Research Projects

KIMONO 2
AI-driven recognition and analysis of actions and processes based on merged multisensor data for optimizing surgical procedures
Start: 05/2024
End: 04/2027

Thanks to increasing digitalization, modern operating rooms offer new opportunities to improve the safety and efficiency of surgical procedures. The aim of the project is to develop an integrated monitoring system that uses ceiling cameras and laparoscopic image data to automatically detect safety-related situations in the operating room. The focus is on protecting both patients and medical staff.
The research project aims to develop an integrated monitoring system for operating rooms. This will be based on the evaluation of ceiling cameras to analyze what is happening in the operating room and on the processing of laparoscopy images to examine the inside of the body. Camera-based analyses are used to automatically record safety-related aspects. These include, in particular, the assessment of X-ray safety by recognizing prescribed protective clothing, the analysis of distances to the X-ray machine to estimate potential radiation exposure, and the recording of door openings in the operating room that may affect sterile procedures and safety processes.

Another focus is on the evaluation of laparoscopic image data to increase patient safety and protect the medical technology used. Among other things, the laser fiber is to be detected during kidney stone surgery in order to avoid premature activation of the laser and thus possible damage to the endoscope.

The project will develop various use cases and evaluate them in terms of feasibility, effort, and benefits. The most promising approaches will then be implemented as prototypes. The project is based on preliminary work from the “KIMONO” project as well as existing recording systems from the Siloah St. Trudbert Clinic in Pforzheim, which will be used for further data collection and evaluation.

Role of the FZI
As part of the research project, video and image data sets from ceiling cameras in the operating room and from laparoscopic systems are collected in order to analyze safety and assistance potential during surgical procedures.

Based on these data sets, machine learning models are developed and trained to automatically analyze specific safety aspects.

In close collaboration with medical professionals, demonstrators are developed and integrated into the processes of a target hospital to enable a realistic assessment of acceptance, performance, and practicability.

Contact person
Staff
Division: Embedded Systems and Sensors Engineering
Headquarters Karlsruhe

Research focus
Applied Artificial Intelligence

In this research focus, the FZI concentrates on practical research into the key technology of Artificial Intelligence (AI). Innovative AI solutions are developed and transferred to application areas such as mobility, robotics, healthcare technology, logistics, production, and supply and disposal on behalf of our partners and customers.

Illustration

Go to Top