Artificial intelligence meets medical robotics. Scenarios, prospects and benefits of a combination destined to change medical procedures
Artificial intelligence and medical robotics. A combination destined to change the medicine of the present and the future. Artificial intelligence (AI) applications in medical robots are bringing a new era to medicine. Advanced medical robots can perform diagnostic and surgical procedures, aid rehabilitation, and provide symbiotic prosthetics to replace limbs.
On this topic, the journal Science published an in-depth article entitled 'Artificial intelligence meets medical robotics', in which international scientists analysed the scenarios, prospects and benefits that this interaction could bring to the field of medicine. Arianna Menciassi, vicerector of the Sant'Anna School and the only Italian professor to sign the article, illustrated the potential of soft robotics for minimally invasive surgery.
Soft robotics for minimally invasive surgery
In 'Soft robotics for minimally invasive surgery', written together with Kaspar Althoefer (Queen Mary University of London), Arianna Menciassi analyses the technological benefits of using soft components in surgical robots. Despite the success of some platforms, such as the da Vinci Surgical System for prostatectomy and abdominal or thoracic surgery, these systems are often limited by their rigid component design, which can make it difficult to access certain areas of the body and can lead to tissue injuries.
The key feature of soft robotics is the use of materials that can deform, bend, shrink, and change stiffness, pushing the paradigm of robotic surgery in a safer and softer direction. These robots address different body regions, such as the ear, abdomen, and thorax, and they can be dedicated both for diagnosis and intervention.
STIFF-FLOP, European project pioneering the use of artificial intelligence and soft robotics in medicine
Arianna Menciassi focused on the importance of the European project STIFF-FLOP (stiffness controllable flexible and learnable manipulator for surgical operations), coordinated by King's College London with the Institute of BioRobotics of the Scuola Sant'Anna among the partners. The soft robotic systems that were developed were made from biocompatible silicone rubber and pneumatically actuated, by using new fabrication methods that allow for the creation of reliable structures that are also safe and effective. In addition, advanced ML techniques were employed to intuitively teleoperate the soft robots in the abdominal cavity of the patient, and haptic systems allowed surgeons to discern interactions of the robot with the soft tissue environment.
Future challenges
One of the main objectives is to improve the precision and accuracy of soft robotic systems. Soft robotic systems rely on deformation of the material that the robot is constructed from to achieve movement. The resultant motion is more difficult to model and can result in lower positional accuracy, which could be a critical concern in surgery. To overcome this challenge, advanced strategies based on AI, ML, and data-driven control that can cope with the highly nonlinear motion behavior of soft robots are being developed. Recent advances in computer power, computer vision, ML, real-time modeling, and simulation can make operation of soft robots for surgery possible without cumbersome teleoperation modalities and extensive training sessions for surgeons.
