Representation Of Artifacts Research Articles

B-MAR: bidirectional artifact representations learning framework for metal artifact reduction in dental CBCT

Objective. Metal artifacts in computed tomography (CT) images hinder diagnosis and treatment significantly. Specifically, dental cone-beam computed tomography (Dental CBCT) images are seriously contaminated by metal artifacts due to the widespread use of low tube voltages and the presence of various high-attenuation materials in dental structures. Existing supervised metal artifact reduction (MAR) methods mainly learn the mapping of artifact-affected images to clean images, while ignoring the modeling of the metal artifact generation process. Therefore, we propose the bidirectional artifact representations learning framework to adaptively encode metal artifacts caused by various dental implants and model the generation and elimination of metal artifacts, thereby improving MAR performance. Approach. Specifically, we introduce an efficient artifact encoder to extract multi-scale representations of metal artifacts from artifact-affected images. These extracted metal artifact representations are then bidirectionally embedded into both the metal artifact generator and the metal artifact eliminator, which can simultaneously improve the performance of artifact removal and artifact generation. The artifact eliminator learns artifact removal in a supervised manner, while the artifact generator learns artifact generation in an adversarial manner. To further improve the performance of the bidirectional task networks, we propose artifact consistency loss to align the consistency of images generated by the eliminator and the generator with or without embedding artifact representations. Main results. To validate the effectiveness of our algorithm, experiments are conducted on simulated and clinical datasets containing various dental metal morphologies. Quantitative metrics are calculated to evaluate the results of the simulation tests, which demonstrate b-MAR improvements of >1.4131 dB in PSNR, >0.3473 HU decrements in RMSE, and >0.0025 promotion in structural similarity index measurement over the current state-of-the-art MAR methods. All results indicate that the proposed b-MAR method can remove artifacts caused by various metal morphologies and restore the structural integrity of dental tissues effectively. Significance. The proposed b-MAR method strengthens the joint learning of the artifact removal process and the artifact generation process by bidirectionally embedding artifact representations, thereby improving the model’s artifact removal performance. Compared with other comparison methods, b-MAR can robustly and effectively correct metal artifacts in dental CBCT images caused by different dental metals.

Assessing text-image patent datasets with text-based metrics for engineering design applications

AbstractImages provide concise representations of design artifacts and emerge as the primary mode of communication among innovators, engineers, and designers. The advanced of Artificial Intelligence tools which integrates image and textual information can significantly support the Engineering Design process. In this paper we create 5 different datasets combining both images and text of patents and we develop a set of text-based metrics to assess the quality of text for multimodal applications. Finally, we discuss the challenges arising in the development of multimodal patent datasets.

Enhanced Inclusion through Advanced Immersion in Cultural Heritage: A Holistic Framework in Virtual Museology

In recent years, the digitization of cultural heritage has been favored by significant advancements in specific technologies, such as photogrammetry and three-dimensional scanning. The digital representations of artifacts, paintings, books, and collections, as well as buildings or archaeological sites, has led to the transfer of cultural organizations to the digital space. On the other hand, the rapid development of immersive technologies and the Internet of Things is expected to decisively shape virtual cultural heritage in the coming years. However, this digital transition should expand its impact on most of the population. This article aims to cover the lack of structured methodology in the design and development of inclusive virtual spaces in cultural heritage. This research introduces a holistic framework that is mainly based on the disciplines of virtual museology. The proposed methodology takes into account the advancements in extended reality and the creative industry of computer games. The multisensory approach would lead to advanced immersive experiences, while the multilayered approach of cultural heritage content would enhance accessibility in inclusive virtual spaces. Moreover, this holistic framework could provide evidence from the virtual worlds that could be applied to real cultural heritage organizations.

Design of Virtual Reality Based Game for Dual Enhancement of City Monuments and Brand Image

