An automatic needle insertion method combining a blood flow optimization model with a neural network
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- ZHEJIANG UNIV
- Filing Date
- 2023-05-26
- Publication Date
- 2026-07-24
AI Technical Summary
In existing technologies, medical staff have difficulty accurately locating veins or arteries, leading to delays in rescue time and multiple unnecessary needle insertions that cause pain and infection risks, especially when the subcutaneous fat and muscle layers are thick or the hair is dense.
By combining a blood flow optimization model with a neural network, the system automatically scans blood flow feedback signals using the Doppler ultrasound principle, calculates the location of blood vessels and the distribution of blood flow velocity, and uses a neural network to determine the optimal insertion point and angle, simulating professional insertion techniques to achieve automatic insertion.
It increases the survival rate of self-rescue and first aid in environments lacking professional personnel, avoids the pain of multiple injections, and the device is small, lightweight, and easy to carry.
Smart Images

Figure CN116584974B_ABST