An Automatic Vein Detection System Using Deep Learning for Intravenous (IV) Access Procedure

Intravenous (IV) access is a common and yet important daily clinical procedure that delivers fluids or medication into a patient’s vein. However, IV insertion is very challenging where clinicians are suffering in locating the subcutaneous vein due to patients’ physiological factors such as hairy forearm and thick dermis fat, and also medical staff’s level of fatigue. As a result, the patients are suffering from multiple IV insertions and the problem has not yet been resolved till-date. Thus, researchers have proposed an autonomous machine for IV access, but such equipment is lack of an artificial intelligence (AI) algorithm in detecting the vein accurately. Therefore, this project proposes an automatic vein detection algorithm using deep learning for Intravenous (IV) access purposes. U-Net, a fully connected network (FCN) architecture is employed in this project due to its capability in detecting the near-infrared (NIR) subcutaneous vein. In our experiment, data augmentation is applied to increase the dataset size and reduce the bias from overfitting. The original U-Net architecture is optimized by replacing up-sampling with transpose convolution as well as the additional implementation of batch normalization. Lastly, the proposed algorithm has achieved an accuracy and specificity of 0.9909 and 0.9970, respectively. This result indicates that the proposed algorithm can be applied into the venipuncture machine to locate the Subcutaneous vein for intravenous (IV) procedures.