The increasing accessibility of Virtual reality (VR) technology presents an opportunity for enhancing human immersion in several domains (Industrial, Social, Media, Cultural heritage, etc.). Moreover, it has huge impact to leverage its interaction and engagement; to un-dominate person on live, work, and diversion. The development of innovative VR-driven method is a sign of evolvement witnessed by the interaction design industry. In this respect, the work presents a complete framework for the design of virtual reality-based game; offering features, mechanisms, and 3D models that facilitate the development of interactive scenes, which reveal of the city’s historic monuments reality. The main research question focuses on empirically establishing the impact of virtual reality on video game design, including its influence on in-game cultural placement and its potential to enhance the retention of legacy game experiences within players’ memories. The results show that the game experience is felt original, enjoyable, and appealing for the user’s target group. Also, participants appreciate the use of VR technologies to explore cultural scenes and product; and to enhance empathy within a virtual experience. Furthermore, our research extends recent studies, proposing a VR-based design methodology, as well as, an assessing process. It guides the creation of visual representation of monuments, artifacts, and culture. Moreover, it improves user’s point of view and knowledge of the place they visit, within playing the WallysCar Crash Team Racing (WCTR) game. Our project intended to achieve a twofold purpose related to the Tunisian context: discovering the popular “Sfax City” with historical and patrimonial monumental heritage, while promoting the local industry creation.

The architecture exhibition as a stage of mediated narratives

ABSTRACT This paper discusses the role and agency of the architecture exhibition as a mediated space of discursive spatial narratives. The presented curatorial approach draws on the exhibition entitled Past-forward: Stavros Economou Unarchived (2021) to reflect on the development of a multimedia-enabled reading of the architectural archive. Stavros Economou is one of the most important representatives of modern architecture in Cyprus, yet his work is underdiscussed and under-published. The architectural archive, unlike other collections, consists of representations (such as drawings, models, photographs) of artefacts (buildings) that communicate design processes and final un/built proposals. The curatorial practice focused on a twofold challenge: on one hand, it explored the role architectural representation can play in the production of the multiple and complex (hi)stories of modern buildings, and secondly, it considered ways in which an architecture exhibition can connect with the host city and its local population by addressing contemporary urgencies of spatial inquiry.

A Virtual Museums and 3D Artefacts to Improve Cultural Heritage Education

In the current era of globalization and modernization, the imperative to safeguard and convey cultural heritage and history to society becomes increasingly significant. Web-based virtual museums have emerged as a pivotal solution, facilitating the preservation and promotion of cultural heritage on a global scale. These virtual platforms offer visitors unprecedented access to artifact collections, transcending the limitations of physical museum visits. The immersive features, such as the ability to view objects from diverse angles and zoom in on intricate details, present a profound and engaging experience. This research is to contribute insights into the development of effective web-based virtual museums featuring 3D artifact representations, thereby making a meaningful contribution to the broader field of cultural heritage preservation. The primary objective of this study is to enrich the exploration and learning experiences of visitors in the realm of cultural heritage through digital platforms. The research employs a structured software development methodology encompassing vital stages like needs analysis, system design, implementation, testing, and maintenance. By focusing on the technological aspects, the study seeks to address challenges related to quality and reliability faced by web-based virtual museums. Furthermore, the findings aim to enhance the overall effectiveness of these museums in offering a comprehensive and captivating journey through cultural artifacts. This research is poised to not only advance the field of virtual museum development but also foster a deeper appreciation and understanding of our rich cultural heritage.

Optimization of Image Processing Algorithms for Character Recognition in Cultural Typewritten Documents

Linked data is used in various fields as a new way of structuring and connecting data. Cultural heritage institutions have been using linked data to improve archival descriptions and facilitate the discovery of information. Most archival records have digital representations of physical artifacts in the form of scanned images that are non-machine-readable. Optical Character Recognition (OCR) recognizes text in images and translates it into machine-encoded text. This article evaluates the impact of image processing methods and parameter tuning in OCR applied to typewritten cultural heritage documents. The approach uses a multi-objective problem formulation to minimize Levenshtein edit distance and maximize the number of words correctly identified with a non-dominated sorting genetic algorithm (NSGA-II) to tune the methods’ parameters. Evaluation results show that parameterization by digital representation typology benefits the performance of image pre-processing algorithms in OCR. Furthermore, our findings suggest that employing image pre-processing algorithms in OCR might be more suitable for typologies where the text recognition task without pre-processing does not produce good results. In particular, Adaptive Thresholding, Bilateral Filter, and Opening are the best-performing algorithms for the theater plays’ covers, letters, and overall dataset, respectively, and should be applied before OCR to improve its performance.

