Lennart Karstensen
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Lennart Karstensen has a total of 50 co-authors. Here are the top co-authors by number of shared publications:
- Franziska Mathis-Ullrich
Dep. Artificial Intelligence in Biomedical Engineering, Friedrich-Alexander-Universität Erlangen-Nürnberg, Erlangen , Germany
6 shared publications Christian Uhl
Department of Vascular Surgery, University Hospital RWTH Aachen, Aachen, 52074, Germany
5 shared publications- Harry Robertshaw
School of Biomedical Engineering and Imaging Sciences, King's College London, London, WC2R 2LS, United Kingdom
4 shared publications Jens Langejürgen
Clinical Health Technologies, Fraunhofer IPA, Mannheim, 68167, Germany
4 shared publicationsJacqueline Ritter
Fraunhofer IPA, Mannheim, Germany
3 shared publications- Johannes Hatzl
Department of Vascular and Endovascular Surgery, University Hospital Heidelberg, 69120 Heidelberg, Germany
3 shared publications
Latest Publications
- Open Access
- 7 April 2026
- Published by Wolters Kluwer Health in Journal of the American Heart Association
- Vol. 15 (7) , e044931
A Position Statement on Endovascular Models and Effectiveness Metrics for Mechanical Thrombectomy Navigation, on Behalf of the Stakeholder Taskforce for Artificial Intelligence–Assisted Robotic Thrombectomy (START)
Although we are making progress in overcoming infectious diseases and cancer, one of the major medical challenges of the mid‐21st century will be the increasing prevalence of stroke. Occlusions in large vessels are especially debilitating, yet effective treatment—needed within hours to achieve best outcomes—remains limited because of geographic accessibility. One solution for improving timely access to mechanical thrombectomy in geographically diverse populations is the widespread deployment of robotic surgical systems. Artificial intelligence assistance may enable the safe and effective upskilling of operators in this emerging therapeutic delivery approach. Our aim was to establish consensus frameworks for developing and validating artificial intelligence–assisted robots for thrombectomy. Objectives included standardizing effectiveness metrics and defining reference testbeds across in silico, in vitro, ex vivo, and in vivo environments. To achieve this, we convened experts in neurointervention, robotics, data science, health economics, policy, statistics, and patient advocacy. Consensus was built through an incubator day, a Delphi process, and a final position statement. We identified that the 4 essential testbed environments each had distinct validation roles. Realism requirements vary: simpler testbeds should include realistic vessel anatomy compatible with guidewire and catheter use, whereas standard testbeds should incorporate deformable vessels. More advanced testbeds should include blood flow, pulsatility, and disease features, such as atheromatous plaques. There are 2 macroclasses of effectiveness metrics: one for in silico, in vitro, and ex vivo stages focusing on technical navigation (eg, path‐following error), and another for in vivo stages, focused on clinical outcomes (eg, modified treatment in cerebral infarction scores). Patient safety is central, and not a barrier, to this technology's development. One requisite patient safety task needed now is to correlate in vitro measurements to in vivo complications.
- 7 April 2026
- Published by Wolters Kluwer Health in Journal of the American Heart Association
- Vol. 15 (7) , e044931
Open AccessA Position Statement on Endovascular Models and Effectiveness Metrics for Mechanical Thrombectomy Navigation, on Behalf of the Stakeholder Taskforce for Artificial Intelligence–Assisted Robotic Thrombectomy (START)
Although we are making progress in overcoming infectious diseases and cancer, one of the major medical challenges of the mid‐21st century will be the increasing prevalence of stroke. Occlusions in large vessels are especially debilitating, yet effective treatment—needed within hours to achieve best outcomes—remains limited because of geographic accessibility. One solution for improving timely access to mechanical thrombectomy in geographically diverse populations is the widespread deployment of robotic surgical systems. Artificial intelligence assistance may enable the safe and effective upskilling of operators in this emerging therapeutic delivery approach. Our aim was to establish consensus frameworks for developing and validating artificial intelligence–assisted robots for thrombectomy. Objectives included standardizing effectiveness metrics and defining reference testbeds across in silico, in vitro, ex vivo, and in vivo environments. To achieve this, we convened experts in neurointervention, robotics, data science, health economics, policy, statistics, and patient advocacy. Consensus was built through an incubator day, a Delphi process, and a final position statement. We identified that the 4 essential testbed environments each had distinct validation roles. Realism requirements vary: simpler testbeds should include realistic vessel anatomy compatible with guidewire and catheter use, whereas standard testbeds should incorporate deformable vessels. More advanced testbeds should include blood flow, pulsatility, and disease features, such as atheromatous plaques. There are 2 macroclasses of effectiveness metrics: one for in silico, in vitro, and ex vivo stages focusing on technical navigation (eg, path‐following error), and another for in vivo stages, focused on clinical outcomes (eg, modified treatment in cerebral infarction scores). Patient safety is central, and not a barrier, to this technology's development. One requisite patient safety task needed now is to correlate in vitro measurements to in vivo complications.
