Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

CDK2 Inhibition Exerts RB-Independent Antitumor Activity in CDK4/6 Inhibitor-Resistant HR+/HER2- Breast Cancer.

Cancer research·2026
Same author

Accuracy and Variability of Spatial Localization of Infarct Core Predicted by CT Perfusion.

Journal of computer assisted tomography·2026
Same author

Imaging, Management, and Treatment of Orbital Trauma.

Radiologic clinics of North America·2026
Same author

OMAMA-DB: the Oregon-Massachusetts Mammography Database.

Journal of medical imaging (Bellingham, Wash.)·2026
Same author

Detecting and Mitigating Bias for Inclusive and Trustworthy Clinical Research: A Scientific Statement From the American Heart Association.

Circulation. Genomic and precision medicine·2026
Same author

Correction: League of Radiologists-an End-to-End AI Framework for Scalable and Gamified Radiology Education: A Pilot Implementation in Chest Radiography.

Journal of imaging informatics in medicine·2026

Related Experiment Video

Updated: Feb 21, 2026

Magnetically-Assisted Remote Controlled Microcatheter Tip Deflection under Magnetic Resonance Imaging
11:27

Magnetically-Assisted Remote Controlled Microcatheter Tip Deflection under Magnetic Resonance Imaging

Published on: April 4, 2013

12.9K

A Deep-Learning System for Fully-Automated Peripherally Inserted Central Catheter (PICC) Tip Detection.

Hyunkwang Lee1, Mohammad Mansouri1, Shahein Tajmir1

  • 1Department of Radiology, Massachusetts General Hospital, 25 New Chardon Street, Suite 400B, Boston, MA, 02114, USA.

Journal of Digital Imaging
|October 7, 2017
PubMed
Summary

A new AI system accurately detects peripherally inserted central catheter (PICC) tip location using deep learning. This automated approach aims to reduce diagnostic delays and improve patient safety by confirming PICC placement faster.

Keywords:
Chest radiographComputer-aided detectionDeep learningMachine learningPICCRadiology workflow

More Related Videos

Remote Magnetic Navigation for Accurate, Real-time Catheter Positioning and Ablation in Cardiac Electrophysiology Procedures
09:13

Remote Magnetic Navigation for Accurate, Real-time Catheter Positioning and Ablation in Cardiac Electrophysiology Procedures

Published on: April 21, 2013

28.5K
Three-Dimensional Ultrasonic Needle Tip Tracking with a Fiber-Optic Ultrasound Receiver
04:33

Three-Dimensional Ultrasonic Needle Tip Tracking with a Fiber-Optic Ultrasound Receiver

Published on: August 21, 2018

10.9K

Related Experiment Videos

Last Updated: Feb 21, 2026

Magnetically-Assisted Remote Controlled Microcatheter Tip Deflection under Magnetic Resonance Imaging
11:27

Magnetically-Assisted Remote Controlled Microcatheter Tip Deflection under Magnetic Resonance Imaging

Published on: April 4, 2013

12.9K
Remote Magnetic Navigation for Accurate, Real-time Catheter Positioning and Ablation in Cardiac Electrophysiology Procedures
09:13

Remote Magnetic Navigation for Accurate, Real-time Catheter Positioning and Ablation in Cardiac Electrophysiology Procedures

Published on: April 21, 2013

28.5K
Three-Dimensional Ultrasonic Needle Tip Tracking with a Fiber-Optic Ultrasound Receiver
04:33

Three-Dimensional Ultrasonic Needle Tip Tracking with a Fiber-Optic Ultrasound Receiver

Published on: August 21, 2018

10.9K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Radiology

Background:

  • Peripherally inserted central catheters (PICCs) require precise tip positioning near the heart for safe intravenous access.
  • Malpositioned PICCs can lead to serious complications, necessitating immediate confirmation via chest radiography (CXR).
  • Radiologist interpretation of PICC tip location on CXRs, while accurate, can introduce significant delays.

Purpose of the Study:

  • To develop and evaluate a fully-automated deep-learning system for detecting PICC lines and their tip locations on chest radiographs.
  • To assess the system's accuracy and potential to expedite the confirmation process for PICC placement.

Main Methods:

  • A deep-learning system utilizing two fully convolutional neural networks for cascading segmentation was employed.
  • Image preprocessing included normalization for quality and dimensions.
  • Post-processing involved pruning false positives to accurately identify the PICC tip.

Main Results:

  • The best model achieved a mean absolute distance of 3.10 mm from the ground truth.
  • The standard deviation was 2.03 mm, and the root mean squared error (RMSE) was 3.71 mm on 150 test cases.
  • The system demonstrated high accuracy in detecting PICC tip location.

Conclusions:

  • The proposed automated deep-learning system can accurately detect PICC tip location, potentially reducing confirmation times.
  • This technology may be generalized to other vascular access devices and therapeutic support systems.
  • Faster confirmation of PICC position can enhance patient safety and clinical workflow efficiency.