Comparing and Evaluating Human and Computationally Derived Representations of Non-Semantic Design Information

Abstract Design artifacts provide a mechanism for illustrating design information and concepts, but their effectiveness relies on alignment across design agents in what these artifacts represent. This work investigates the agreement between multi-modal representations of design artifacts by humans and artificial intelligence (AI). Design artifacts are considered to constitute stimuli designers interact with to become inspired (i.e., inspirational stimuli), for which retrieval often relies on computational methods using AI. To facilitate this process for multi-modal stimuli, a better understanding of human perspectives of non-semantic representations of design information, e.g., by form or function-based features, is motivated. This work compares and evaluates human and AI-based representations of 3D-model parts by visual and functional features. Humans and AI were found to share consistent representations of visual and functional similarities, which aligned well with coarse, but not more granular, levels of similarity. Human–AI alignment was higher for identifying low compared to high similarity parts, suggesting mutual representation of features underlying more obvious than nuanced differences. Human evaluation of part relationships in terms of belonging to the same or different categories revealed that human and AI-derived relationships similarly reflect concepts of “near” and “far.” However, levels of similarity corresponding to “near” and “far” differed depending on the criteria evaluated, where “far” was associated with nearer visually than functionally related stimuli. These findings contribute to a fundamental understanding of human evaluation of information conveyed by AI-represented design artifacts needed for successful human–AI collaboration in design.

Artificial Intelligence and Archaeological Illustration

AbstractThe reconstruction and representation of ancient artifacts and scenes through illustration is a cornerstone in the communication of archaeological findings. Sketches of the past have transformed over time, incorporating broader technological changes, from photography to the digital tools that have become prevalent through the twenty-first century. Most recently, developments in generative artificial intelligence (AI) promise to reshape the way we represent the past to professional and public audiences. This article shows how to use an accessible and inexpensive artificial intelligence platform to generate complex archaeological illustrations. As a case study, we create multiple scenes representing competing hypotheses about Neanderthal behavior. Using the images to visually communicate alternative hypotheses, we demonstrate how archaeological illustration using artificial intelligence promises to democratize the production of visual representations of the past.

Automated detection, segmentation and measurement of major vessels and the trachea in CT pulmonary angiography

Mediastinal structure measurements are important for the radiologist’s review of computed tomography pulmonary angiography (CTPA) examinations. In the reporting process, radiologists make measurements of diameters, volumes, and organ densities for image quality assessment and risk stratification. However, manual measurement of these features is time consuming. Here, we sought to develop a time-saving automated algorithm that can accurately detect, segment and measure mediastinal structures in routine clinical CTPA examinations. In this study, 700 CTPA examinations collected and annotated. Of these, a training set of 180 examinations were used to develop a fully automated deterministic algorithm. On the test set of 520 examinations, two radiologists validated the detection and segmentation performance quantitatively, and ground truth was annotated to validate the measurement performance. External validation was performed in 47 CTPAs from two independent datasets. The system had 86–100% detection and segmentation accuracy in the different tasks. The automatic measurements correlated well to those of the radiologist (Pearson’s r 0.68–0.99). Taken together, the fully automated algorithm accurately detected, segmented, and measured mediastinal structures in routine CTPA examinations having an adequate representation of common artifacts and medical conditions.

Intrinsic Shape Analysis in Archaeology: A Case Study on Ancient Sundials

The fact that the physical shapes of man-made objects are subject to overlapping influences—such as technological, economic, geographic, and stylistic progressions—holds great information potential. On the other hand, it is also a major analytical challenge to uncover these overlapping trends and to disentagle them in an unbiased way. This article explores a novel mathematical approach to extract archaeological insights from ensembles of similar artifact shapes. We show that by considering all shape information in a find collection , it is possible to identify shape patterns that would be difficult to discern by considering the artifacts individually or by classifying shapes into predefined archaeological types and analyzing the associated distinguishing characteristics. Recently, a series of high-resolution digital representations of artifacts have become available. Such datasets enable the application of extremely sensitive and flexible methods of shape analysis. We explore this potential on a set of 3D models of ancient Greek and Roman sundials, with the aim of providing alternatives to the traditional archaeological method of “trend extraction by ordination” (typology). In the proposed approach, each 3D shape is represented as a point in a shape space —a high-dimensional, curved, non-Euclidean space. Proper consideration of its mathematical properties reduces bias in data analysis and thus improves analytical power. By performing regression in shape space, we find that for Roman sundials, the bend of the shadow-receiving surface of the sundials changes with the latitude of the location. This suggests that, apart from the inscribed hour lines, also a sundial’s shape was adjusted to the place of installation. As an example of more advanced inference, we use the identified trend to infer the latitude at which a sundial, whose location of installation is unknown, was placed. We also derive a novel method for differentiated morphological trend assertion, building upon and extending the theory of geometric statistics and shape analysis. Specifically, we present a regression-based method for statistical normalization of shapes that serves as a means of disentangling parameter-dependent effects (trends) and unexplained variability . In addition, we show that this approach is robust to noise in the digital reconstructions of the artifact shapes.