- Open Access
- 13 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (4) , 4745-4752
Toward AI Autonomous Navigation for Mechanical Thrombectomy Using Hierarchical Modular Multi-Agent Reinforcement Learning (HM-MARL)
Mechanical thrombectomy (MT) is typically the optimal treatment for acute ischemic stroke involving large vessel occlusions, but access is limited due to geographic and logistical barriers. Reinforcement learning (RL) shows promise in autonomous endovascular navigation, but generalization across ‘long’ navigation tasks remains challenging. We propose a Hierarchical Modular Multi-Agent Reinforcement Learning (HM-MARL) framework for autonomous two-device navigation in vitro, enabling efficient and generalizable navigation. HM-MARL was developed to autonomously navigate a guide catheter and guidewire from the femoral artery to the internal carotid artery (ICA). A modular multi-agent approach was used to decompose the complex navigation task into specialized subtasks, each trained using Soft Actor-Critic RL. The framework was validated in both in silico and in vitro testbeds to assess generalization and real-world feasibility. In silico, a single-vasculature model achieved 92–100% success rates on individual anatomies, while a multi-vasculature model achieved 56–80% across multiple patient anatomies. In vitro, both HM-MARL models successfully navigated 100% of trials from the femoral artery to the right common carotid artery and 80% to the right ICA but failed on the left-side vessel superhuman challenge due to the anatomy and catheter type used in navigation. This study presents the first demonstration of in vitro autonomous navigation in MT vasculature. While HM-MARL enables generalization across anatomies, the simulation-to-real transition introduces challenges. Future work will refine RL strategies using world models and validate performance on unseen in vitro data, advancing autonomous MT towards clinical translation.
- 13 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Robotics and Automation Letters
- Vol. 11 (4) , 4745-4752
Open AccessToward AI Autonomous Navigation for Mechanical Thrombectomy Using Hierarchical Modular Multi-Agent Reinforcement Learning (HM-MARL)
Mechanical thrombectomy (MT) is typically the optimal treatment for acute ischemic stroke involving large vessel occlusions, but access is limited due to geographic and logistical barriers. Reinforcement learning (RL) shows promise in autonomous endovascular navigation, but generalization across ‘long’ navigation tasks remains challenging. We propose a Hierarchical Modular Multi-Agent Reinforcement Learning (HM-MARL) framework for autonomous two-device navigation in vitro, enabling efficient and generalizable navigation. HM-MARL was developed to autonomously navigate a guide catheter and guidewire from the femoral artery to the internal carotid artery (ICA). A modular multi-agent approach was used to decompose the complex navigation task into specialized subtasks, each trained using Soft Actor-Critic RL. The framework was validated in both in silico and in vitro testbeds to assess generalization and real-world feasibility. In silico, a single-vasculature model achieved 92–100% success rates on individual anatomies, while a multi-vasculature model achieved 56–80% across multiple patient anatomies. In vitro, both HM-MARL models successfully navigated 100% of trials from the femoral artery to the right common carotid artery and 80% to the right ICA but failed on the left-side vessel superhuman challenge due to the anatomy and catheter type used in navigation. This study presents the first demonstration of in vitro autonomous navigation in MT vasculature. While HM-MARL enables generalization across anatomies, the simulation-to-real transition introduces challenges. Future work will refine RL strategies using world models and validate performance on unseen in vitro data, advancing autonomous MT towards clinical translation.
