Machine Learning for Detection of Correct Peripherally Inserted Central Catheter Lines and Tips Position from NICU Radiology


In critically ill infants, the position of a peripherally inserted central catheter (PICC) must be confirmed frequently, as the tip may move from its original position and run the risk of hyperosmolar vascular damage or extravasation into surrounding spaces. Automated detection of PICC lines and tips position holds great promise for alerting bedside clinicians to non-central PICCs. This research seeks to use natural language processing (NLP) [1], image processing [2] with machine learning (ML) techniques to predict, and segment PICC lines and tips positions based on text analysis of radiograph reports, and corresponding X-ray imaging data.

NLP: Detection of correct PICC tip positions from unstructured radiology reports

Check-out our website :


M. Shah, D. Shu, V. B. S. Prasath, Y. Ni, A. Schapiro, K. Dufendach. Machine learning for detection of correct peripherally inserted central catheter tip position from radiology reports in infants. Applied Clinical Informatics, 12(04), 856-863, August 2021. doi:10.1055/s-0041-1735178

Please see our related PICCLineNet project: Detection of correct PICC lines and tip positions from X-ray images

Segmentation of PICC lines and tip localization with deep learning - TBA

PICCLineNet - Initial Results

Deoghare et al., PICCLineNet: Deep learning for detecting peripherally inserted central catheter (PICC) lines and tips from radiological images in infants. In preparation, 2023. Preliminary version at arXiv:23xx.abcde.