AI and robotics are transforming precision in medical needle procedures

AI and robotics are transforming precision in medical needle procedures

Imagine a doctor trying to reach a cancerous nodule deep in a patient's lung — a target the size of a pea hidden behind a maze of critical blood vessels and airways that shift with every breath. A millimeter of a stretch can penetrate a large artery, and falling could mean the cancer is missing entirely and allowed to spread if left untreated.

This is in thousands of procedures every day in which accuracy is critical and the task is exposed to anatomical obstacles that are not penetrable or sensitive. Can artificial intelligence (AI) and robots help overcome these challenges and improve patient outcomes?

A new era of “AI leadership” is in medicine. Robots with advanced AI can assist doctors and automate certain tasks, making unprecedented accuracy and complex procedures safer and more effective. “

Ron Alterovitz, Lawrence Grossberg, who is a professor in the Department of Computer Science

A new article inScience Robotics Formalizes the concept of AI guidance for medical needle procedures and outlines the levels of AI guidance for each component. The authors define four components of AI guidance: perception of anatomy, planning of instrument movements, perception of instrument status, and execution of instrument movements during a procedure. AI-guided robots can achieve greater accuracy and precision in needle guidance than human doctors, while enabling the use of cutting-edge needle designs that can curve through the body.

The paper, “Medical Needles in the Hands of AI: Toward Autonomous Robot Navigation,” was written by Alterovitz, as well as Janine Hoelscher of Clemson University and Alan Kuntz of the University of Utah. Hoelscher and Kuntz previously completed doctoral work in computer science at UNC with Alterovitz as an advisor.

The era of AI leadership

For decades, physicians have relied on image guidance and the use of x-rays, computed tomography (CT), and magnetic resonance (MR) images to visualize a patient's anatomy and needle path plan before a procedure. This advance, stemming from the discovery of X-rays in the late 19th century, allowed safer access to points within the body.

Recent advances in AI now enable a leap forward. AI can automatically analyze images, identify targets and obstacles, calculate safe trajectories, and even autonomously guide robotic needles around sensitive tissues at locations deep within the body. One such example, demonstrated by a team of researchers at the University of North Carolina at Chapel Hill, Vanderbilt University and the University of Utah, demonstrated a medical robot that can autonomously direct a needle to clinically relevant targets in a lung with high accuracy in living tissue, demonstrating better performance than traditional tools alone. The authors describe this transformative shift from image guidance to AI guidance, whereby AI assists in perceiving patient anatomy, tracking progress through the procedure, planning instrument movements, and even executing these requests.

“For decades, visual guidance has helped physicians better plan and perform medical procedures,” Alterovitz said. “The AI ​​guidance goes even further to make procedures safer and less invasive.”

The article formalizes the concept of AI guidance, which leverages AI to improve physician performance and create building blocks for greater levels of robotic autonomy. The article defines the four components of AI guidance as:

1. Perceiving anatomy

2. Planning instrument movements

3. Perception of instrument state

4. Perform instrument movements during a procedure

Each of these four components can provide its own level of AI guidance:

• Eye-On/Practice-On-where the doctor performs the task with AI providing assistance

• Eyes-on/Hands-Off-where the AI ​​performs the task while the doctor monitors the AI ​​and is ready to intervene in unusual situations

• Shutdown/Hands-Off-where the AI ​​performs the task and the doctor only enters when requested by the AI

• Complete AI guide – where the AI ​​completes the task

Finally, the article classifies current systems into these categories and discusses research challenges to enable higher levels of AI guidance. In particular, researchers highlight critical barriers to widespread clinical adoption, such as the need to guarantee safety, operate within the regulatory environment, develop physician-AI interfaces that are intuitive at any level of AI guidance, and the ability to integrate required technology into all aspects of a clinical workflow.

Although Alterovitz acknowledged the many challenges that remained to be overcome, he expressed his thoughts on the future of AI guidance in medical procedures.

“Breakthroughs in AI and robotics will continue to enable increasing levels of AI guidance and robotic automation for medical procedures,” Alterovitz said. “AI and robotics can provide physicians with new tools to make challenging procedures safer and more effective.”

Sources: