Visualizing veins from color skin images using convolutional neural networks

Abstract

Intravenous cannulation is the most important phase in medical practices. Currently, limited literature is available about visibility of veins and the characteristics of patients associated with difficult intravenous access. In modern medical treatment, a major challenge is locating veins for patients who have difficult venous access. Presently, some products of vein locators are available in the market to improve vein access, but they need auxiliary equipment such as near infrared (NIR) illumination and camera, which add weight and cost to the devices, and cause inconveniences to daily medical care. In this paper, a vein visualization algorithm based on the deep learning method was proposed. Based on a group of synchronous RGB/NIR arm images, a convolutional neural network (CNN) model was designed to implement the mapping from RGB to NIR images, where veins can be detected from skin. The model has a simple structure and less optimization parameters. A color transfer scheme was also proposed to make the network adaptive to the images taken by smartphone in daily medical treatments. Comprehensive experiments were conducted on three datasets to evaluate the proposed method. Subjective and objective evaluations showed the effectiveness of the proposed method. These results indicated that the deep learning-based method can be used for visualizing veins in medical care applications.

Keywords

• intravenous cannulation
• vein visualization
• convolutional neural network