Performance Evaluation of Dorsal Vein Network of Hand Imaging Using Relative Total Variation-Based Regularization for Smoothing Technique in a Miniaturized Vein Imaging System: A Pilot Study

Abstract

Vein puncture is commonly used for blood sampling, and accurately locating the blood vessel is an important challenge in the field of diagnostic tests. Imaging systems based on near-infrared (NIR) light are widely used for accurate human vein puncture. In particular, segmentation of a region of interest using the obtained NIR image is an important field, and research for improving the image quality by removing noise and enhancing the image contrast is being widely conducted. In this paper, we propose an effective model in which the relative total variation (RTV) regularization algorithm and contrast-limited adaptive histogram equalization (CLAHE) are combined, whereby some major edge information can be better preserved. In our previous study, we developed a miniaturized NIR imaging system using light with a wavelength of 720-1100 nm. We evaluated the usefulness of the proposed algorithm by applying it to images acquired by the developed NIR imaging system. Compared with the conventional algorithm, when the proposed method was applied to the NIR image, the visual evaluation performance and quantitative evaluation performance were enhanced. In particular, when the proposed algorithm was applied, the coefficient of variation was improved by a factor of 15.77 compared with the basic image. The main advantages of our algorithm are the high noise reduction efficiency, which is beneficial for reducing the amount of undesirable information, and better contrast. In conclusion, the applicability and usefulness of the algorithm combining the RTV approach and CLAHE for NIR images were demonstrated, and the proposed model can achieve a high image quality.

Keywords: adaptive smoothing technique; development of miniaturized vein imaging system; near-infrared image; performance evaluation of image quality; relative total variation.

Figure 1

(a) Schematic of the developed vein viewer system configuration; (b) photograph of the system.

Figure 2

Flowchart describing the application of the proposed dorsal vein recognition framework to a near infrared (NIR) image.

Figure 3

Vein segmentation images (top) of the left hand for an 850-nm NIR image (none ①), the median filter (②), the Wiener filter (③), and the proposed relative total variation (RTV) regularization-based smoothing algorithm (④), which were acquired using our established miniaturized vein imaging system and the synthesized images of blending them with a light image (bottom).

Figure 4

Experimental results for the coefficient of variation (COV) factors of the segmentation image under four conditions: none (①), the median filter (②), the Wiener filter (③), and the proposed filter (④). The COV was calculated for the specified regions A to D in the yellow-box regions in Figure 3. The regions of interest (ROIs) were set as boxes A to D because these parts quantitatively determined the amount of additional noise relative to the manicured vein. The average COV factors of image-processing methods ①to ④ were 0.86, 0.60, 0.35, and 0.05, respectively.

Figure 5

Examples of vein segmentation images (top) of the right hand for a 940-nm NIR image (none (①), the median filter (②), the Wiener filter (③), and the proposed filter (④) and the fusion images with the vein image on the top (bottom). These results exhibited a similar tendency to those for the 850-nm NIR image and the vessel extraction results, indicating that excellent visibility can be obtained using the proposed algorithm.

Figure 6

Intensity profiles (for line AB in Figure 5) for different smoothing methods applied to the acquired NIR image.