• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.37 no.2
• /
• pp.143-149
• /
• 2024

Segmentation of material phases through image analysis is essential for analyzing the microstructure of materials. Micro-CT images exhibit variations in grayscale values depending on the phases constituting the material. Phase segmentation is generally achieved by comparing the grayscale values in the images. In the case of waste concrete used as a recycled aggregate, it is challenging to distinguish between hydrated cement paste and natural aggregates, as these components exhibit similar grayscale values in micro-CT images. In this study, we propose a method for automatically separating the aggregates in concrete, in micro-CT images. Utilizing the Unet-VGG16 deep-learning network, we introduce a technique for segmenting the 2D aggregate images and stacking them to obtain 3D aggregate images. Image filtering is employed to separate aggregate particles from the selected 3D aggregate images. The performance of aggregate segmentation is validated through accuracy, precision, recall, and F1-score assessments.

• The Journal of Engineering Geology
• /
• v.28 no.3
• /
• pp.455-463
• /
• 2018

This study developed a method to quantitatively measure the size of cracks in concrete using X-ray CT images. We prepared samples with a diameter of 50 mm and a length of 100 mm by coring cracked concrete block that was obtained by chipping. We used a micro-focus X-ray CT, then applied the 3DMA method (3 Dimensional Medial axis Analysis) to the 3D CT images to find effective parameters for damage assessment. Finally, we quantitatively assessed the damage based on sample locations, using the damage assessment parameter. Results clearly show that the area near the chipping surface was damaged to a depth of 3 cm. Furthermore, X-ray methods can be used to evaluate the porosity index, burn number, and medial axis, which are used to estimate the damage to the area near the chipping surface.

• Tunnel and Underground Space
• /
• v.29 no.6
• /
• pp.542-557
• /
• 2019

The behavior of rock mass is influenced by its microscopic feature of internal structure generating from forming and metamorphic process. This study investigated a new methodology for characterization of rock based on the X-ray CT (computed tomography) images reflecting the spatial distribution characteristics of internal constituent materials. The X-ray image based analysis is capable of quantification of heterogeneity and anisotropy of rock fabric, size distribution and shape parameter analysis of rock mineral grains, fluid flow simulation based on pore geometry image and roughness evaluation of unexposed joint surface which are hardly acquired by conventional rock testing methods.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.5
• /
• pp.323-330
• /
• 2023

The development of an analysis model that reflects the microstructure characteristics of polyvinyl alcohol (PVA) fiber-reinforced cementitious composites, which have a highly complex microstructure, enables synergy between efficient material design and real experiments. PVA fiber orientations are an important factor that influences the mechanical behavior of PVA fiber-reinforced cementitious composites. Owing to the difficulty in distinguishing the gray level value obtained from micro-CT images of PVA fibers from adjacent phases, fiber segmentation is time-consuming work. In this study, a micro-CT test with a voxel size of 0.65 ㎛³ was performed to investigate the three-dimensional distribution of fibers. To segment the fibers and generate training data, histogram, morphology, and gradient-based phase-segmentation methods were used. A U-net model was proposed to segment fibers from micro-CT images of PVA fiber-reinforced cementitious composites. Data augmentation was applied to increase the accuracy of the training, using a total of 1024 images as training data. The performance of the model was evaluated using accuracy, precision, recall, and F1 score. The trained model achieved a high fiber segmentation performance and efficiency, and the approach can be applied to other specimens as well.

• Composites Research
• /
• v.36 no.6
• /
• pp.395-401
• /
• 2023

In this study, finite element modeling of unidirectional composite materials of the computed tomography (CT) was conducted using a supervised learning-based segmentation technique. Firstly, Micro-CT scan was performed to obtain the raw volume of unidirectional composite materials, providing microstructure information. From the CT volume images, actual microstructure of the cross-section of unidirectional composite materials was extracted by the labeling process. Then, a U-net deep learning model was trained with a small number of raw images as inputs and their labeled images as outputs to generate a segmentation model. Subsequently, most of remaining images were input to the trained U-net deep learning model to segment all raw volume for identifying complex microstructure, which was used for the generation of finite element model. Finally, the fiber volume fraction of the finite element model was compared with that of experimentally measured volume to validate the appropriateness of the proposed method.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.36 no.5
• /
• pp.339-346
• /
• 2023

The uncertainties of microstructural features affect the properties of materials. Numerous pores that are randomly distributed in materials make it difficult to predict the properties of the materials. The distribution of pores in cementitious materials has a great influence on their mechanical properties. Existing studies focus on analyzing the statistical relationship between pore distribution and material responses, and the correlation between them is not yet fully determined. In this study, the mechanical response of cementitious materials is predicted through an image-based data approach using a convolutional neural network (CNN), and the correlation between pore distribution and material response is analyzed. The dataset for machine learning consists of high-resolution micro-CT images and the properties (tensile strength) of cementitious materials. The microstructures are characterized, and the mechanical properties are evaluated through 2D direct tension simulations using the phase-field fracture model. The attributes of input images are analyzed to identify the spot with the greatest influence on the prediction of material response through CNN. The correlation between pore distribution characteristics and material response is analyzed by comparing the active regions during the CNN process and the pore distribution.