- Open Access
- 15 August 2025
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 196 (Pt C) , 110844
Learning-based autonomous navigation, benchmark environments and simulation framework for endovascular interventions
- 15 August 2025
- Published by Elsevier in Computers in Biology and Medicine
- Vol. 196 (Pt C) , 110844
Open AccessLearning-based autonomous navigation, benchmark environments and simulation framework for endovascular interventions
- Open Access
Learning-Based Autonomous Navigation, Benchmark Environments and Simulation Framework for Endovascular Interventions
Endovascular interventions are a life-saving treatment for many diseases, yet suffer from drawbacks such as radiation exposure and potential scarcity of proficient physicians. Robotic assistance during these interventions could be a promising support towards these problems. Research focusing on autonomous endovascular interventions utilizing artificial intelligence-based methodologies is gaining popularity. However, variability in assessment environments hinders the ability to compare and contrast the efficacy of different approaches, primarily due to each study employing a unique evaluation framework. In this study, we present deep reinforcement learning-based autonomous endovascular device navigation on three distinct digital benchmark interventions: BasicWireNav, ArchVariety, and DualDeviceNav. The benchmark interventions were implemented with our modular simulation framework stEVE (simulated EndoVascular Environment). Autonomous controllers were trained solely in simulation and evaluated in simulation and on physical test benches with camera and fluoroscopy feedback. Autonomous control for BasicWireNav and ArchVariety reached high success rates and was successfully transferred from the simulated training environment to the physical test benches, while autonomous control for DualDeviceNav reached a moderate success rate. The experiments demonstrate the feasibility of stEVE and its potential for transferring controllers trained in simulation to real-world scenarios. Nevertheless, they also reveal areas that offer opportunities for future research. This study demonstrates the transferability of autonomous controllers from simulation to the real world in endovascular navigation and lowers the entry barriers and increases the comparability of research on endovascular assistance systems by providing open-source training scripts, benchmarks and the stEVE framework.
Open AccessLearning-Based Autonomous Navigation, Benchmark Environments and Simulation Framework for Endovascular Interventions
Endovascular interventions are a life-saving treatment for many diseases, yet suffer from drawbacks such as radiation exposure and potential scarcity of proficient physicians. Robotic assistance during these interventions could be a promising support towards these problems. Research focusing on autonomous endovascular interventions utilizing artificial intelligence-based methodologies is gaining popularity. However, variability in assessment environments hinders the ability to compare and contrast the efficacy of different approaches, primarily due to each study employing a unique evaluation framework. In this study, we present deep reinforcement learning-based autonomous endovascular device navigation on three distinct digital benchmark interventions: BasicWireNav, ArchVariety, and DualDeviceNav. The benchmark interventions were implemented with our modular simulation framework stEVE (simulated EndoVascular Environment). Autonomous controllers were trained solely in simulation and evaluated in simulation and on physical test benches with camera and fluoroscopy feedback. Autonomous control for BasicWireNav and ArchVariety reached high success rates and was successfully transferred from the simulated training environment to the physical test benches, while autonomous control for DualDeviceNav reached a moderate success rate. The experiments demonstrate the feasibility of stEVE and its potential for transferring controllers trained in simulation to real-world scenarios. Nevertheless, they also reveal areas that offer opportunities for future research. This study demonstrates the transferability of autonomous controllers from simulation to the real world in endovascular navigation and lowers the entry barriers and increases the comparability of research on endovascular assistance systems by providing open-source training scripts, benchmarks and the stEVE framework.
- Open Access
- 28 May 2023
- Published by Springer Nature in International Journal of Computer Assisted Radiology and Surgery
- Vol. 18 (9) , 1735-1744
Recurrent neural networks for generalization towards the vessel geometry in autonomous endovascular guidewire navigation in the aortic arch
Purpose: Endovascular intervention is the state-of-the-art treatment for common cardiovascular diseases, such as heart attack and stroke. Automation of the procedure may improve the working conditions of physicians and provide high-quality care to patients in remote areas, posing a major impact on overall treatment quality. However, this requires the adaption to individual patient anatomies, which currently poses an unsolved challenge. Methods: This work investigates an endovascular guidewire controller architecture based on recurrent neural networks. The controller is evaluated in-silico on its ability to adapt to new vessel geometries when navigating through the aortic arch. The controller’s generalization capabilities are examined by reducing the number of variations seen during training. For this purpose, an endovascular simulation environment is introduced, which allows guidewire navigation in a parametrizable aortic arch. Results: The recurrent controller achieves a higher navigation success rate of 75.0% after 29,200 interventions compared to 71.6% after 156,800 interventions for a feedforward controller. Furthermore, the recurrent controller generalizes to previously unseen aortic arches and is robust towards size changes of the aortic arch. Being trained on 2048 aortic arch geometries gives the same results as being trained with full variation when evaluated on 1000 different geometries. For interpolation a gap of 30% of the scaling range and for extrapolation additional 10% of the scaling range can be navigated successfully. Conclusion: Adaption to new vessel geometries is essential in the navigation of endovascular instruments. Therefore, the intrinsic generalization to new vessel geometries poses an essential step towards autonomous endovascular robotics.
