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 JF - Advanced Engineering Materials 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 - TY - JOUR A1 - Lapenna, Michela A1 - Tsamos, Athanasios A1 - Faglioni, Francesco A1 - Fioresi, Rita A1 - Zanchetta, Ferdinando A1 - Bruno, Giovanni T1 - Geometric deep learning for enhanced quantitative analysis of microstructures in X-ray computed tomography data JF - Discover Applied Sciences N2 - Quantitative microstructural analysis of XCT 3D images is key for quality assurance of materials and components. In this paper we implement a Graph Convolutional Neural Network (GCNN) architecture to segment a complex Al-Si Metal Matrix composite XCT volume (3D image). We train the model on a synthetic dataset and we assess its performance on both synthetic and experimental, manually-labeled, datasets. Our simple GCNN shows a comparable performance, measured via the Dice score, to more standard machine learning methods, but uses a greatly reduced number of parameters (less than 1/10 of parameters), features low training time, and needs little hardware resources. Our GCNN thus achieves a cost-effective reliable segmentation. KW - Geometric deep learning KW - Segmentation KW - Microstructure KW - X-ray computed tomography KW - Al–Si metal matrix composites PY - 2024 UR - https://nbn-resolving.org/urn:nbn:de:kobv:b43-602517 DO - https://doi.org/10.1007/s42452-024-05985-0 SN - 3004-9261 VL - 6 SP - 1 EP - 9 AN - OPUS4-60251 LA - eng AD - Bundesanstalt fuer Materialforschung und -pruefung (BAM), Berlin, Germany ER -