Corpus ID: 235212568

VeniBot: Towards Autonomous Venipuncture with Automatic Puncture Area and Angle Regression from NIR Images

@inproceedings{Cao2021VeniBotTA,
  title={VeniBot: Towards Autonomous Venipuncture with Automatic Puncture Area and Angle Regression from NIR Images},
  author={Xuechun Cao and Zijie Chen and Bolin Lai and Yuxuan Wang and Yu Chen and Zhe Cao and Zhilin Yang and Nanyang Ye and Junbo Zhao and Xiao-Yun Zhou and Peng Qi},
  year={2021}
}
Venipucture is a common step in clinical scenarios, and is with highly practical value to be automated with robotics. Nowadays, only a few on-shelf robotic systems are developed, however, they can not fulfill practical usage due to varied reasons. In this paper, we develop a compact venipucture robot — VeniBot, with four parts, six motors and two imaging devices. For the automation, we focus on the positioning part and propose a Dual-In-Dual-Out network based on two-step learning and two-task… Expand

References

SHOWING 1-10 OF 22 REFERENCES
Artery-vein segmentation in fundus images using a fully convolutional network
TLDR
A novel application of the U-Net semantic segmentation architecture (based on FCNs) on the discrimination of arteries and veins in fundus images is presented, and results are obtained that exceed accuracies reported in the literature. Expand
Deep learning robotic guidance for autonomous vascular access
TLDR
A portable robotic device capable of introducing needles and catheters into deformable tissues such as blood vessels to draw blood or deliver fluids autonomously is presented and the potential for autonomous systems to outperform humans on complex visuomotor tasks is suggested. Expand
U-Net: Convolutional Networks for Biomedical Image Segmentation
TLDR
It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Expand
Normalization in Training U-Net for 2-D Biomedical Semantic Segmentation
TLDR
Four normalization methods—BN, IN, LN, and GN are compared in details, specifically for 2-D biomedical semantic segmentation and results show that detailed subdivision of the feature map, i.e., GN with a large group number or IN, achieves higher accuracy. Expand
Efficient multi‐scale 3D CNN with fully connected CRF for accurate brain lesion segmentation
TLDR
An efficient and effective dense training scheme which joins the processing of adjacent image patches into one pass through the network while automatically adapting to the inherent class imbalance present in the data, and improves on the state-of-the‐art for all three applications. Expand
3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
TLDR
The proposed network extends the previous u-net architecture from Ronneberger et al. by replacing all 2D operations with their 3D counterparts and performs on-the-fly elastic deformations for efficient data augmentation during training. Expand
Vascular access in COVID-19 patients: Smart decisions for maximal safety
TLDR
In the experience of the vascular access team of the hospital, hit by the COVID epidemic in March 2020, the safety of both the patient and the staff can be ensured by an insertion bundle of few smart strategies. Expand
Phlebotomy-Related Lateral Antebrachial Cutaneous Nerve Injury
TLDR
This is the first case in which electrodiagnostic studies were used to document venipuncture-related injury of the lateral antebrachial cutaneous nerve and specific electro Diagnostic testing is used to definitively diagnose this rare injury and to track recovery. Expand
Vascular Access Management 1: An Overview
TLDR
Cannulation of the vascular access requires on the part of the nephrology nurse, clinical expertise and knowledge on the management of different types of vascular access including different cannulation techniques. Expand
Incidence, severity and risk factors of peripheral intravenous cannula-induced complications: An observational prospective study.
TLDR
The incidence of infiltration, occlusion and dislodgment is almost congruent with the average incidence of previous studies, however, the incidence and degree of severity associated with the occurrence of phlebitis were significantly higher. Expand
...
1
2
3
...