Abstract
Assessing the condition and visibility of veins is a crucial step before obtaining intravenous access in the antecubital fossa, which is a common procedure to draw blood or administer intravenous therapies (IV therapies). Even though medical practitioners are highly skilled at intravenous cannulation, they usually struggle to perform the procedure in patients with low visible veins due to fluid retention, age, overweight, dark skin tone, or diabetes. Recently, several investigations proposed combining Near Infrared (NIR) imaging and deep learning (DL) techniques for forearm vein segmentation. Although they have demonstrated compelling results, their use has been rather limited owing to the portability and precision needs to perform venipuncture. In this paper, we aim to contribute in bridging this gap using three strategies. First, we introduce a new NIR-based forearm vein segmentation dnataset of 2016 labelled images collected from 1008 subjects with low visible veins. Second, we propose a modified U-Net architecture that locates veins specifically in the antecubital fossa region of the examined patient. Finally, a compressed version of the proposed architecture was deployed inside an bespoke, portable vein finder device after testing four common embedded microcomputers and four common quantization modalities. Experimental results showed that the model compressed with Dynamic Range Quantization and deployed on a Raspberry Pi 4B card produced the best execution time and precision balance, with 5.14 FPS and 0.957 of latency and Intersection over Union (IoU), respectively. These results show promising performance inside a resource-restricted low-cost device. The full implementation and data are available at: https://github.com/EdwinTSalcedo/CUBITAL
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Adi Surya Gunawan, I.P., Sigit, R., Gunawan, A.I.: Vein visualization system using camera and projector based on distance sensor. In: 2018 International Electronics Symposium on Engineering Technology and Applications (IES-ETA), pp. 150–156. arXiv, Berlin, October 2018. https://doi.org/10.1109/ELECSYM.2018.8615501
Ai, D., et al.: Augmented reality based real-time subcutaneous vein imaging system. Biomed. Opt. Express. 7(7), 2565–2585 (2016). https://doi.org/10.1364/BOE.7.002565, https://opg.optica.org/boe/abstract.cfm?URI=boe-7-7-2565
Azueto, R., Santiago, G., Hernández, G., Hernández, S.: Implementación de un sistema de imagenología infrarroja para la detección vascular del antebrazo y mano. Revista Mexicana de Ingeniería Biomédica. 1(1), 27–35 (2017). https://www.redalyc.org/articulo.oa?id=61950989005
Chen, Y., et al.: VeniBot: towards autonomous venipuncture with semi-supervised vein segmentation from ultrasound images. In: Arxiv, pp. 150–156. arXiv, Berlin (2021)
Company, A.: Comparing the accuvein av500 vs veinsight vs500 vs aimvein pro 2.0 (2022). https://aimvein.com/blogs/news/compare-model-av500-vs-vs500-vs-pro-2-0
Corzo Gómez, E.G., Gómez Díaz, O.L., Niño Mantilla, M.E., Ramírez Vargas, L.M., Zárate Sierra, L.M.: Distribución de los patrones venosos de la fosa cubital en una muestra de personas nacidas en el departamento de santander, colombia. Int. J. Morphol. 32(1), 221–226 (2014). https://doi.org/10.4067/s0717-95022014000100037
Francisco, M.D., et al.: Competitive real-time near infrared (NIR) vein finder imaging device to improve peripheral subcutaneous vein selection in venipuncture for clinical laboratory testing. Micromachines 12(4), 27–35 (2021). https://doi.org/10.3390/mi12040373
Fronheiser, M.P., et al.: Real-time optoacoustic monitoring and three-dimensional mapping of a human arm vasculature. J. Biomed. Opt. 15(2), 21305 (2010). https://doi.org/10.1117/1.3370336
Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2017). https://doi.org/10.1109/cvpr.2017.632
Kuthiala, A., et al.: U-DAVIS-deep learning based arm venous image segmentation technique for venipuncture. Comput. Intell. Neurosci. 2022, 4559219 (2022). https://doi.org/10.1155/2022/4559219
Lee, J., Jeong, I., Kim, K., Cho, J.: Design and implementation of embedded-based vein image processing system with enhanced denoising capabilities. Sensors 22(21), 887 (2022). https://doi.org/10.3390/s22218559
Leipheimer, J., Balter, M., Chen, A., Yarmush, M.: Design and evaluation of a handheld robotic device for peripheral catheterization. J. Med. Dev. 16(2), 021015 (2022). https://doi.org/10.1115/1.4053688
Li, Y., et al.: A novel method for low-contrast and high-noise vessel segmentation and location in venipuncture. IEEE Trans. Med. Imaging 36(11), 2216–2227 (2017). https://doi.org/10.1109/TMI.2017.2732481
Naik, V., Mantha, S.P., Rayani, B.: Vascular access in children. Indian J. Anaesth. 63(9), 737 (2019)
Ng, K.W., Furqan, M.S., Gao, Y., Ngiam, K.Y., Khoo, E.T.: Holovein: mixed-reality venipuncture aid via convolutional neural networks and semi-supervised learning. Electronics. 12(2), 292 (2023). https://doi.org/10.3390/electronics12020292, https://www.mdpi.com/2079-9292/12/2/292
Rojas, W., Salcedo, E., Sahonero, G.: ADRAS: airborne disease risk assessment system for closed environments. In: Lossio-Ventura, J.A., Valverde-Rebaza, J., Díaz, E., Alatrista-Salas, H. (eds.) Information Management and Big Data, vol. 1837, pp. 96–112. Springer Nature Switzerland, Cham (2023). https://doi.org/10.1007/978-3-031-35445-8_8
Shah, Z., et al.: Deep learning-based forearm subcutaneous veins segmentation. IEEE Access 10, 42814–42820 (2022). https://doi.org/10.1109/ACCESS.2022.3167691
Shahzad, A., Walter, N., Malik, A.S., Saad, N.M., Meriaudeau, F.: Multispectral venous images analysis for optimum illumination selection. In: 2013 IEEE International Conference on Image Processing, pp. 2383–2387. ICIP, Berlin, September 2013. https://doi.org/10.1109/ICIP.2013.6738491
Tang, C., Xia, S., Qian, M., Wang, B.: Deep learning-based vein localization on embedded system. IEEE Access 9, 27916–27927 (2021). https://doi.org/10.1109/ACCESS.2021.3058014
Yildiz, M.Z., Boyraz, Ö.F.: Development of a low-cost microcomputer based vein imaging system. Infrared Phys. Technol. 98, 27–35 (2019). https://doi.org/10.1016/j.infrared.2019.02.010
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Salcedo, E., Peñaloza, P. (2024). Edge AI-Based Vein Detector for Efficient Venipuncture in the Antecubital Fossa. In: Calvo, H., Martínez-Villaseñor, L., Ponce, H. (eds) Advances in Soft Computing. MICAI 2023. Lecture Notes in Computer Science(), vol 14392. Springer, Cham. https://doi.org/10.1007/978-3-031-47640-2_24
Download citation
DOI: https://doi.org/10.1007/978-3-031-47640-2_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-47639-6
Online ISBN: 978-3-031-47640-2
eBook Packages: Computer ScienceComputer Science (R0)