- 28 May 2023
- Published by Springer Nature in International Journal of Computer Assisted Radiology and Surgery
- Vol. 18 (9) , 1735-1744
Open AccessRecurrent neural networks for generalization towards the vessel geometry in autonomous endovascular guidewire navigation in the aortic arch
Purpose: Endovascular intervention is the state-of-the-art treatment for common cardiovascular diseases, such as heart attack and stroke. Automation of the procedure may improve the working conditions of physicians and provide high-quality care to patients in remote areas, posing a major impact on overall treatment quality. However, this requires the adaption to individual patient anatomies, which currently poses an unsolved challenge. Methods: This work investigates an endovascular guidewire controller architecture based on recurrent neural networks. The controller is evaluated in-silico on its ability to adapt to new vessel geometries when navigating through the aortic arch. The controller’s generalization capabilities are examined by reducing the number of variations seen during training. For this purpose, an endovascular simulation environment is introduced, which allows guidewire navigation in a parametrizable aortic arch. Results: The recurrent controller achieves a higher navigation success rate of 75.0% after 29,200 interventions compared to 71.6% after 156,800 interventions for a feedforward controller. Furthermore, the recurrent controller generalizes to previously unseen aortic arches and is robust towards size changes of the aortic arch. Being trained on 2048 aortic arch geometries gives the same results as being trained with full variation when evaluated on 1000 different geometries. For interpolation a gap of 30% of the scaling range and for extrapolation additional 10% of the scaling range can be navigated successfully. Conclusion: Adaption to new vessel geometries is essential in the navigation of endovascular instruments. Therefore, the intrinsic generalization to new vessel geometries poses an essential step towards autonomous endovascular robotics.
- Open Access
- 1 July 2022
- Published by Walter de Gruyter GmbH in Current Directions in Biomedical Engineering
- Vol. 8 (1) , 21-24
Quality-dependent Deep Learning for Safe Autonomous Guidewire Navigation
Cardiovascular diseases are the main cause of death worldwide. State-of-the-art treatment often includes the process of navigating endovascular instruments through the vasculature. Automation of the procedure receives much attention lately and may increase treatment quality and unburden clinicians. However, in order to ensure the patient’s safety the endovascular device needs to be steered carefully through the body. In this work, we present a collection of medical criteria that are considered by physicians during an intervention and that can be evaluated automatically enabling a highly objective assessment. Additionally, we trained an autonomous controller with deep reinforcement learning to gently navigate within a 2D simulation of an aortic arch. Among others, the controller reduced the maximum and mean contact force applied to the vessel walls by 43% and 29%, respectively.
- 1 July 2022
- Published by Walter de Gruyter GmbH in Current Directions in Biomedical Engineering
- Vol. 8 (1) , 21-24
Open AccessQuality-dependent Deep Learning for Safe Autonomous Guidewire Navigation
Cardiovascular diseases are the main cause of death worldwide. State-of-the-art treatment often includes the process of navigating endovascular instruments through the vasculature. Automation of the procedure receives much attention lately and may increase treatment quality and unburden clinicians. However, in order to ensure the patient’s safety the endovascular device needs to be steered carefully through the body. In this work, we present a collection of medical criteria that are considered by physicians during an intervention and that can be evaluated automatically enabling a highly objective assessment. Additionally, we trained an autonomous controller with deep reinforcement learning to gently navigate within a 2D simulation of an aortic arch. Among others, the controller reduced the maximum and mean contact force applied to the vessel walls by 43% and 29%, respectively.