• KIPS Transactions on Computer and Communication Systems
• /
• v.10 no.11
• /
• pp.305-310
• /
• 2021

Artificial intelligence technology in the medical field initially focused on analysis and algorithm development, but it is gradually changing to web application development for service as a product. This paper describes a Urinary Stone segmentation model in abdominal CT images and an artificial intelligence web application based on it. To implement this, a model was developed using U-Net, a fully-convolutional network-based model of the end-to-end method proposed for the purpose of image segmentation in the medical imaging field. And for web service development, it was developed based on AWS cloud using a Python-based micro web framework called Flask. Finally, the result predicted by the urolithiasis segmentation model by model serving is shown as the result of performing the AI web application service. We expect that our proposed AI web application service will be utilized for screening test.

• Tunnel and Underground Space
• /
• v.31 no.6
• /
• pp.400-414
• /
• 2021

Under high-level radioactive waste repository conditions, bentonite as an engineered barrier material undergoes thermal, hydrological, mechanical, and chemical processes. We report the applications of X-ray Computed Tomography (CT) imaging technique on the characterization and analysis of bentonite over the past decade to provide a reference of the utilization of this technique and the recent research trends. This overview of the X-ray CT technique applications includes the characterization of the bentonite either in pellets or powder form. X-ray imaging has provided a means to extract grain information at the microscale and identify crack networks responsible for the pellets' heterogeneity. Regarding samples of pellets-powder mixtures under hydration, X-ray CT allowed the identification and monitoring of heterogeneous zones throughout the test. Some results showed how zones with pellets only swell faster compared to others composed of pellets and powder. Moreover, the behavior of fissures between grains and bentonite matrix was observed to change under drying and hydrating conditions, tending to close during the former and open during the latter. The development of specializing software has allowed obtaining strain fields from a sequence of images. In more recent works, X-ray CT technique has served to estimate the dry density, water content, and particle displacement at different testing times. Also, when temperature was added to the hydration process of a sample, CT technology offered a way to observe localized and global density changes over time.

• Korean Journal of Dental Materials
• /
• v.44 no.2
• /
• pp.187-195
• /
• 2017

TheraCal LC, a new light-cured, resin-modified calcium silicate-filled base/liner material, has been introduced as a pulpotomy agent. The aim of this study was to evaluate the capacity of hard tissue formation and pulpal response after pulpotomy with TheraCal LC. Twenty-two 9-week-old male rats were anesthetized, cavities were prepared in maxillary first molars and pulps were capped with formocresol (FC), mineral trioxide aggregate (MTA), and TheraCal LC. Specimens obtained from rats were scanned using a high-resolution micro CT system. The specimens were prepared and evaluated histologically, and immunofluorescence assay was performed to assess the dentin matrix protein-1 (DMP-1) expression. On micro CT analysis, the MTA and TheraCal LC groups showed thicker hard tissue formation than the FC group. On hematoxylin and eosin (H&E) staining, MTA and TheraCal LC groups showed dentine bridge formation with vital pulp beneath the materials. On immunofluorescence analysis, DMP-1 was highly expressed in the TheraCal LC group compared to the FC group. TheraCal LC showed similar capacity to form hard tissue as MTA when it was used as a pulpotomy agent. Because of its good manipulation and faster setting time compared to MTA, TheraCal LC could be considered as a good alternative to MTA.

• Journal of Digital Convergence
• /
• v.11 no.9
• /
• pp.365-370
• /
• 2013

This mouse calvarial defected model is frequently used for new scaffold development in the bone regeneration. Most experiments are carried out in this way by measuring the bone regeneration of mouse calvaria defected area. As a next step, hematoxylin and eosin staining is analyzed by sacrificing mice On the other hand, the quantitative analysis for bone regeneration is carried out by micro computed tomography. However, there are several drawbacks with the micro computed tomography. That is, it takes a long time and it is quite expensive for bone regeneration quantitative analysis. This study was performed by simply measuring the quantity of bone regeneration in mouse clavaira defected area on two-dimensional digital x-ray images via Image J. Consequentially, this experimental method by using J program might help bio-technologist researcher regarding new bone regeneration by comparing the quantity of bone regeneration quickly and precisely as well.