Forearm vein pattern extraction algorithm based on double range image subtraction

Modern laboratory diagnostics often require venipuncture. This can be difficult when veins are not visible. This may lead to errors in blood collection, multiple puncture attempts, and patient discomfort. Optical methods in medicine are developing rapidly. Vein visualization in the near-infrared (NIR) range is a promising direction. It is based on differences in absorption and scattering of IR radiation by blood hemoglobin and surrounding tissues. However, existing vein visualization methods have limitations. These include shallow visualization depth, low contrast, and a lack of standardized device parameters. Furthermore, current research does not focus enough on vessel segmentation. This limits the use of digital image processing algorithms. This work proposes a vein visualization method using dual-band image registration (532 nm + 850 nm) and computer vision algorithms. Using two spectral ranges allows automatic vessel segmentation on the image. This supports the doctor's decision on vein selection for puncture by combining information from both channels. Existing image processing approaches for vein visualization were reviewed. An image processing algorithm was developed. It includes preprocessing, channel alignment, vessel enhancement, and segmentation mask creation. An evaluation approach using Recall and Dice Similarity Index (DSI) metrics is proposed. Experimental modeling showed that the proposed algorithm achieves high Recall (up to 0.95) with a low DSI value (up to 0.35). The solution can be used as a decision support tool in real medical practice. It can also be used for training medical personnel.

1. Remizov N.V., Bataeva E.M., Stramousov D.P., et al. 3D Printed Modular Vein Viewing System Based on Differential Light Absorption in the Near Infrared Range. Journal of Biomedical Photonics & Engineering. 2023;9(2):20307. https://doi.org/10.18287/JBPE23.09.020307

2. Remizov N.V., Yakimenko D.S., Artemyev D.N. NIR Imaging: Development of Digital Image Processing Algorithm for Vein Contrast Enhancement. Journal of Biomedical Photonics & Engineering. 2025;11(2):020309. https://doi.org/10.18287/JBPE25.11.020309

3. Francisco M.D., Chen W.-F., Pan Ch.-T., 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. 2021;12(4):373. https://doi.org/10.3390/mi12040373

4. Abd Rahman A.B., Juhim F., Chee F.P., et al. Near Infrared Illumination Optimization for Vein Detection: Hardware and Software Approaches. Applied Sciences. 2022;12(21):11173. https://doi.org/10.3390/app122111173

5. Vt G. A novel design proposal for low-cost vein-viewer for medical and non-contact biometric applications using NIR imaging. Journal of Medical Engineering & Technology. 2021;45(4):303–312. https://doi.org/10.1080/03091902.2021.1895898

6. Sharma N., Hefeeda M. Hyperspectral reconstruction from RGB images for vein visualization. In: Proceedings of the 11th ACM Multimedia Systems Conference (MMSys 2020), 08–11 June 2020, Istanbul, Turkey. New York: ACM; 2020. P. 77–87. https://doi.org/10.1145/3339825.3391861

7. Ozkan H., Aydin M., Ozcan O.A., et al. A portable multispectral vein imaging system. Journal of Electrical Engineering. 2023;74(1):64–69. https://doi.org/10.2478/jee-2023-0008

8. Hamza M., Skidanov R., Podlipnov V. Visualization of Subcutaneous Blood Vessels Based on Hyperspectral Imaging and Three-Wavelength Index Images. Sensors. 2023;23(21):8895. https://doi.org/10.3390/s23218895

9. May H.Y., Ernawan F. Real Time Vein Visualization using Near-Infrared Imaging. In: 2020 International Conference on Computational Intelligence (ICCI), 08–09 October 2020, Bandar Seri Iskandar, Malaysia. IEEE; 2020. P. 276–280. https://doi.org/10.1109/ICCI51257.2020.9247732

10. Song J.H., Kim Ch., Yoo Y. Vein Visualization Using a Smart Phone With Multispectral Wiener Estimation for Point-of-Care Applications. IEEE Journal of Biomedical and Health Informatics. 2015;19(2):773–778. https://doi.org/10.1109/JBHI.2014.2313145

11. Francis M., Jose A., Devadhas G.G., et al. A novel technique for forearm blood vein detection and enhancement. Biomedical Research. 2017;28(7):2913–2919.

12. Maray A.H., Hasan S.Q., Mohammed N.L. Design and implementation of low-cost vein-viewer detection using near infrared imaging. Indonesian Journal of Electrical Engineering and Computer Science. 2023;29(2):1039–1046. https://doi.org/10.11591/ijeecs.v29.i2.pp1039-1046

13. Chekanov K., Danko D., Tlyachev T., et al. State-of-the-Art in Skin Fluorescent Photography for Cosmetic and Skincare Research: From Molecular Spectra to AI Image Analysis. Life. 2024;14(10):1271. https://doi.org/10.3390/life14101271

14. Du P., Liu S., Gamba P., et al. Fusion of Difference Images for Change Detection Over Urban Areas. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2012;5(4):1076–1086. https://doi.org/10.1109/JSTARS.2012.2200879