Abstract
This study addresses the current challenges in obtaining preliminary cost estimates for hair transplant procedures, which often involve time-consuming and frustrating communication between clinics and patients. Our goal is to streamline this process by integrating image processing and computer visualization techniques into an application tailored for individuals seeking hair transplantation services. Specifically, our focus is on Asian men experiencing hair loss in Stages 1 to 3. To achieve this, we have developed an image acquisition app, enhanced images as necessary using GFP-GAN, and performed image segmentation with BiSeNet. Additionally, we utilized MediaPipe to create new hairline projections for individuals with receding hairlines. This comprehensive approach allows us to calculate the hair recipient area and the required number of hair grafts accurately. Comparing our estimations to actual measurements, our method shows errors ranging from -15% to +25%, whereas estimations provided by hair clinics range from -35% to +18%. This highlights the superior accuracy of our individual-specific estimations compared to the general guidelines found on internet sources, enabling a more precise cost estimate for patients.
Similar content being viewed by others
Data availability
All measurements used in calculation were collected by the authors. The computer specifications used in this study are provided in the Appendix. All codes used in the study are written in Python, specifically Version 3.10.11. The libraries used include: NumPy version 1.25.0; OpenCV version 4.7.0; MediaPipe version 0.9.3.0; Matplotlib version 3.4.3; Plotly version 5.14.1; Open3D version 0.17.0; Scipy version 1.10.1; PyTorch version 2.0.1; Torchvision version 0.15.2 + cpu. The datasets generated and/or analysed during the current study are available from the corresponding author on reasonable request.
References
American Academy of Dermatology Association, https://www.aad.org/public/diseases/hair-loss/causes/18-causes, [Online]. Available: https://www.aad.org/public/diseases/hair-loss/causes/18-causes. Accessed 26 June 2023
Salman KE, Altunay IK, Kucukunal NA, Cerman AA (2017) Frequency, severity and related factors of androgenetic alopecia in dermatology outpatient clinic: hospital-based cross-sectional study in Turkey. An Bras Dermatol 92(1):35–40
Walter K (2022) Common causes of hair loss. JAMA 328(7):686
Anastassakis K (2023) Androgenetic Alopecia From A to Z, 1 ed. Springer, Cham, p 340
Chen S, Xie X, Zhang G, Zhang Y (2022) Comorbidities in androgenetic alopecia: a comprehensive review. Dermatol Ther (Heidelb) 12:2233–2247
FACT.MR (2023) https://www.globenewswire.com/news-release/2023/02/15/2608929/0/en/Hair-Transplant-Market-Is-Expected-To-Register-Growth-at-a-CAGR-Of-12-7-by-2033-Fact-Mr-Study.html, Rockville
UPGUYS Editorial Team (2020) https://upguys.com/blog/receding-hairline-seven-stages, 5 April 2020. [Online]. Available: https://upguys.com/blog/receding-hairline-seven-stages. Accessed 26 June 2023
Hwang D-Y, Choi S-H, Shin J, Kim M, Choi Y-H (2021) GAN-based ROI image translation method for predicting image after hair transplant surgery. Electronics 10:3066
Kim M, Kang S, Lee B-D (2022) Evaluation of automated measurement of hair density using deep neural networks. Sensors 22:650
Lin Y, Shen J, Wang Y, Pantic M (2021) RoI Tanh-polar transformer network for face parsing in the wild. J Image Vis Comput 112:104190
Lee C-H, Liu Z, Wu L, Luo P (2020) MaskGAN: Towards diverse and interactive facial image manipulation. In: 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Seattle, pp 5549–5558
Lugaresi C, Tang J, Nash H, McClanahan C, Uboweja E, Hays M, Zhang F, Chang C-L, Yong MG, Lee J, Chang W-T, Hua W, Georg M, Grundmann M (2019) MediaPipe: a framework for perceiving and processing reality. In: Third Workshop on Computer Vision for AR/VR at IEEE Computer Vision and Pattern Recognition (CVPR), California. https://mixedreality.cs.cornell.edu/s/NewTitle_May1_MediaPipe_CVPR_CV4ARVR_Workshop_2019.pdf
Wang Z, Li Y, Zhang H, Shan Y (2021) Towards real-world blind face restoration with generative facial prior. In: 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), Nashville, pp 9168–9178
