A robotic arm that guides the endoscope could support the surgeon in the...
A robotic arm that guides the endoscope could support the surgeon in the future, as could navigation systems that display the tumor position, incision and risk structures on the monitor or via data glasses.
Source: EKFZ/André Wirsig

Surgical data science: data-driven assistance in the OR

In the next-generation operating room interconnected sensors will collect data, analyse it in real-time and make it available to digital assistance functions: OR nurses will be shown the instruments to be used in the next phase of surgery and the surgeon will receive reliable predictive information on complications.

Report: Sonja Buske, Sascha Keutel

Dr Stefanie Speidel, professor of translational surgical oncology at the National Center for Tumor Diseases (NCT) in Dresden, Germany, is turning this vision into reality: she is developing assistance systems that guide the surgeon safely and directly to the tumor. While this OR scenario is not quite around the corner yet, Professor Speidel is confident that “we are on the right track”.

Surgical data science is a new medical sub-discipline that aims to analyse data in order to provide certain assistance functions. The prognosis of complications and visualizing structures are two potential clinical applications. “Navigation systems are particularly useful in soft tissue surgery since the tissue is moving, so to speak. With the help of Artificial Intelligence the navigation system has learnt how the organ and the surrounding tissue behave. Thus it can accurately predict tissue movement”, Professor Speidel explains. The relevant data is provided by different sources. The endoscope, for example, sends data from inside the patient’s body. Vital signs are transmitted and movement sensors and room cameras provide an uninterrupted data flow. In addition, there are image data acquired pre-surgery.

Robots – the surgeon’s helping hands

According to Professor Speidel robot-assisted surgery offers considerable added value for surgeon and patient alike: an endoscope, which is usually guided by a human hand, might well be fitted on a robotic arm that automatically chooses the viewing angle that is ideal for the surgeon. Suction devices to remove blood are also conceivable. While the surgeon performs the interventions as usual, many assistance functions are performed by a robot. “To be sure”, Professor Speidel emphasizes, “we don’t envisage replacing the surgeon by a robot. The machine is nothing but a helping hand that supports the surgeon. The surgeon will never become obsolete. The decisions have to be made by human beings; the robot however can assist in the decision-making process.”

Surgical data science has to be integrated into surgical training so everybody involved is on the same page. “We need to understand each other,” Professor Speidel in convinced. “In Dresden, we already have interdisciplinary programmes where engineers and physicians are trained side by side. This concept should be implemented everywhere.”

The navigation system shows the tumor (yellow) and risk structures such as...
The navigation system shows the tumor (yellow) and risk structures such as vessels (blue) in the endoscopic image of the liver.
Source: NCT Dresden/VTG Universitätsklinikum Carl Gustav Carus

Interdisciplinary cooperation

This is exactly the starting point of the Surgical Data Science Initiative, which was founded in 2016. Leading experts from research and industry jointly developed questions and solutions to advance this new discipline over the next few years. The data-driven approach plays a crucial role, says Professor Speidel: “We are inundated with data. In clinical routine, no human being is able to interpret all data. But for AI purposes we need lots of annotated data, not just raw data supplied by sensors in the OR.” An expert would have to view the videos and add annotations – far too time-consuming a task. Thus the team of the Surgical Data Science Initiative also wants to develop strategies to improve annotation.

That cannot be done on the fly. “We need representative data from several hospitals. Device standards and interfaces need to be harmonized and integrated into the surgical workflow“, Professor Speidel explains. Despite all the open questions, she has no doubts that her vision of the OR will one day be reality.

Profile:
Professor Dr Stefanie Speidel studied computer science at the University of Karlsruhe and the Royal Institute of Technology Stockholm. The received her doctoral degree in 2009 at the Karlsruhe Institute of Technology (KIT) in a graduate programme “Intelligent Surgery” (KIT, University Heidelberg, DKFZ). From 2012 to 2016 she headed the junior researcher group “Computer-aided Surgery” at KIT. In 2017 she was appointed Professor of Translational Surgical Oncology at the National Center for Tumor Diseases (NCT). Her current research focuses on computer-aided and robot-aided surgery, soft tissue navigation and intraoperative visualisation in the context of the operating room of the future.


You are a professional from the emtech ecosystem and interested in sharing your tech tale with a guest contribution at Tectales? Just contact us: editorial@tectales.com.

Subscribe to our newsletter

Related articles

About the end of medicine, as we know it

About the end of medicine, as we know it

Our health system today can no longer be sustained in its existing form. It has become too expensive and too ineffective.

Smart surgery - from technical fascination to clinical reality

Smart surgery - from technical fascination to clinical reality

Artificial intelligence is developing at an enormous speed and intelligent instruments will profoundly change surgery and medical interventions.

AI system for recognition of hand gestures

AI system for recognition of hand gestures

Scientists have developed an AI system that recognises hand gestures by combining skin-like electronics with computer vision.

Humanising wearable health technologies

Humanising wearable health technologies

Designer Leah Heiss considers her work as creating “emotional technologies”, i.e. wearable devices based on human-centred design principles. For her, empathy is everything!

Nexkin: multiparametric monitoring shirt launched

Nexkin: multiparametric monitoring shirt launched

Chronolife announced the launch of Nexkin, a washable smart T-shirt that monitors six key physiological parameters to enable prevention, risk reduction, and remote monitoring.

Deep learning identifies molecular patterns of cancer

Deep learning identifies molecular patterns of cancer

An AI platform can analyze genomic data extremely quickly, picking out key patterns to classify different types of colorectal tumors and improve the drug discovery process.

Are humans too slow for digitalisation?

Are humans too slow for digitalisation?

Today, drones are happily regarded as the pinnacle of digitalisation in healthcare. However, for Dr Dominik Pförringer, “Drones are not even in the top 100 of my wish list for digital solutions."

Blockchain – paradigm shift towards patient-centered healthcare

Blockchain – paradigm shift towards patient-centered healthcare

The use of blockchain will change paradigm towards patient-centered healthcare.

Transactions, trust and tokens – Blockchain for healthcare

Transactions, trust and tokens – Blockchain for healthcare

“A central pillar of blockchain is trust, because data cannot be altered,” says Dr Eberhard Scheuer, Chairman of the Health Information Traceability Foundation.

Popular articles