Go to ewuu.nl

Anatomical recognition in robot-assisted surgery

Scientists from Eindhoven University of Technology (TU/e), Wageningen University Research (WUR), the University of Utrecht (UU), and the University Medical Center Utrecht (UMC Utrecht) are working on a research project on the digital representation of the human anatomy for robot-assisted surgery. Project leader and surgeon Prof. dr. Jelle Ruurda explains:

What is it you are working on? And what is the role of AI?
“What we are working on is a kind of google maps for robot-assisted surgery, so that we, surgeons, get the patient’s anatomy projected on our screen. The surgeon operates on the patient by making small incisions in the skin. These are approximately the size of a fingertip and range in size from 5 to 12 millimeters. Because of the small size of the instruments, surgeons can operate through one or a few small incisions, making robot-assisted surgery a minimally invasive procedure. The camera can magnify the operating field up to 20 times its actual size, allowing the surgeons to fiddle with the square millimeter. However, at that level of detail, surgeons lose their helicopter view of the human body and struggle to orientate themselves inside it, also everything that they touch alters the anatomy of the operating field. We are developing an algorithm that analyzes video images of operations and recognizes the anatomy of the patient; for example, this is a blood vessel, this is a nerve.”

What is the impact for society?
“This assists surgeons – and mostly surgeons who are still in training (“residents”) – and reduces the likelihood of mistakes. Of course, above all, this eventually benefits the patient. Moreover, the entry of digital tools into the still pretty old-fashioned world of operating will open the field of applications that will help surgeons and patients during surgery.”

How do you see the future of AI in this field? And what is the value of collaboration in the Alliance?
“In the future robots will be used more and more in surgery, especially to perform very precise tasks. For example, there are already robots that drill channels in the rock bone of an ear to place a hearing aid. But also, robots exist that help to pick fruit from trees, something WUR developed. The computer science department of UU has a research focus on monitoring systems that provide automated warnings if a potential dangerous situation may arise. These systems are promising for the domain of robotic surgery as well. TU/e has huge experience with analysis of medical images. Mainly, this experience was in the field of radiological images, but the video images we use in this project are an expanding field of research, also in the development of new AI techniques.”

About the project:

Project title: Towards the future of surgery: anatomical recognition in robot-assisted surgery

Applicants: Jelle Ruurda (UMCU, J.P.Ruurda@umcutrecht.nl ), Josien Pluim (TU/e), Fred van Eeuwijk (WUR), Frank van der Stappen, Natasha Alechina (UU).

Subject: The project leverages extensive experience and expertise of the partners in clinical practice and research experience in minimally invasive and upper-gastrointestinal surgery (UMCU), medical object recognition and AI in medical image analysis (TU/e), man-machine interfaces and autonomous intelligent systems (UU), and AI, applied statistics, and realization of digital twins with a focus on applications in life and environmental sciences (WUR).