4 results
Search Results
Now showing 1 - 4 of 4
- ItemEvolutionary 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, SylvainAn 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.
- ItemRetrieving spin textures on curved magnetic thin films with full-field soft X-ray microscopies([London] : Nature Publishing Group UK, 2015) Streubel, Robert; Kronast, Florian; Fischer, Peter; Parkinson, Dula; Schmidt, Oliver G.; Makarov, DenysX-ray tomography is a well-established technique to characterize 3D structures in material sciences and biology; its magnetic analogue--magnetic X-ray tomography--is yet to be developed. Here we demonstrate the visualization and reconstruction of magnetic domain structures in a 3D curved magnetic thin films with tubular shape by means of full-field soft X-ray microscopies. The 3D arrangement of the magnetization is retrieved from a set of 2D projections by analysing the evolution of the magnetic contrast with varying projection angle. Using reconstruction algorithms to analyse the angular evolution of 2D projections provides quantitative information about domain patterns and magnetic coupling phenomena between windings of azimuthally and radially magnetized tubular objects. The present approach represents a first milestone towards visualizing magnetization textures of 3D curved thin films with virtually arbitrary shape.
- ItemPseudo-chemotaxis of active Brownian particles competing for food(San Francisco, California, US : PLOS, 2020) Merlitz, Holger; Vuijk, Hidde D.; Wittmann, René; Sharma, Abhinav; Sommer, Jens-UweActive Brownian particles (ABPs) are physical models for motility in simple life forms and easily studied in simulations. An open question is to what extent an increase of activity by a gradient of fuel, or food in living systems, results in an evolutionary advantage of actively moving systems such as ABPs over non-motile systems, which rely on thermal diffusion only. It is an established fact that within confined systems in a stationary state, the activity of ABPs generates density profiles that are enhanced in regions of low activity, which is thus referred to as ‘anti-chemotaxis’. This would suggest that a rather complex sensoric subsystem and information processing is a precondition to recognize and navigate towards a food source. We demonstrate in this work that in non-stationary setups, for instance as a result of short bursts of fuel/food, ABPs do in fact exhibit chemotactic behavior. In direct competition with inactive, but otherwise identical Brownian particles (BPs), the ABPs are shown to fetch a larger amount of food. We discuss this result based on simple physical arguments. From the biological perspective, the ability of primitive entities to move in direct response to the available amount of external energy would, even in absence of any sensoric devices, encompass an evolutionary advantage.
- ItemSurface effects of vapour-liquid-solid driven Bi surface droplets formed during molecular-beam-epitaxy of GaAsBi([London] : Macmillan Publishers Limited, part of Springer Nature, 2016) Steele, J.A.; Lewis, R.A.; Horvat, J.; Nancarrow, M.J.B.; Henini, M.; Fan, D.; Mazur, Y.I.; Schmidbauer, M.; Ware, M.E.; Yu, S.-Q.; Salamo, G.J.Herein we investigate a (001)-oriented GaAs1−xBix/GaAs structure possessing Bi surface droplets capable of catalysing the formation of nanostructures during Bi-rich growth, through the vapour-liquid-solid mechanism. Specifically, self-aligned “nanotracks” are found to exist trailing the Bi droplets on the sample surface. Through cross-sectional high-resolution transmission electron microscopy the nanotracks are revealed to in fact be elevated above surface by the formation of a subsurface planar nanowire, a structure initiated mid-way through the molecular-beam-epitaxy growth and embedded into the epilayer, via epitaxial overgrowth. Electron microscopy studies also yield the morphological, structural and chemical properties of the nanostructures. Through a combination of Bi determination methods the compositional profile of the film is shown to be graded and inhomogeneous. Furthermore, the coherent and pure zincblende phase property of the film is detailed. Optical characterisation of features on the sample surface is carried out using polarised micro-Raman and micro-photoluminescence spectroscopies. The important light producing properties of the surface nanostructures are investigated through pump intensity-dependent micro-PL measurements, whereby relatively large local inhomogeneities are revealed to exist on the epitaxial surface for important optical parameters. We conclude that such surface effects must be considered when designing and fabricating optical devices based on GaAsBi alloys.