News

AI-based intra- and postoperative measurement from stereoimages
The publication "Redefining the Laparoscopic Spatial Sense: AI-based Intra- and Postoperative Measurement from Stereoimages“ has been accepted for the 38th AAAI Conference on Artificial Intelligence and is available via https://doi.org/10.48550/arXiv.2311.09744. The publication is the result of a fruitful collaboration between Karlsruhe Institute of Technology (KIT), Fraunhofer FIT, University of Bayreuth, and Charité – Universitätsmedizin Berlin. Authors are Leopold Müller, Patrick Hemmer, Moritz Queisner, Igor Sauer, Simeon Allmendinger, Johannes Jakubik, Michael Vössing, and Niklas Kühl.

A significant challenge in image-guided surgery is the accurate measurement task of relevant structures such as vessel segments, resection margins, or bowel lengths. While this task is an essential component of many surgeries, it involves substantial human effort and is prone to inaccuracies. In this paper, we develop a novel human-AI-based method for laparoscopic measurements utilizing stereo vision that has been guided by practicing surgeons. Based on a holistic qualitative requirements analysis, this work proposes a comprehensive measurement method, which comprises state-of-the-art machine learning architectures, such as RAFT-Stereo and YOLOv8. The developed method is assessed in various realistic experimental evaluation environments. Our results outline the potential of our method achieving high accuracies in distance measurements with errors below 1 mm. Furthermore, on-surface measurements demonstrate robustness when applied in challenging environments with textureless regions. Overall, by addressing the inherent challenges of image-guided surgery, we lay the foundation for a more robust and accurate solution for intra- and postoperative measurements, enabling more precise, safe, and efficient surgical procedures.

Stacks Image 23746
Back
Stacks Image 27655
Our manuscript "Depletion of donor dendritic cells ameliorates immunogenicity of both skin and hind limb transplants" has been accepted for publication in Frontiers in Immunology, section Alloimmunity and Transplantation. Authors are Muhammad Imtiaz Ashraf, Joerg Mengwasser, Anja Reutzel-Selke, Dietrich Polenz, Kirsten Führer, Steffen Lippert, Peter Tang, Edward Michaelis, Rusan Catar, Johann Pratschke, Christian Witzel, Igor M. Sauer, Stefan G. Tullius, and Barbara Kern.

Acute cellular rejection remains a significant obstacle affecting successful outcomes of organ transplantation including vascularized composite tissue allografts (VCA). Donor antigen presenting cells (APC), particularly dendritic cells (DC), orchestrate early alloimmune responses by activating recipient effector T cells. Employing a targeted approach, we investigated the impact of donor-derived conventional DC (cDC) and APC on the immunogenicity of skin and skin-containing VCA grafts, using mouse models of skin and hind limb transplantation.
By post-transplantation day 6, skin grafts demonstrated severe rejections, characterized by predominance of recipient CD4 T cells. In contrast, hind limb grafts showed moderate rejection, primarily infiltrated by CD8 T cells. While donor depletion of cDC and APC reduced frequencies, maturation, and activation of DC in all analysed tissues of skin transplant recipients, reduction in DC activities was only observed in the spleen of hind limb recipients. Donor cDC and APC depletion did not impact all lymphocyte compartments but significantly affected CD8 T cells and activated CD4 T in lymph nodes of skin recipients. Moreover, both donor APC and cDC depletion attenuated the Th17 immune response, evident by significantly reduced Th17 (CD4+IL-17+) cells in the spleen of skin recipients and reduced levels of IL-17E and lymphotoxin-α in the serum samples of both skin and hind limb recipients. In conclusion, our findings underscore the highly immunogenic nature of skin component in VCA. The depletion of donor APC and cDC mitigates the immunogenicity of skin grafts while exerting minimal impact on VCA.

Archive


Categories

Year

This website or its third-party tools use cookies, which are necessary to its functioning and required to achieve the purpose illustrated in the Disclaimer. By closing this banner, scrolling this page, clicking a link or continuing to browse otherwise, you agree to the use of cookies.