Sentante's CE-marked robotic platform is building the data foundation for endovascular physical AI

Drive-side force sensing and a 1:1 motion-mimicking interface make every procedure a training-grade record of expert clinical skill

KAUNAS, Lithuania, July 23, 2026 /PRNewswire/ -- Sentante, the medical robotics company building a haptic, device-agnostic platform for remote vascular surgery, is turning its newly CE-marked robotic system into a data engine for the next generation of intelligent, endovascular intervention.

Much of the field claims autonomy ahead of the data needed to deliver it. Sentante built the opposite: a system architected from the start to capture force and torque, device kinematics and time-aligned fluoroscopy together, on every procedure. Hardware and AI are one effort, and each procedure refines the dataset that makes increasing machine assistance possible.

"The next wave of technology is physical AI: systems that can sense, act and operate in the real world, not just process information," said Edvardas Satkauskas, CEO and co-founder of Sentante. "For endovascular intervention, the constraint has never been ambition, it has been data. You cannot train a system to navigate a living vessel without a rich, accurate record of how the best clinicians do it. We have spent years building the platform that captures exactly that, and CE mark means it is now generating that data in real clinical settings across Europe."

Imaging is being deliberately reduced, and force has to fill the gap:

Fluoroscopy and contrast media both carry harm: radiation exposure for patients and staff, and contrast-related risk, notably renal injury. Guidelines accordingly push every endovascular procedure toward minimum imaging, which means the situational-awareness data available to the operator goes down, not up.

The hand fills the gap: the load profile up the catheter column distinguishes safe contact from a perforation precursor. On a dose-limited 2D image the two can look identical, and no computer-vision force indicator can recover a signal that was never captured. An AI built on imaging alone is extracting more from a data source the field is deliberately driving down.

Drive-side force and torque sensing remains rare in medical robotics; da Vinci 5 only brought force feedback to laparoscopy in March 2024, with preclinical evidence of up to 43% less force on tissue.

Sentante engineered force and torque sensing into the catheter drive from day one, and the endovascular setting makes the case even stronger: a thin column of wire and catheters in continuous contact with the vessel wall, where the safety envelope is a load profile, not a position.

"The image tells you where the device is. The hand tells you what the vessel is doing," said Dr. Tomas Baltrūnas, co-founder and Chief Medical Officer of Sentante. "A system that captures only the image is missing the half that matters most for safety."

The interface decides whether the data carries real skill:

Every joystick or screen-based controller in endovascular robotics forces the operator to translate a career of feel and micro-adjustment through an artificial input layer. The captured demonstration records expert joystick operation, not expert catheter operation, and the demonstrator pool is limited to physicians who have completed a months-long learning curve on that specific robot.

Sentante's platform is different: the clinician manipulates standard catheters and guidewires exactly as in manual intervention, with authentic force feedback at the fingertips, and the system records that natural motor program directly. The captured behaviour carries the actual clinical skill, the demonstrator pool expands to every existing interventionalist, and every procedure performed on the platform is a training-grade demonstration in its natural form.

Da Vinci proved the principle in 1999: its one-to-one motion-mimicking console let manual surgical skill transfer without re-learning, and that made it adoptable. Sentante applies the same logic to the catheter, removing the training-bandwidth bottleneck of every prior platform: an expert is competent from day one, and the system accumulates training data from day one.

"What I learned to do with my hands over fifteen years of intervention is replicable with the Sentante platform." said Baltrūnas. "The motion-mimicking interface lets me operate as I always have, with the platform recording what I do as I do it. The expertise stays in the operator's hands, and the data stays in the system."

Over the past year the company has run a world-first transatlantic remote thrombectomy on perfused human cadaver models and a GLP animal study of 24 remote procedures across three continents, each adding to a dataset built under procedure-authentic conditions.

The CE-marked system integrates with existing cath-lab infrastructure and supports peripheral vascular interventions, with remote stroke thrombectomy on a parallel regulatory pathway. The latest-generation robot uses NVIDIA hardware, and Sentante was among the first to develop on NVIDIA Isaac for Healthcare.

Sentante is continuing its European commercial rollout, progressively introducing AI-driven assistance as the dataset matures.

About Sentante:

Sentante is a medical robotics company founded in 2017 building a haptic, device-agnostic endovascular platform that enables clinicians to perform complex vascular procedures remotely with full tactile feedback. Designed to integrate with existing cath-lab infrastructure, Sentante aims to expand access, improve clinician safety, and elevate procedural consistency across peripheral vascular, neurovascular and cardiovascular applications. Sentante is a member of the NVIDIA Inception programme. www.sentante.com

Press contact:
Harry Ashcroft | Perseid PR
harry@perseidpr.com