Maj Stenmark
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Maj Stenmark has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
Phan-Kiet Tran
Pediatric Cardiac Surgery, Children’s Heart Center, Skåne University Hospital, Lund, Sweden
3 shared publicationsMåns Magnusson
Pediatric Cardiac Surgery, Children's Heart Center, Skåne University Hospital, Lund, Sweden
2 shared publications- Andreas Stolt
Lund University
1 shared publication - Edin Omerbasic
Pediatric Cardiac Surgery, Children's Heart Center, Skåne University Hospital, Lund, Sweden
1 shared publication Edin Omerbašić
Cardiac Surgery Unit, Children’s Heart Centre, Skåne University Hospital
1 shared publication- Jacek Malec
Lund University
1 shared publication
Latest Publications
- Open Access
- 6 August 2026
- Published by Springer Nature in Journal of Robotic Surgery
- Vol. 20 (1) , 801
Artificial intelligence-supported segmentation of cardiac anatomy in open-heart surgery videos
Accurate identification of anatomical structures is essential for safe congenital cardiac surgery and for the development of assistive robotic systems. However, scalable annotation of open-heart surgical video remains a major challenge due to dynamic tissue motion, occlusion, and anatomical variability. The aim of this study was to develop and evaluate a human-in-the-loop segmentation and tracking pipeline for congenital open-heart surgery videos. A dataset of 72 annotated video clips comprising 27,461 frames was created from routine recordings of congenital cardiac surgery. Independent tracking evaluation was performed on 6 video clips (2,400 frames) from three surgical cases that were not used for training or validation. A hybrid framework combining fine-tuned Segment Anything Model 2 (SAM 2) for propagation-based tracking and YOLOv11 for detection-based monitoring was implemented and evaluated. Fine-tuning improved temporal tracking performance compared with the pretrained model, increasing the mean IoU from 82.1% to 92.2% and the proportion of frames with IoU ≥ 90% from 48.2% to 72.3% on the independent evaluation dataset. A graphical user interface enabled efficient dataset creation, reducing annotation time by approximately 40-fold compared with manual tracing. This study demonstrates that domain-adapted foundation-model tracking can provide robust anatomical tracking in a dynamic open surgical environment and offers a scalable framework for future assistive and robotic cardiac applications.
- 6 August 2026
- Published by Springer Nature in Journal of Robotic Surgery
- Vol. 20 (1) , 801
Open AccessArtificial intelligence-supported segmentation of cardiac anatomy in open-heart surgery videos
Accurate identification of anatomical structures is essential for safe congenital cardiac surgery and for the development of assistive robotic systems. However, scalable annotation of open-heart surgical video remains a major challenge due to dynamic tissue motion, occlusion, and anatomical variability. The aim of this study was to develop and evaluate a human-in-the-loop segmentation and tracking pipeline for congenital open-heart surgery videos. A dataset of 72 annotated video clips comprising 27,461 frames was created from routine recordings of congenital cardiac surgery. Independent tracking evaluation was performed on 6 video clips (2,400 frames) from three surgical cases that were not used for training or validation. A hybrid framework combining fine-tuned Segment Anything Model 2 (SAM 2) for propagation-based tracking and YOLOv11 for detection-based monitoring was implemented and evaluated. Fine-tuning improved temporal tracking performance compared with the pretrained model, increasing the mean IoU from 82.1% to 92.2% and the proportion of frames with IoU ≥ 90% from 48.2% to 72.3% on the independent evaluation dataset. A graphical user interface enabled efficient dataset creation, reducing annotation time by approximately 40-fold compared with manual tracing. This study demonstrates that domain-adapted foundation-model tracking can provide robust anatomical tracking in a dynamic open surgical environment and offers a scalable framework for future assistive and robotic cardiac applications.
- Open Access
- 16 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 1288-1292
Quest2ROS2: A ROS 2 Framework for Bi-manual VR Teleoperation
- 16 March 2026
- Published by Association for Computing Machinery (ACM)
- p. 1288-1292
Open AccessQuest2ROS2: A ROS 2 Framework for Bi-manual VR Teleoperation
- Open Access
- 23 March 2023
- Published by Elsevier in Journal of Innovation & Knowledge
- Vol. 8 (2)
A socio-institutional perspective on the reluctance among the elderly concerning the commercialization of 3D surgical video technology in Sweden
- 23 March 2023
- Published by Elsevier in Journal of Innovation & Knowledge
- Vol. 8 (2)
Open AccessA socio-institutional perspective on the reluctance among the elderly concerning the commercialization of 3D surgical video technology in Sweden
- Open Access
- 1 March 2022
- Published by Elsevier in Journal of Surgical Research
- Vol. 271, 106-116
Vision-Based Tracking of Surgical Motion During Live Open-Heart Surgery
- 1 March 2022
- Published by Elsevier in Journal of Surgical Research
- Vol. 271, 106-116
Open AccessVision-Based Tracking of Surgical Motion During Live Open-Heart Surgery
- 12 August 2021
- Published by MyJove Corporation in Journal of Visualized Experiments
- No. 174,p. e62786
Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery
Stereo 3D video from surgical procedures can be highly valuable for medical education and improve clinical communication. But access to the operating room and the surgical field is restricted. It is a sterile environment, and the physical space is crowded with surgical staff and technical equipment. In this setting, unobscured capture and realistic reproduction of the surgical procedures are difficult. This paper presents a method for rapid and reliable data collection of stereoscopic 3D videos at different camera baseline distances and distances of convergence. To collect test data with minimum interference during surgery, with high precision and repeatability, the cameras were attached to each hand of a dual-arm robot. The robot was ceiling-mounted in the operating room. It was programmed to perform a timed sequence of synchronized camera movements stepping through a range of test positions with baseline distance between 50-240 mm at incremental steps of 10 mm, and at two convergence distances of 1100 mm and 1400 mm. Surgery was paused to allow 40 consecutive 5-s video samples. A total of 10 surgical scenarios were recorded.
- 12 August 2021
- Published by MyJove Corporation in Journal of Visualized Experiments
- No. 174,p. e62786
Robotized Testing of Camera Positions to Determine Ideal Configuration for Stereo 3D Visualization of Open-Heart Surgery
Stereo 3D video from surgical procedures can be highly valuable for medical education and improve clinical communication. But access to the operating room and the surgical field is restricted. It is a sterile environment, and the physical space is crowded with surgical staff and technical equipment. In this setting, unobscured capture and realistic reproduction of the surgical procedures are difficult. This paper presents a method for rapid and reliable data collection of stereoscopic 3D videos at different camera baseline distances and distances of convergence. To collect test data with minimum interference during surgery, with high precision and repeatability, the cameras were attached to each hand of a dual-arm robot. The robot was ceiling-mounted in the operating room. It was programmed to perform a timed sequence of synchronized camera movements stepping through a range of test positions with baseline distance between 50-240 mm at incremental steps of 10 mm, and at two convergence distances of 1100 mm and 1400 mm. Surgery was paused to allow 40 consecutive 5-s video samples. A total of 10 surgical scenarios were recorded.
- 1 January 2015
- Published by Springer Nature
- p. 189-202
From High-Level Task Descriptions to Executable Robot Code
- 1 January 2015
- Published by Springer Nature
- p. 189-202
From High-Level Task Descriptions to Executable Robot Code