Related Experiment Video
Updated: May 3, 2026
Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
Published on: May 19, 2023
Topology preserving embedded network for PICC segmentation in pediatric X ray images
Xi Yin1, Kai Cheng2, Zipeng Chen1
1Department of Radiology, First Affiliated Hospital of Shihezi University, Shihezi, China.
Insights
TopNet accurately segments peripherally inserted central catheters (PICCs) in pediatric patients. This AI tool precisely localizes PICC tips, improving safety for infants and toddlers receiving long-term infusions.
Area of Science:
- Medical Imaging
- Artificial Intelligence in Medicine
- Pediatric Interventional Radiology
Background:
- Peripherally inserted central catheters (PICCs) are vital for pediatric long-term infusions.
- Optimal PICC tip placement is crucial but challenging in infants and toddlers due to small anatomy and imaging difficulties.
- Current automated methods fail to accurately segment PICCs in pediatric populations.
Purpose of the Study:
- To develop and validate an automated segmentation network for PICC placement in pediatric patients.
- To improve the precision of PICC tip localization in neonates, infants, and toddlers.
- To address the limitations of existing adult-focused segmentation algorithms in pediatric imaging.
Main Methods:
- Retrospective collection of 1184 PICC cases, including 280 pediatric patients (neonates, infants, toddlers).
- Development of TopNet, a novel topology-preserving embedded network for automated PICC segmentation.
- Quantitative and qualitative evaluations using internal and external validation datasets.
Main Results:
- TopNet demonstrated superior performance in segmenting PICCs in pediatric patients compared to existing methods.
- The network achieved precise tip localization even under challenging imaging conditions.
- Both internal and external validation confirmed the robustness and accuracy of TopNet.
Conclusions:
- TopNet offers a reliable solution for automated PICC segmentation and tip localization in pediatric patients.
- This technology has the potential to enhance patient safety and reduce complications associated with PICC placement in vulnerable young populations.
- Further integration of TopNet can improve diagnostic accuracy and workflow efficiency in pediatric interventional radiology.
Abstract:
Peripherally inserted central catheters (PICCs) are essential for long-term infusion in vulnerable pediatric patients. Optimal tip placement in the lower third of the superior vena cava or at the cavoatrial junction is critical to prevent serious complications. Verifying correct tip position in infants and toddlers is challenging because of very small anatomic target zones, non-standard radiograph acquisition, interference from other devices, low contrast, and high risk of catheter migration. Existing automated segmentation methods, mostly developed for adults, perform poorly on pediatric images. We retrospectively collected 1184 PICC patients from three medical centers, including 280 pediatric cases (210 neonates, 46 infants, 24 toddlers), with appropriate ethical approval. We introduce TopNet, a topology-preserving embedded network designed for automated PICC segmentation in pediatric patients. TopNet maintains catheter continuity and enables precise tip localization under difficult conditions. Quantitative and qualitative evaluations show superior segmentation and tip localization on both internal and external validation.
