Infusion port level detection for intravenous infusion based on Yolo v3 neural network

Purpose: In order to improve the accuracy of liquid level detection in intravenous left auxiliary vein infusion and reduce the pain of patients with blood returning from intravenous infusion, we propose a deep learning based liquid level detection model of infusion levels to facilitate this operation. Method: We implemented a Yolo v3 -based detection model of infusion level images in intravenous infusion, and at the same time, compare it with SURF image processing technique, RCNN, and Fast-RCNN methods. Results: The model in this paper is better than the comparison algorithm in Intersection over Union (IoU), precision, recall and test time. The liquid level detection model based on Yolo v3 has a precision of 0.9768, a recall rate of 0.9688, an IoU of 0.8943, and a test time of 2.9 s. Conclusion: The experimental results prove that the liquid level detection method based on deep learning has the characteristics of high accuracy and good real-time performance. This method can play a certain auxiliary role in the hospital environment and improve work efficiency of medical workers.

Automated summary

This paper proposes a liquid level detection model based on deep learning to improve the accuracy of intravenous infusion liquid level detection, reduce patient pain, and demonstrates high precision and real-time performance in experiments.