Liu Y, Shi H, Shen H, Si Y, Wang X, Mei T (2020) A new dataset and boundary-attention semantic segmentation for face parsing. In: The thirty-fourth AAAI Conference on Artificial Intelligence (AAAI-20), vol 34. New York, pp 11637–11644
Li Z, Cao L, Wang H, Xu L (2022) A masked self-supervised pretraining method for face parsing. Mathematics 10:2002
Yu C, Gao C, Wang J, Yu G, Shen C, Sang N (2021) BiSeNet V2: bilateral network with guided aggregation for real-time semantic segmentation. Int J Comput Vis 129:3051–3068
Tsai T-H, Tseng Y-W (2023) BiSeNet V3: Bilateral segmentation network with coordinate attention for real-time semantic segmentation. Neurocomputing 532:33–42
Ahmad M, Mohmand MH (2018) Hairline designing: a wall mirror—a simple solution of a critical problem. Am J Cosmet Surg 35(2):56–58
Ahmad M (2020) The first hair transplant assessment scale: parameters for good hair transplantation. J Cosmet Med 4(1):1–6
Hair Palace, https://www.hairpalace.co.uk/hair-loss/hairline/, [Online]. Available: https://www.hairpalace.co.uk/hair-loss/hairline/. Accessed 26 June 2023
Kim HJ, Baek JH, Lim YR, Kim JH, Yang SM, Koh JS, Oh S, Shin MK (2023) An analysis of shapes and location of anterior hairline in Asian men. Arch Dermatol Res 315:1233–1239
Moulton R https://moultano.wordpress.com/2013/08/09/logs-tails-long-tails/, [Online]. Available: https://moultano.wordpress.com/2013/08/09/logs-tails-long-tails/. Accessed 26 June 2023
Ngeow WC, Akan A, George JM (2006) The intercanthal and interpupillary distances in KadazanDusun in Malaysia. Malaysian J Oral Maxillofac Surg 4(1):8–11
Hickson-Curran S, Brennan NA, Igarashi Y, Young G (2014) Comparative evaluation of Asian and White ocular topography. Optom Vis Sci 91(12):1396–1405
Alsaqr A, Fagehi R, Sharha AA, Alkhudair M, Alshabrami A, Muammar AB, Abdulwahed S, Alshehri A (2021) Ethnic differences of corneal parameters: a cross-sectional study. Open Ophthalmol J 15:13–20
ABB Optical Group, https://www.abboptical.com/hvid-measurements, [Online]. Available: https://www.abboptical.com/hvid-measurements. Accessed 26 June 2023
MacGabhann A https://www.visiondirect.com.au/optical-centre/prescription/pupillary-distance/, 28 March 2023. [Online]. Available: https://www.visiondirect.com.au/optical-centre/prescription/pupillary-distance/. Accessed 26 June 2023
Topsakal O, Sawyer P, Akinci TC, Celikoyar MM (2023) Algorithms to measure area and volume on 3D face models for facial surgeries. IEEE Access 11:39577–39585
Heva Clinic, https://www.dentalhairclinicturkey.com/blog/what-is-hair-graft/, [Online]. Available: https://www.dentalhairclinicturkey.com/blog/what-is-hair-graft/. Accessed 26 June 2023
Acknowledgements
Special thanks to Mr. Vatchara R. and Mr. Tawatchai S. for serving as our models, allowing us to collect measurements.
Funding
No funds, grants, or other support was received for conducting this study.
Author information
Authors and Affiliations
Contributions
All authors contributed equally.
Corresponding author
Ethics declarations
Conflicts of interest
No conflict of interest to declare.
Additional information
Publisher's note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Appendix: Computer specifications
Appendix: Computer specifications
-
(1)
Processor: Intel(R) Core(TM) i5-8300H CPU @ 2.30 GHz, GPU Device name: NVIDIA GeForce GTX 1050; RAM: 24 GB; Disk: 500 GB; OS: Windows 11 Home Single Language.
-
(2)
Processor: AMD Ryzen 7 5800H with Radeon Graphics 3.20 GHz.; GPU Device name: NVIDIA GeForce RTX 3070 8 GB, RAM: 32 GB, Disk: 1 TB; OS: Windows 11 Home Single Language
-
(3)
Processor: AMD Ryzen 7 3700X 8-Core Processor 3.60 GHz; GPU Device name: AMD Radeon RX5700XT 8 GB; RAM: 16 GB; Disk: 1 TB; OS: Windows 11 Home
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Sinlapanurak, S., Peerasantikul, K., Phongvichian, N. et al. Hair transplant assessment in Asian men with receding hairlines using images and computer vision techniques. Multimed Tools Appl (2024). https://doi.org/10.1007/s11042-024-18619-9
Received:
Revised:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11042-024-18619-9