Bendy-but-Sturdy Robot Autonomously Travels Through Lung Tissue

Andrew Corselli

Lung cancer is the leading cause of cancer-related deaths in the United States. Some tumors are extremely small and hide deep within lung tissue, making it difficult for surgeons to reach them. To address this challenge, UNC–Chapel Hill and Vanderbilt University researchers have been working on an extremely bendy but sturdy robot capable of traversing lung tissue.

In a new paper, published in Science Robotics, UNC’s Ron Alterovitz, PhD, and Jason Akulian, MD MPH, have proven that their robot can autonomously go from “Point A” to “Point B” while avoiding important structures, such as tiny airways and blood vessels, in a living laboratory model.

“This technology allows us to reach targets we can’t otherwise reach with a standard or even robotic bronchoscope,” said Co-Author Akulian. “It gives you that extra few centimeters or few millimeters even, which would help immensely with pursuing small targets in the lungs.”

The robot is made of several separate components. A mechanical control provides controlled thrust of the needle to go forward and backward, and the needle design allows for steering along curved paths. The needle is made from a nickel-titanium alloy and has been laser etched to increase its flexibility, allowing it to move effortlessly through tissue.

To drive through tissue, the needle needs to know where it is going. The research team used CT scans of the subject’s thoracic cavity and AI to create 3D models of the lung, including the airways, blood vessels, and the chosen target. Using this 3D model and once the needle has been positioned for launch, their AI-driven software instructs it to automatically travel from “Point A” to “Point B” while avoiding important structures.

“The autonomous steerable needle we’ve developed is highly compact, but the system is packed with a suite of technologies that allow the needle to navigate autonomously in real time,” said Senior Author Alterovitz. “It’s akin to a self-driving car, but it navigates through lung tissue, avoiding obstacles like significant blood vessels as it travels to its destination.”

The needle can also account for respiratory motion. Unlike other organs, the lungs are constantly expanding and contracting in the chest cavity. This can make targeting especially difficult in a living, breathing subject. According to Akulian, it’s like shooting at a moving target.

“There remain some nuances in terms of the robot’s ability to acquire targets and then actually get to them effectively,” said Akulian, “and while there’s still a lot of work to be done, I’m very excited about continuing to push the boundaries of what we can do for patients with the world-class experts that are here.”

“We plan to continue creating new autonomous medical robots that combine the strengths of robotics and AI to improve medical outcomes for patients facing a variety of health challenges while providing guarantees on patient safety,” said Alterovitz.

Here is an exclusive Tech Briefs interview — edited for length and clarity — with Alterovitz.

Tech Briefs: I’m sure there were too many to count, but what was the biggest technical challenge you faced while developing this robot?

Alterovitz: A key challenge is translating research advances in AI into a medical robot capable of autonomously steering a needle through living tissue. Medical procedures are an especially challenging domain for autonomous robots. We must develop algorithms for the robot’s AI that consider complex anatomy, tissue motion, and the uncertainty that comes from variations across living organisms.

Decades ago, rocket science enabled us to autonomously launch rockets into space and reach specific orbits. Creating autonomous medical robots that can reach targets in the body is, in many ways, more challenging than rocket science. We are only now beginning to see progress towards robots capable of operating autonomously inside living tissue.

Tech Briefs: Can you explain in simple terms how it works?

Alterovitz: The autonomous steerable needle we've developed is highly compact, but the system is packed with a suite of technologies that allow the needle to navigate autonomously in real-time. It’s akin to a self-driving car, but it navigates through lung tissue, avoiding obstacles like significant blood vessels as it travels to its destination.

Our approach begins with our image analysis software that analyzes a pre-procedure CT scan of the lungs to identify anatomical structures like bronchial tubes, significant blood vessels, and the lung boundary. The physician also identifies the target in the CT scan. Our planning software then computes a plan for the system. Based on that computed plan, the operator first guides a bronchoscope through the airways and pierces into the lung parenchyma, the tissue of the lung. The robot then deploys the steerable needle into the lung parenchyma and autonomously steers the needle to reach the target while avoiding obstacles like significant blood vessels.

Tech Briefs: What are your next steps?

Alterovitz: We plan to continue research and development of our new system to bring autonomous robotic steerable needles closer toward human use.

Tech Briefs: Any future research/work/etc. on the horizon?

Alterovitz: We plan to investigate new medical applications for which AI and robotics have the potential to improve patient care. In particular, we’re investigating new robotic solutions to enable physicians to safely and efficiently reach currently hard-to-access sites within the body.

Tech Briefs: Do you have any advice for engineers/researchers aiming to bring their ideas to fruition?

Alterovitz: Due to recent advances in AI and robotics, the time is now ripe for the development and deployment of many novel medical robotic systems. A key challenge in the coming years will be identifying and developing the right algorithms and software to enable medical robots with autonomous capabilities to be deployed in a safe and effective manner.

Tech Briefs: Anything else you’d like to add?

Alterovitz: Commercial medical robots sold today are typically tele-operated, meaning a human is always directly controlling every motion. By leveraging the power of robotics and AI, we developed a robot capable of autonomously steering needles to targets in living tissue with unprecedented accuracy and safety.

---