A Near-Infrared Imaging System for Robotic Venous Blood Collection
Zhikang Yang, Mao Shi, Yassine Gharbi, Qian Qi, Huan Shen, Gaojian Tao, Wu Xu, Wenqi Lyu, Aihong Ji · 2024
Read A Near-Infrared Imaging System for Robotic Venous Blood Collection by Zhikang Yang, Mao Shi, Yassine Gharbi, Qian Qi, Huan Shen, Gaojian Tao, Wu Xu, Wenqi Lyu, Aihong Ji (2024) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/pmc-11598678.txt.
Description
Zhikang Yang and eight co-authors built a near-infrared vein imaging system for robot blood draws in a 2024 paper. A robot's success starts with seeing the vein clearly. The team tuned imaging settings by simulation, then trained a segmentation network that grafts residual blocks into a U-shaped design.
Self-taught pretraining let the network learn from few labeled images. Against the plain U-shaped net, the hybrid cut loss and boundary error while raising overlap scores by wide margins. A smarter stereo matching method, with weights that vary by region, cut its average error by about a quarter. The authors plan to wire the system into a full robotic blood collection rig for live puncture guidance.
Catalog record
| CREATOR | Zhikang Yang, Mao Shi, Yassine Gharbi, Qian Qi, Huan Shen, Gaojian Tao, Wu Xu, Wenqi Lyu, Aihong Ji |
|---|---|
| YEAR | 2024 |
| COLLECTION | PAPERS |
| FORMAT | TXT |
| FILE SIZE | 31 KB |
| VERSION | 1.0 |
| LICENSE | CC BY 4.0 |
| RIGHTS | CC BY |
| SOURCE | Europe PMC |