A5000978525- Robotics and Sensor-Based Localization
- Cardiac Valve Diseases and Treatments
- Advanced Vision and Imaging
- Surgical Simulation and Training
- Cardiac and Coronary Surgery Techniques
- Soft Robotics and Applications
- Computer Graphics and Visualization Techniques
- Generative Adversarial Networks and Image Synthesis
- Artificial Intelligence in Healthcare and Education
- Augmented Reality Applications
- Health and Medical Research Impacts
- Cardiovascular Function and Risk Factors
- Cardiac Imaging and Diagnostics
- Radiomics and Machine Learning in Medical Imaging
- Cardiac Structural Anomalies and Repair
- Optical measurement and interference techniques
- 3D Surveying and Cultural Heritage
- Medical Imaging and Analysis
- Optical Imaging and Spectroscopy Techniques
- 3D Shape Modeling and Analysis
- Multimodal Machine Learning Applications
- Anatomy and Medical Technology
- Digital Imaging in Medicine
- Infrared Target Detection Methodologies
- Image Enhancement Techniques
University Hospital Heidelberg
2020-2024
Heidelberg University
2020-2024
German Centre for Cardiovascular Research
2022-2024
Mannheim University of Applied Sciences
2019
The stereo correspondence and reconstruction of endoscopic data sub-challenge was organized during the Endovis challenge at MICCAI 2019 in Shenzhen, China. task to perform dense depth estimation using 7 training datasets 2 test sets structured light captured porcine cadavers. These were provided by a team Intuitive Surgical. 10 teams participated day. This paper contains 3 additional methods which submitted after finished as well supplemental section from these on issues they found with dataset.
Minimally invasive surgeries have restricted surgical ports, demanding a high skill level from the surgeon. Surgical simulation potentially reduces this steep learning curve and additionally provides quantitative feedback. Markerless depth sensors show great promise for quantification, but most such are not designed accurate reconstruction of complex anatomical forms in close-range.This work compares three commercially available sensors, namely Intel D405, D415, Stereolabs Zed-Mini range...
Abstract Purpose: Mitral valve repair is a complex minimally invasive surgery of the heart valve. In this context, suture detection from endoscopic images highly relevant task that provides quantitative information to analyse suturing patterns, assess prosthetic configurations and produce augmented reality visualisations. Facial or anatomical landmark tasks typically contain fixed number landmarks, use regression heatmap-based approaches localize landmarks. However in endoscopy, there are...
Abstract In endoscopy, depth estimation is a task that potentially helps in quantifying visual information for better scene understanding. A plethora of algorithms have been proposed the computer vision community. The endoscopic domain however, differs from typical scenario due to differences setup and nature scene. Furthermore, it unfeasible obtain ground truth owing an unsuitable detection range off-the-shelf sensors difficulties setting up depth-sensor surgical environment. this paper,...
The CycleGAN framework allows for unsupervised image-to-image translation of unpaired data. In a scenario surgical training on physical simulator, this method can be used to transform endoscopic images phantoms into which more closely resemble the intra-operative appearance same target structure. This viewed as novel augmented reality approach, we coined Hyperrealism in previous work. use case, it is paramount importance display objects like needles, sutures or instruments consistent both...
Abstract OBJECTIVES Minimally invasive mitral valve repair (MVR) is considered one of the most challenging operations in cardiac surgery and requires much practice experience. Simulation-based surgical training might be a method to support learning process help flatten steep curve novices. The purpose this study was show possible effects on using high-fidelity simulator with patient-specific replicas. METHODS Twenty-five participants were recruited perform MVR anatomically realistic models...
Our research focuses on enhancing the CI/CD pipeline with innovative approaches for vulnerability mitigation and effective handling of dependency-based attacks. By integrating advanced security measures throughout development stages, we identify address vulnerabilities early on. Through rigorous monitoring strict control dependencies, ensure robust protection against potential The positive outcome our is a fortified that streamlines software development, reduces risks, enables rapid secure...
Abstract Mitral valve regurgitation is one of the most common heart diseases that can occur when structural composition mitral affected. repair, typically performed in a minimally invasive setting, complex surgery aims to reinstate integrity and thereby restore normal function. The current practice lacks quantification geometrical changes interactive 3D visualization could enhance understanding pathomorphological impact surgical correction. This work presents functionalities from smartMVR,...
Minimally Invasive Surgery (MIS) techniques have gained rapid popularity among surgeons since they offer significant clinical benefits including reduced recovery time and diminished post-operative adverse effects.However, conventional endoscopic systems output monocular video which compromises depth perception, spatial orientation field of view.Suturing is one the most complex tasks performed under these circumstances.Key components this are interplay between needle holder surgical...
Purpose: Machine learning models can only be reliably evaluated if training, validation, and test data splits are representative not affected by the absence of classes interest. Surgical workflow instrument recognition tasks complicated in this manner, because heavy imbalances resulting from different lengths phases their erratic occurrences. Furthermore, issue becomes difficult as sub-properties that help define phases, like (co-)occurrence, usually considered when defining split. We argue...
Phantoms for surgical training are able to mimic cutting and suturing properties patient-individual shape of organs, but lack a realistic visual appearance that captures the heterogeneity scenes. In order overcome this in endoscopic approaches, hyperrealistic concepts have been proposed be used an augmented reality-setting, which based on deep image-to-image transformation methods. Such generate representations phantoms learned from real intraoperative sequences. Conditioned frames process,...
Minimally Invasive Surgery (MIS) techniques have gained rapid popularity among surgeons since they offer significant clinical benefits including reduced recovery time and diminished post-operative adverse effects. However, conventional endoscopic systems output monocular video which compromises depth perception, spatial orientation field of view. Suturing is one the most complex tasks performed under these circumstances. Key components this are interplay between needle holder surgical...
To support minimally-invasive intraoperative mitral valve repair, quantitative measurements from the can be obtained using an infra-red tracked stylus. It is desirable to view such manually measured points together with endoscopic image for further assistance. Therefore, hand-eye calibration required that links both coordinate systems and a prerequisite project onto plane. A complementary approach this use vision-based stereo-setup detect triangulate of interest, obtain 3D coordinates. In...