TY - CONF A1 - Tsamos, Athanasios T1 - CNN Architectures for Image Processing. N2 - Deep Convolutional Neural Networks (DCNNs) and their applications in (XCT) data conditioning and automatic segmentation. A case study in Al-Si MMCs with synthetic training data. T2 - EUROLAB-D Tagung: KI im Prüflabor: Chancen und Herausforderungen von Künstlicher Intelligenz für akkreditierte Stellen CY - Berlin, Germany DA - 14.11.2023 KW - Automatic Segmentation KW - XCT KW - Artificial Intelligence KW - Synthetic Training Data PY - 2023 AN - OPUS4-59093 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - CONF A1 - Tsamos, Athanasios T1 - Denoising, Deblurring and Automatic Segmentation of XCT Data with Deep Learning and Synthetic XCT Training Data. A Case Study on Al-Si MMCs. N2 - 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. T2 - 12th International Conference on Industrial Computed Tomography (iCT2023) CY - Fürth, Germany DA - 27.02.2023 KW - Automatic Segmentation KW - Denoising Deblurring Sharpening KW - Artificial Intelligence KW - DCNNs KW - Synthetic Training Data KW - XCT PY - 2023 AN - OPUS4-59095 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER - TY - JOUR A1 - Tsamos, Athanasios A1 - Evsevleev, Sergei A1 - Fioresi, Rita A1 - Faglioni, Francesco A1 - Bruno, Giovanni T1 - A Complete Strategy to Achieve High Precision Automatic Segmentation of Challenging Experimental X‐Ray Computed Tomography Data Using Low‐Resemblance Synthetic Training Data N2 - 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. KW - Automatic Segmentation KW - XCT KW - Artificial Intelligence KW - Synthetic Training Data KW - i.S.Sy.Da.T.A. KW - BAM SynthMAT KW - BAM SynthCOND KW - Triple UNet KW - Convolutional Neural Network (DCNN) PY - 2023 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-590912 DO - https://doi.org/10.1002/adem.202301030 SN - 1438-1656 VL - 26 IS - 2 SP - 1 EP - 9 PB - Wiley online library AN - OPUS4-59091 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER -