A5043334481- Surgical Simulation and Training
- Colorectal Cancer Screening and Detection
- Anatomy and Medical Technology
- Colorectal Cancer Surgical Treatments
- Soft Robotics and Applications
- Cardiac, Anesthesia and Surgical Outcomes
- Advanced Sensor Technologies Research
- Medical Imaging and Analysis
- Robotics and Sensor-Based Localization
- Medical Image Segmentation Techniques
- Robotic Path Planning Algorithms
- Robot Manipulation and Learning
- Photoacoustic and Ultrasonic Imaging
- Pelvic floor disorders treatments
- Advanced Neural Network Applications
Heidelberg University
2020-2024
University Hospital Heidelberg
2020-2024
National Center for Tumor Diseases
2023
Surgical workflow and skill analysis are key technologies for the next generation of cognitive surgical assistance systems. These systems could increase safety operation through context-sensitive warnings semi-autonomous robotic or improve training surgeons via data-driven feedback. In up to 91% average precision has been reported phase recognition on an open data single-center video dataset. this work we investigated generalizability algorithms in a multicenter setting including more...
Abstract Image-based tracking of medical instruments is an integral part surgical data science applications. Previous research has addressed the tasks detecting, segmenting and based on laparoscopic video data. However, proposed methods still tend to fail when applied challenging images do not generalize well they have been trained on. This paper introduces Heidelberg Colorectal (HeiCo) set - first publicly available enabling comprehensive benchmarking instrument detection segmentation...
Abstract Semantic segmentation of organs and tissue types is an important sub-problem in image based scene understanding for laparoscopic surgery a prerequisite context-aware assistance cognitive robotics. Deep Learning (DL) approaches are prominently applied to tracking instruments. This work compares different combinations neural networks, loss functions, training strategies their application semantic human images order investigate applicability as components systems. TernausNet-11 trained...
Abstract Background Laparoscopic videos are increasingly being used for surgical artificial intelligence (AI) and big data analysis. The purpose of this study was to ensure privacy in video recordings laparoscopic surgery by censoring extraabdominal parts. An inside-outside-discrimination algorithm (IODA) developed protection while maximizing the remaining data. Methods IODAs neural network architecture based on a pretrained AlexNet augmented with long-short-term-memory. set training testing...
PURPOSE: Surgical workflow and skill analysis are key technologies for the next generation of cognitive surgical assistance systems. These systems could increase safety operation through context-sensitive warnings semi-autonomous robotic or improve training surgeons via data-driven feedback. In up to 91% average precision has been reported phase recognition on an open data single-center dataset. this work we investigated generalizability algorithms in a multi-center setting including more...
Abstract Purpose Endovascular interventions require intense practice to develop sufficient dexterity in catheter handling within the human body. Therefore, we present a modular training platform, featuring 3D-printed vessel phantoms with patient-specific anatomy and integrated piezoresistive impact force sensing of instrument interaction at clinically relevant locations for feedback-based skill detect reduce damage delicate vascular wall. Methods The platform was fabricated then evaluated...
Abstract Background Laparoscopic cholecystectomy is a very frequent surgical procedure. However, in an ageing society, less staff will need to perform surgery on patients. Collaborative robots (cobots) could address shortages and workload. To achieve context-awareness for surgeon-robot collaboration, the intraoperative action workflow recognition key challenge. Methods A process model was developed activities including actor, instrument, target laparoscopic (excluding camera guidance). These...
Abstract Smart medical phantoms for training and evaluation of endovascular procedures ought to measure impact forces on the vessel walls worth protecting provide feedback clinicians articulated soft robots. Recent commercial smart are expensive, usually not customizable different applications lack accessibility integrated development. This work investigates piezoresistive films as highly integratable flexible sensors be used in arbitrary phantom anatomies over large surfaces curved shapes...
Image-based tracking of medical instruments is an integral part surgical data science applications. Previous research has addressed the tasks detecting, segmenting and based on laparoscopic video data. However, proposed methods still tend to fail when applied challenging images do not generalize well they have been trained on. This paper introduces Heidelberg Colorectal (HeiCo) set - first publicly available enabling comprehensive benchmarking instrument detection segmentation algorithms...