Intelligent magnetic manipulation for gastrointestinal ultrasound

Joseph C. Norton (Lead / Corresponding author), Piotr R. Slawinski, Holly S. Lay, James W. Martin, Benjamin F. Cox, Gerard Cummins, Marc Phillipe Yves Desmulliez, Richard E. Clutton, Keith L. Obstein, Sandy Cochran, Pietro Valdastri

Research output: Contribution to journalArticlepeer-review

59 Citations (Scopus)
115 Downloads (Pure)


Diagnostic endoscopy in the gastrointestinal tract has remained largely unchanged for decades and is limited to the visualization of the tissue surface, the collection of biopsy samples for diagnoses, and minor interventions such as clipping or tissue removal. In this work, we present the autonomous servoing of a magnetic capsule robot for in-situ, subsurface diagnostics of microanatomy. We investigated and showed the feasibility of closed-loop magnetic control using digitized microultrasound (μUS) feedback; this is crucial for obtaining robust imaging in an unknown and unconstrained environment. We demonstrated the functionality of an autonomous servoing algorithm that uses μUS feedback, both on benchtop trials as well as in-vivo in a porcine model. We have validated this magnetic-μUS servoing in instances of autonomous linear probe motion and were able to locate markers in an agar phantom with 1.0 ± 0.9 mm position accuracy using a fusion of robot localization and μUS image information. This work demonstrates the feasibility of closed-loop robotic μUS imaging in the bowel without the need for either a rigid physical link between the transducer and extracorporeal tools or complex manual manipulation.
Original languageEnglish
Article numbereaav7725
Number of pages31
JournalScience Robotics
Issue number31
Early online date19 Jun 2019
Publication statusPublished - 19 Jun 2019

ASJC Scopus subject areas

  • Mechanical Engineering
  • Computer Science Applications
  • Control and Optimization
  • Artificial Intelligence


Dive into the research topics of 'Intelligent magnetic manipulation for gastrointestinal ultrasound'. Together they form a unique fingerprint.

Cite this