Filtern
Dokumenttyp
- Zeitschriftenartikel (5)
- Vortrag (3)
Sprache
- Englisch (8)
Schlagworte
Organisationseinheit der BAM
Eingeladener Vortrag
- nein (3)
The greatest challenge when using deep convolutional neural networks (DCNNs) for automatic segmentation of microstructural X-ray computed tomography (XCT) data is the acquisition of sufficient and relevant data to train the working network. Traditionally, these have been attained by manually annotating a few slices for 2D DCNNs. However, complex multiphase microstructures would presumably be better segmented with 3D networks. However, manual segmentation labeling for 3D problems is prohibitive. In this work, we introduce a method for generating synthetic XCT data for a challenging six-phase Al–Si alloy composite reinforced with ceramic fibers and particles. Moreover, we propose certain data augmentations (brightness, contrast, noise, and blur), a special in-house designed deep convolutional neural network (Triple UNet), and a multi-view forwarding strategy to promote generalized learning from synthetic data and therefore achieve successful segmentations. We obtain an overall Dice score of 0.77. Lastly, we prove the detrimental effects of artifacts in the XCT data on achieving accurate segmentations when synthetic data are employed for training the DCNNs. The methods presented in this work are applicable to other materials and imaging techniques as well. Successful segmentation coupled with neural networks trained with synthetic data will accelerate scientific output.
Irrespective of the experimental care used to acquire Computed Tomography Data, certain artifacts might still exist such as: Noise, Blurring, Ring Artifacts etc. To tackle this problem, a complete multi-level framework employing AI (Deep Artificial Neural Nets), targeting specific artifacts individually, is presented. The goal is to render the data suitable for subsequent unproblematic segmentation without any loss of information, compared to manual conditioning with traditional filters.
The strategy can therefore be used to acquire faster CT data (e.g. in-situ investigations) and ensure legacy with existing data obtained, perhaps, on older instruments.
Regardless of the experimental care practiced in acquiring X-ray computed tomography (XCT) data, artifacts might still exist, such as noise and blur. This is typical for fast XCT data acquisitions (e.g., in-situ investigations), or low-dose XCT. Such artifacts can complicate subsequent analysis of the data. Digital filters can moderately cure extensive artifacts. The selection of filter type, intensity, and order of application is not always straight forward. To tackle these problems, a complete sequential multilevel, multi-scale framework: BAM SynthCOND, employing newly designed deep convolutional neural networks (DCNNs), was formulated. Although data conditioning with neural networks is not uncommon, the main complication is that completely artifact-free XCT data for training do not exist. Thus, training data were acquired from an in-house developed library (BAM SynthMAT) capable of generating synthetic XCT material microstructures. Some novel DCNN architectures were introduced (2D/3D ACEnet_Denoise, 2D/3D ACEnet_Deblur) along with the concept of Assertive Contrast Enhancement (ACE) training, which boosts the performance of neural networks trained with continuous loss functions. The proposed methodology accomplished very good generalization from low resemblance synthetic training data. Indeed, denoising, sharpening (deblurring), and even ring artifact removal performance were achieved on experimental post-CT scans of challenging multiphase Al-Si Metal Matrix Composite (MMC) microstructures. The conditioning efficiencies were: 92% for combined denoising/sharpening, 99% for standalone denoising, and 95% for standalone sharpening. The results proved to be independent of the artifact intensity. We believe that the novel concepts and methodology developed in this work can be directly applied on the CT projections prior to reconstruction, or easily be extended to other imaging techniques such as: Microscopy, Neutron Tomography, Ultrasonics, etc.
The osseointegration in/around additively manufactured (AM) lattice structures of a new titanium alloy, Ti–19Nb–14Zr, was evaluated. Different lattices with increasingly high sidewalls gradually closing them were manufactured and implanted in sheep. After removal, the bone–interface implant (BII) and bone–implant contact (BIC) were studied from 3D X-ray computed tomography images. Measured BII of less than 10 µm and BIC of 95% are evidence of excellent osseointegration.
Since AMnaturally leads to a high-roughness surface finish, the wettability of the implant is increased.
The new alloy possesses an increased affinity to the bone. The lattice provides crevices in which the biological tissue can jump in and cling. The combination of these factors is pushing ossification beyond its natural limits. Therefore, the quality and speed of the ossification and osseointegration in/around these Ti–19Nb–14Zr laterally closed lattice implants open the possibility of bone spline key of prostheses. This enables the stabilization of the implant into the bone while keeping the possibility of punctual hooks allowing the implant to be removed more easily if required. Thus, this new titanium alloy and such laterally closed lattice structures are appropriate candidates to be implemented in a new generation of implants.
We propose a novel iterative segmentation algorithm (i.S.Sy.Da.T.A: Iterative Segmentation Synthetic Data Training Algorithm) employing Deep Convolutional Neural Networks and synthetic training data for X-ray tomographic reconstructions of complex microstructures. In our method, we reinforce the synthetic training data with experimental XCT datasets that were automatically segmented in the previous iteration. This strategy produces better segmentations in successive iterations. We test our algorithm with experimental XCT re constructions of a 6-phase Al-Si Matrix Composite reinforced with ceramic fibers and particles. We perform the analysis in 3D with a special network architecture that demonstrates good generalization with synthetic training data. We show that our iterative algorithm returns better segmentations compared to the standard single training approach. More specifically, phases possessing similar attenuation coefficients can be better segmented: for Al2O3 fibers, SiC particles, and Intermetallics, we see an increase of the Dice score with respect to the classic approach: from 0.49 to 0.54, from 0.66 to 0.72, and from 0.55 to 0.66 respectively. Furthermore, the overall Dice score increases from 0.77 to 0.79. The methods presented in this work are also applicable to other materials and imaging techniques.
It is shown that preconditioning of experimental X‐ray computed tomography (XCT) data is critical to achieve high‐precision segmentation scores. The challenging experimental XCT datasets and deep convolutional neural networks (DCNNs) are used that are trained with low‐resemblance synthetic XCT data. The material used is a 6‐phase Al–Si metal matrix composite‐reinforced with ceramic fibers and particles. To achieve generalization, in our past studies, specific data augmentation techniques were proposed for the synthetic XCT training data. In addition, two toolsets are devised: (1) special 3D DCNN architecture (3D Triple_UNet), slicing the experimental XCT data from multiple views (MultiView Forwarding), the i.S.Sy.Da.T.A. iterative segmentation algorithm, and (2) nonlocal means (NLM) conditioning (filtering) for the experimental XCT data. This results in good segmentation Dice scores across all phases compared to more standard approaches (i.e., standard UNet architecture, single view slicing, standard single training, and NLM conditioning). Herein, the NLM filter is replaced with the deep conditioning framework BAM SynthCOND introduced in a previous publication, which can be trained with synthetic XCT data. This leads to a significant segmentation precision increase for all phases. The proposed methods are potentially applicable to other materials and imaging techniques.
We employ in-house generated synthetic Al-Si matrix composite XCT data for training deep convolutional neural networks for XCT data conditioning and automatic segmentation. We propose an in-house multilevel deep conditioning framework capable of rectifying noise and blur in corrupted XCT data sequentially. Furthermore, for automatic segmentation, we utilize a special in-house network coupled with a novel iterative segmentation algorithm capable of generalized learning from synthetic data. We report a consistent SSIM efficiency of 92%, 99%, and 95% for the combined denoising/deblurring, standalone denoising, and standalone deblurring, respectively. The overall segmentation precision was over 85% according to the Dice coefficient. We used experimental XCT data from various scans of Al-Si matrix composites reinforced with ceramic particles and fibers.