and discuss the studies carried out and state their advantages and disadvantages. Create a table for this.
8. You should increase the explanations in the Challenges of the anatomical landmark identification section and cite studies used in the literature.
9. Explanations with only 1 reference regarding transfer learning should be increased as they are insufficient.
10. In section 3.2, the sections written one under the other, starting with Symmetry, are not understandable. Section 3.2 should be redesigned from scratch.
11. AI based techniques should be detailed more, there are different models. These models should also be added with reference.
12. Please refer to the following related papers
Collier, E., Nadjmi, N., Verbraecken, J., & Van de Casteele, E. (2023). Anthropometric 3D evaluation of the face in patients with sleep related breathing disorders. Sleep and Breathing, 27(6), 2209-2221.
Zhang, Z., Feng, Y., Li, Y., Zhao, L., Wang, X., & Han, D. (2023). Prediction of obstructive sleep apnea using deep learning in 3D craniofacial reconstruction. Journal of thoracic disease, 15(1), 90.
Kayabekir, M., YaÄŸanoÄŸlu, M., & Köse, C. E. M. A. L. (2022). SNOROSALAB: A method facilitating the diagnosis of sleep breathing disorders before polysomnography. IRBM, 43(4), 259-271.
YaÄŸanoÄŸlu, M., Kayabekir, M., & Köse, C. (2017). SNORAP: A device for the correction of Impaired Sleep health by using tactile stimulation for individuals with mild and moderate sleep disordered breathing. Sensors, 17(9), 2006.
Chen, Q., Liang, Z., Wang, Q., Ma, C., Lei, Y., Sanderson, J. E., ... & Fang, F. (2023). Self-helped detection of obstructive sleep apnea based on automated facial recognition and machine learning. Sleep and Breathing, 27(6), 2379-2388.
Yuen, H. M., Chan, K. C. C., Chu, W. C. W., Chan, J. W., Wing, Y. K., Li, A. M., & Au, C. T. (2023). Craniofacial phenotyping by photogrammetry in Chinese prepubertal children with obstructive sleep apnea. Sleep, 46(3), zsac289.
Wong, M. H., Li, M., Tam, K. M., Yuen, H. M., Au, C. T., Chan, K. C. C., ... & Lui, L. M. (2023). A Quasiconformal-Based Geometric Model for Craniofacial Analysis and Its Application. Axioms, 12(4), 393.
Singh, P., Bornstein, M. M., Hsung, R. T. C., Ajmera, D. H., Leung, Y. Y., & Gu, M. (2024). Frontiers in Three-Dimensional Surface Imaging Systems for 3D Face Acquisition in Craniofacial Research and Practice: An Updated Literature Review. Diagnostics, 14(4), 423.
Kayabekir, M., & YaÄŸanoÄŸlu, M. (2022). The relationship between snoring sounds and EEG signals on polysomnography. Sleep and Breathing, 1-8.
Ji, X., Li, Y., & Wen, P. (2023). 3DSleepNet: A multi-channel bio-signal based sleep stages classification method using deep learning. IEEE Transactions on Neural Systems and Rehabilitation Engineering.
Comments on the Quality of English LanguageExtensive editing of English language required
Author Response
Dear Reviewer,
Thank you very much for taking the time to review my manuscript. I have followed your guidance and made enhancements in multiple sections to present the information in a more systematic manner. I have also included some of the papers you suggested. I hope the paper has been improved and would like to get your opinion on the revisions.
Thank you.
Best regards, Rastislav Hornak
Reviewer 2 Report
Comments and Suggestions for AuthorsThe core contribution of this work is somewhat not clear enough. Therefore, a separate subsection highlighting the contribution of this work needs to be added. 3D Facial anatomical 47 landmark detection is used as a screening tool for diagnosing Obstructive Sleep Apnea 48 (OSA) syndrome. However, some other techniques need to be mentioned also. For example, Radar remote sensing has been used for OSA diagnosis several times. This paper also fails to report some of the novel technological papers that discussed the OSA diagnosis. Please add those papers to make your paper stronger.
1. https://doi.org/10.1109/JERM.2023.3317304
2. https://doi.org/10.1109/ACCESS.2021.3062385
3. https://doi.org/10.1109/LSENS.2022.3148378
Author Response
Dear Reviewer,
Thank you very much for taking the time to review my manuscript. Please find the updated manuscript with the highlighted corrections in the attachment. I have followed your guidance and made enhancements in multiple sections. I hope the paper has been improved and would like to get your opinion on the revisions.
