外科数据科学：数据驱动的帮助或

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”.

手术数据科学是一种新的医学子学科，旨在分析数据以提供某些援助职能。并发症和可视化结构的预后是两个潜在的临床应用。“导航系统在软组织中特别有用surgerysince the tissue is moving, so to speak. With the help ofArtificial Intelligencethe navigation system has learnt how theorganand 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传感器and room cameras provide an uninterrupted data flow. In addition, there areimage数据获得术前。

Robots – the surgeon’s helping hands

According to Professor Speidelrobot-assisted surgeryoffers considerable added value for surgeon and patient alike: anendoscope, which is usually guided by a human hand, might well be fitted on aroboticarm 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 intosurgical trainingso 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.”

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@www.lzdntxqz.com.