The Helmholtz-Zentrum Hereon is operating imaging beamlines for X-ray tomography (P05 IBL, P07 HEMS) for academic and industrial users at the synchrotron-radiation source PETRA III at DESY in Hamburg, Germany. The high flux density and coherence of synchrotron radiation enable high-resolution in situ/operando/in vivo tomography experiments and phase-contrast imaging techniques, respectively. Large amounts of 3D and 4D data are collected that are difficult to process and analyze. Recently, we have explored machine learning approaches for the reconstruction, processing and analysis of synchrotron-radiation tomography data. Here, we report on the application of supervised learning for multimodal data analysis to generate a virtual 3D histology, digital volume correlation of 4D in situ tomography data, and instance segmentation. Furthermore, we present findings related to unsupervised learning in the context of semantic segmentation.
The Helmholtz-Zentrum Hereon is operating imaging beamlines for X-ray tomography (P05 IBL, P07 HEMS) for academic and industrial users at the synchrotron radiation source PETRA III at DESY in Hamburg, Germany. The high X-ray flux density and coherence of synchrotron radiation enables high-resolution in situ/operando/vivo tomography experiments and provides phase contrast, respectively. Large amounts of 3D/4D data are collected that are difficult to process and analyze. Here, we report on the application of machine learning for image segmentation including a guided interactive framework, multimodal data analysis (virtual histology), image enhancement (denoising), and self-supervised learning for phase retrieval.
KEYWORDS: Tomography, Image segmentation, Monte Carlo methods, Performance modeling, Bone, Process modeling, Data acquisition, Analytical research, Web services, Synchrotron radiation
The Helmholtz-Zentrum Hereon is operating several tomography end stations at the beamlines P05 and P07 of the synchrotron radiation facility PETRA III at DESY in Hamburg, Germany. Attenuation and phase contrast imaging techniques are provided as well as sample environments for in situ/operando/vivo experiments for applications in biology, medicine, materials science, etc. Very large and diverse data sets with varying spatiotemporal resolution, noise levels and artifacts are acquired which are challenging to process and analyze. Here we report on an active learning approach for the semantic segmentation of tomography data using a guided and interactive framework, and evaluate different acquisition functions for the selection of images to be annotated in the iterative process.
A load frame for in situ mechanical testing is developed for the microtomography end stations at the imaging beamline P05 and the high-energy material science beamline P07 of PETRA III at DESY, both operated by the Helmholtz- Zentrum Geesthacht. The load frame is fully integrated into the beamline control system and can be controlled via a feedback loop. All relevant parameters (load, displacement, temperature, etc.) are continuously logged. It can be operated in compression or tensile mode applying forces of up to 1 kN and is compatible with all contrast modalities available at IBL and HEMS i.e. conventional attenuation contrast, propagation based phase contrast and differential phase contrast using a grating interferometer. The modularity and flexibility of the load frame allows conducting a wide range of experiments. E.g. compression tests to understand the failure mechanisms in biodegradable implants in rat bone or to investigate the mechanics and kinematics of the tessellated cartilage skeleton of sharks and rays, or tensile tests to illuminate the structure-property relationship in poplar tension wood or to visualize the 3D deformation of the tendonbone insertion. We present recent results from the experiments described including machine-learning driven volume segmentation and digital volume correlation of load tomography sequences.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.