Image showing the robotic components like the steerable needle, bronchoscope, and actuation unit. (Image Credit: The University of North Carolina at Chapel Hill)
Lung cancer claims more lives than any other cancer type in the US. It’s difficult to treat some tumors because they’re tiny and deep in the tissue, so surgeons find it difficult to reach that area. UNC-Chapel Hill and Vanderbilt University researchers developed a robotic needle that autonomously moves inside a patient’s lung, reaching a specified target for medical treatment while avoiding obstacles.
“Commercial medical robots sold today are typically teleoperated, meaning a human is always directly controlling every motion,” said Professor Alterovitz. “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.”
If a medical tool isn’t on the right target --- even by a few millimeters --- during surgery, it could lead to the wrong results and complications. For instance, imprecisely reaching a lung’s suspicious nodule means that a misdiagnosis is made, putting the patient at risk due to the spreading of cancer. An autonomous robotic needle can perform safer, more accurate procedures in the body, like biopsies, drug delivery, and radiotherapy. “This technology allows us to reach targets we can’t otherwise reach with a standard or even robotic bronchoscope,” said Dr. Akulian, co-author of the paper.
The needle has a specialized design, allowing it to move along curved paths, and the mechanical control enables the needle to thrust forward/backward. Additionally, the needle consists of a nickel-titanium alloy and underwent laser etching to make it more flexible for easy movement through tissue. Catheters can work with the needle for lung biopsy procedures.
However, the needle must know where it’s heading before getting started. The team scanned a patient’s thoracic cavity, producing 3D models of the lung, including the airways, blood vessels, and targets. After that, they used the 3D model and positioned the needle for launch. Their AI software then told it to autonomously move from one location to the next without impacting crucial 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 Professor 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 team’s next step is to refine the system and ensure the needle performs well in challenging cases before bringing it closer to clinical use. “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,” said Dr. Akulian. Professor Alterovitz added, “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.”
How the needle works on patients. The following is described by The University of North Carolina at Chapel Hill in their paper at science.org.
We show both the procedure sequence flow (thick black arrows) and information flow (thin colored arrows). A CT scan was segmented and used to construct a map leveraged by the three-stage motion planning software in the preoperative phase. The scan, segmentation, and three-stage plan were used intraoperatively in the procedure, during which the devices were tracked, registered to the CT frame, and visualized for the operator. These steps informed the three-stage deployment of the system and the interaction between the physician and the robot.
Have a story tip? Message me at: http://twitter.com/Cabe_Atwell