Thank you.
Best regards, Rastislav Hornak
Author Response File: Author Response.docx
Reviewer 3 Report
Comments and Suggestions for AuthorsI would like to acknowledge the authors on this well-written paper. It gives a very nice overview on plausible techniques to be used as screening tools for diagnosis of the Obstructive Sleep Apnea syndrome in children and young adults. The illustrations are satisfactory; however, I do think the manuscript would benefit from some uniting tables showings the forces and draw backs for the single techniques including suggested patient age of the application. I find the use of references satisfactory. Thus, I would recommend a minor revision of this paper before publication.
Author Response
Dear Reviewer,
Thank you very much for taking the time to review my manuscript. I also want to thank you for your positive feedback. I have not however included the uniting tables. I have not found the information required to be presented in the tables. But, I have made some enhancements in my manuscript to present the information in a more systematic approach and also have added some more references. I hope the paper has been improved and would like to get your opinion on the revisions.
Thank you.
Best regards, Rastislav Hornak
Round 2
Reviewer 1 Report
Comments and Suggestions for AuthorsFigure explanations are still not sufficient. Please let's increase the explanations
What does the red line mean in Figure 1?
Figure resolutions are low. In Figure 3, the line in the box on the left is not clear. Also the text is not clear
The discussion section is missing. What are the advantages and disadvantages of this study? Compare it with other studies and indicate the limitations and unique aspects of this study.
State the contribution of this study at the end of the introduction.
Some studies should be referenced:
Costa, J. C., Rebelo-Marques, A., Machado, J. N., Gama, J. M. R., Santos, C., Teixeira, F., & Moita, J. (2019). Validation of NoSAS (Neck, Obesity, Snoring, Age, Sex) score as a screening tool for obstructive sleep apnea: Analysis in a sleep clinic. Pulmonology, 25(5), 263-270.
Monna, F., Messaoud, R. B., Navarro, N., Baillieul, S., Sanchez, L., Loiodice, C., ... & Pépin, J. L. (2022). Machine learning and geometric morphometrics to predict obstructive sleep apnea from 3D craniofacial scans. Sleep Medicine, 95, 76-83.
Jayaratne, Y. S., Elsharkawi, I., Macklin, E. A., Voelz, L., Weintraub, G., Rosen, D., & Skotko, B. G. (2017). The facial morphology in Down syndrome: A 3D comparison of patients with and without obstructive sleep apnea. American journal of medical genetics Part A, 173(11), 3013-3021.
Kayabekir, M., & YaÄŸanoÄŸlu, M. (2024). SPINDILOMETER: a model describing sleep spindles on EEG signals for polysomnography. Physical and Engineering Sciences in Medicine, 1-13.
Cetinoglu, E. D., Ursavas, A., Ozdemir, S., Ercan, I., Can, F., Ocakoglu, G., ... & Ursavas, A. (2019). Three-dimensional analysis of craniofacial shape in obstructive sleep apnea syndrome using geometric morphometrics. International Journal of Morphology, 37, 338-343.
Zhang, Z., Feng, Y., Li, Y., Zhao, L., Wang, X., & Han, D. (2023). Prediction of obstructive sleep apnea using deep learning in 3D craniofacial reconstruction. Journal of thoracic disease, 15(1), 90.
Chen, Q., Liang, Z., Wang, Q., Ma, C., Lei, Y., Sanderson, J. E., ... & Fang, F. (2023). Self-helped detection of obstructive sleep apnea based on automated facial recognition and machine learning. Sleep and Breathing, 27(6), 2379-2388.
Comments on the Quality of English LanguageExtensive editing of English language required
Author Response
Dear Reviewer,
Thank you very much for taking the time to review my manuscript. I have followed your guidance and hope the paper has been improved.
- I have completely removed Figure 1 as I believe it did not provide much value.
- I have updated the figure explanations.
- Regarding the Figure 3 (now Figure 2). I have been using the original full-size picture of this diagram since the beginning. It may have appeared blurry in Microsoft Word. The size of the picture is 1319 x 886 px, which I find good enough.
- I have added the missing sections.
Thank you.
Best regards, Rastislav Hornák