- Open Access
- 23 May 2022
- Published by Springer Nature in International Journal of Computer Assisted Radiology and Surgery
- Vol. 17 (11) , 2033-2040
Learning-based autonomous vascular guidewire navigation without human demonstration in the venous system of a porcine liver
Purpose: The navigation of endovascular guidewires is a dexterous task where physicians and patients can benefit from automation. Machine learning-based controllers are promising to help master this task. However, human-generated training data are scarce and resource-intensive to generate. We investigate if a neural network-based controller trained without human-generated data can learn human-like behaviors. Methods: We trained and evaluated a neural network-based controller via deep reinforcement learning in a finite element simulation to navigate the venous system of a porcine liver without human-generated data. The behavior is compared to manual expert navigation, and real-world transferability is evaluated. Results: The controller achieves a success rate of 100% in simulation. The controller applies a wiggling behavior, where the guidewire tip is continuously rotated alternately clockwise and counterclockwise like the human expert applies. In the ex vivo porcine liver, the success rate drops to 30%, because either the wrong branch is probed, or the guidewire becomes entangled. Conclusion: In this work, we prove that a learning-based controller is capable of learning human-like guidewire navigation behavior without human-generated data, therefore, mitigating the requirement to produce resource-intensive human-generated training data. Limitations are the restriction to one vessel geometry, the neglected safeness of navigation, and the reduced transferability to the real world.
- 23 May 2022
- Published by Springer Nature in International Journal of Computer Assisted Radiology and Surgery
- Vol. 17 (11) , 2033-2040
Open AccessLearning-based autonomous vascular guidewire navigation without human demonstration in the venous system of a porcine liver
Purpose: The navigation of endovascular guidewires is a dexterous task where physicians and patients can benefit from automation. Machine learning-based controllers are promising to help master this task. However, human-generated training data are scarce and resource-intensive to generate. We investigate if a neural network-based controller trained without human-generated data can learn human-like behaviors. Methods: We trained and evaluated a neural network-based controller via deep reinforcement learning in a finite element simulation to navigate the venous system of a porcine liver without human-generated data. The behavior is compared to manual expert navigation, and real-world transferability is evaluated. Results: The controller achieves a success rate of 100% in simulation. The controller applies a wiggling behavior, where the guidewire tip is continuously rotated alternately clockwise and counterclockwise like the human expert applies. In the ex vivo porcine liver, the success rate drops to 30%, because either the wrong branch is probed, or the guidewire becomes entangled. Conclusion: In this work, we prove that a learning-based controller is capable of learning human-like guidewire navigation behavior without human-generated data, therefore, mitigating the requirement to produce resource-intensive human-generated training data. Limitations are the restriction to one vessel geometry, the neglected safeness of navigation, and the reduced transferability to the real world.
- 17 March 2022
- Published by Springer Nature
- p. 153-174
KI-Systeme für die nächste Medizintechnikgeneration
- 17 March 2022
- Published by Springer Nature
- p. 153-174
KI-Systeme für die nächste Medizintechnikgeneration
- Open Access
- 1 August 2021
- Published by Walter de Gruyter GmbH in Current Directions in Biomedical Engineering
- Vol. 7 (1) , 121-125
Facile Testbed for Robotic X-ray based Endovascular Interventions
Endovascular surgical robotics requires a facile and realistic testbed to validate control algorithms. This work compares methods to manufacture such a testbed. Utilizing animal tissue, a mannequin, and a low-voltage flow pump it is possible to perform catheter-based interventions with X-ray feedback for less than €300. The aim of this paper is to lower the entry hurdle for validating endovascular surgical robots by providing a method to build a facile and low-budget testbed.
- 1 August 2021
- Published by Walter de Gruyter GmbH in Current Directions in Biomedical Engineering
- Vol. 7 (1) , 121-125
Open AccessFacile Testbed for Robotic X-ray based Endovascular Interventions
Endovascular surgical robotics requires a facile and realistic testbed to validate control algorithms. This work compares methods to manufacture such a testbed. Utilizing animal tissue, a mannequin, and a low-voltage flow pump it is possible to perform catheter-based interventions with X-ray feedback for less than €300. The aim of this paper is to lower the entry hurdle for validating endovascular surgical robots by providing a method to build a facile and low-budget testbed.