Filters

2014 - 201922020 - 20231

More filters

2019 - 201912020 - 20242
Reset filters

Settings

Has files: Yes × Subject: article × Subject: procedures ×

Search Results

Now showing 1 - 3 of 3
  • Thumbnail Image
    Item
    Evolutionary design of explainable algorithms for biomedical image segmentation
    ([London] : Nature Publishing Group UK, 2023) Cortacero, Kévin; McKenzie, Brienne; Müller, Sabina; Khazen, Roxana; Lafouresse, Fanny; Corsaut, Gaëlle; Van Acker, Nathalie; Frenois, François-Xavier; Lamant, Laurence; Meyer, Nicolas; Vergier, Béatrice; Wilson, Dennis G.; Luga, Hervé; Staufer, Oskar; Dustin, Michael L.; Valitutti, Salvatore; Cussat-Blanc, Sylvain
    An unresolved issue in contemporary biomedicine is the overwhelming number and diversity of complex images that require annotation, analysis and interpretation. Recent advances in Deep Learning have revolutionized the field of computer vision, creating algorithms that compete with human experts in image segmentation tasks. However, these frameworks require large human-annotated datasets for training and the resulting “black box” models are difficult to interpret. In this study, we introduce Kartezio, a modular Cartesian Genetic Programming-based computational strategy that generates fully transparent and easily interpretable image processing pipelines by iteratively assembling and parameterizing computer vision functions. The pipelines thus generated exhibit comparable precision to state-of-the-art Deep Learning approaches on instance segmentation tasks, while requiring drastically smaller training datasets. This Few-Shot Learning method confers tremendous flexibility, speed, and functionality to this approach. We then deploy Kartezio to solve a series of semantic and instance segmentation problems, and demonstrate its utility across diverse images ranging from multiplexed tissue histopathology images to high resolution microscopy images. While the flexibility, robustness and practical utility of Kartezio make this fully explicable evolutionary designer a potential game-changer in the field of biomedical image processing, Kartezio remains complementary and potentially auxiliary to mainstream Deep Learning approaches.
  • Thumbnail Image
    Item
    Persistent effectivity of gas plasma-treated, long time-stored liquid on epithelial cell adhesion capacity and membrane morphology
    (San Francisco, CA : Public Library of Science, 2014) Hoentsch, M.; Bussiahn, R.; Rebl, H.; Bergemann, C.; Eggert, M.; Frank, M.; Von Woedtke, T.; Nebe, B.
    Research in plasma medicine includes a major interest in understanding gas plasma-cell interactions. The immediate application of gas plasma in vitro inhibits cell attachment, vitality and cell-cell contacts via the liquid. Interestingly, in our novel experiments described here we found that the liquid-mediated plasma effect is long-lasting after storage up to seven days; i. e. the liquid preserves the characteristics once induced by the argon plasma. Therefore, the complete Dulbecco's Modified Eagle cell culture medium was argon plasma-treated (atmospheric pressure, kINPen09) for 60 s, stored for several days (1, 4 and 7 d) at 37°C and added to a confluent mouse hepatocyte epithelial cell (mHepR1) monolayer. Impaired tight junction architecture as well as shortened microvilli on the cell membrane could be observed, which was accompanied by the loss of cell adhesion capacity. Online-monitoring of vital cells revealed a reduced cell respiration. Our first timedependent analysis of plasma-treated medium revealed that temperature, hydrogen peroxide production, pH and oxygen content can be excluded as initiators of cell physiological and morphological changes. The here observed persisting biological effects in plasma-treated liquids could open new medical applications in dentistry and orthopaedics.
  • Thumbnail Image
    Item
    Trapping self-propelled micromotors with microfabricated chevron and heart-shaped chips
    (Cambridge : Royal Society of Chemistry, 2014) Restrepo-Pérez, Laura; Soler, Lluís; Martínez-Cisneros, Cynthia S.; Sanchez, Samuel; Schmidt, Oliver G.
    We demonstrate that catalytic micromotors can be trapped in microfluidic chips containing chevron and heart-shaped structures. Despite the challenge presented by the reduced size of the traps, microfluidic chips with different trapping geometries can be fabricated via replica moulding. We prove that these microfluidic chips can capture micromotors without the need for any external mechanism to control their motion.