Robotic transesophageal echocardiography: system design and deep learning-based kinematic modeling

Seyed MohammadReza Sajadi; Abbas Tariverdi; Henrik Brun; Ole Jakob Elle; Kim Mathiassen

doi:10.3389/frobt.2025.1705142

Robotic transesophageal echocardiography: system design and deep learning-based kinematic modeling

Front Robot AI. 2026 Jan 27:12:1705142. doi: 10.3389/frobt.2025.1705142. eCollection 2025.

Authors

Seyed MohammadReza Sajadi¹, Abbas Tariverdi², Henrik Brun^{3

4}, Ole Jakob Elle^{1

3}, Kim Mathiassen⁵

Affiliations

¹ Department of Informatics, University of Oslo, Oslo, Norway.
² Department of Physics, University of Oslo, Oslo, Norway.
³ The Intervention Center, Oslo University Hospital, Oslo, Norway.
⁴ Department for Pediatric Cardiology, Oslo University Hospital, Oslo, Norway.
⁵ Department of Technology Systems, University of Oslo, Oslo, Norway.

Abstract

Introduction: This paper presents a robotic transesophageal echocardiography (TEE) system that replicates all essential degrees of freedom available in manual TEE procedures. The developed robotic system advances dual-subsystem architectures through enhanced mechanical design and deep learning-based kinematic modeling.

Methods: Building upon previous designs that manipulate the TEE probe from both handle and gastroscope tube, our system integrates with a teleoperated UR5 manipulator to accommodate both supine and left lateral decubitus patient positions, addressing the full spectrum of clinical TEE procedures. The system features 6 DOF at the probe handle and 2 DOF at the gastroscope tube. Together, these create optimal gastroscope tube geometry, minimizing cable tension asymmetry and friction-induced nonlinearities inherent in cable-driven mechanisms. The primary contribution is a data-driven kinematic model using recurrent neural networks with LSTM units that overcomes fundamental limitations of analytical approaches for continuum manipulators. Trained on 42,000 synchronized pose-command pairs collected across three gastroscope tube configurations (0°, 45°, 90° bends), the model effectively captures dead zones, hysteresis, and coupling effects between steering mechanisms.

Results: Experimental validation demonstrates strong position tracking across all three gastroscope tube configurations. The model achieves RMSE of 1.267 mm for the 0° configuration, 1.209 mm for the 45° configuration, and 1.194 mm for the 90° configuration. Mean orientation errors are 7.064° at 0°, 8.503° at 45°, and 4.947° at the clinically critical 90° configuration. The model exhibits coordinate frame independence with only 0.06 mm RMSE difference between original and rotated datasets. This confirms true kinematic learning rather than coordinate-specific patterns. With 1.8 ms inference time, the system achieves real-time performance essential for clinical deployment.

Discussion: This integration of robotic system design with deep learning establishes a foundation for semi-autonomous TEE systems. The developed system can support both diagnostic TEE examinations and TEE-guided structural heart interventions.

Keywords: LSTM; cable-driven mechanism; continuum mechanism; deep learning kinematic modeling; robotic transesophageal echocardiography; robotic-assisted echocardiography; synchronized robotic subsystems.