Breath-Hold CBCT-Guided CBCT-to-CT Synthesis via Multimodal Unsupervised Representation Disentanglement Learning.

Adaptive radiation therapy (ART) aims to deliver radiotherapy accurately and precisely in the presence of anatomical changes, in which the synthesis of computed tomography (CT) from cone-beam CT (CBCT) is an important step. However, because of serious motion artifacts, CBCT-to-CT synthesis remains a challenging task for breast-cancer ART. Existing synthesis methods usually ignore motion artifacts, thereby limiting their performance on chest CBCT images. In this paper, we decompose CBCT-to-CT synthesis into artifact reduction and intensity correction, and we introduce breath-hold CBCT images to guide them. To achieve superior synthesis performance, we propose a multimodal unsupervised representation disentanglement (MURD) learning framework that disentangles the content, style, and artifact representations from CBCT and CT images in the latent space. MURD can synthesize different forms of images using the recombination of disentangled representations. Also, we propose a multipath consistency loss to improve structural consistency in synthesis and a multidomain generator to improve synthesis performance. Experiments on our breast-cancer dataset show that MURD achieves impressive performance with a mean absolute error of 55.23±9.94 HU, a structural similarity index measurement of 0.721±0.042, and a peak signal-to-noise ratio of 28.26±1.93 dB in synthetic CT. The results show that compared to state-of-the-art unsupervised synthesis methods, our method produces better synthetic CT images in terms of both accuracy and visual quality.

Quantitative Assessment of Dimensional Evaluation and Artefacts from Filling Materials with CBCT Using Standard Phantom Roots.

To investigate the accuracy of dimensional evaluation and representation of artefacts generated by different gutta-percha (GP) cones with or without sealer with CBCT using a reproducible, standardised phantom root methodology. The reproducible artificial phantom roots with six root canal sizes from #25 to #50 and 0.04 taper were aligned according to the jaw curvature in a stone model for dimensional measurements. Each root was scanned while empty and filled with four types of filling materials. The specimens were scanned using the CS 9300 3D (Carestream Dental, Rochester, NY, USA) (at two different resolutions), 3D Accuitomo (J Morita, Kyoto, Japan) and NewTom VGi (Verona, Italy) CBCT systems. The hyperdense and hypodense axial slice artefacts from root canal sizes #40, #45 and #50 were recorded. Dimensions were significantly smaller and more accurate with CS 9300/0.09 mm voxel size than with other protocols. The hypodense band was found mostly in the CS 9300 3D system with 0.18 mm voxel size, especially in the buccal-lingual (95%) and coronal (64%) sections. The 3D Accuitomo CBCT system showed the lowest presence of the hypodense band. Areas of both light and dark artefacts were significantly larger in the coronal third than in the apical and middle thirds. Artefacts in the coronal locations and in buccal-lingual sections were more evident in the CS 9300 3D system with a 0.18-mm voxel size.

Axes in the Funerary Ceremonies of the Northern Pontic Scythians

Axes were rare among the Scythians but are occasionally found in Scythian kurgans. Like other weapons, axes had practical as well as social and religious roles. The Scythians not only placed axes in burials as burial gifts, but also used them at various stages of the funeral ritual. This article considers several hitherto unknown, highly unusual archaeological contexts featuring axes. These contexts show that axes were used in the ritual preceding the excavation of the grave; they completed the ritual before the filling of the grave; and they were included in the final sealing of the burial. In addition to the ritual implications of Scythian axes found in kurgan burials, this article considers the meaning of the representations of related artifacts on Scythian metalwork, as well as on the coins of Kerkinitis and Olbia. A bronze votive axe similar to the one from L’vovo Kurgan 18, Burial 2 is shown on Olbian Borysthenes coins, indicating a permanent relationship between the city and the Scythians, perhaps in the form of paying tribute (“gifts”) to the Scythians. The dating of Olbian Borysthenes coinage is also discussed.

StruNet: Perceptual and low-rank regularized transformer for medical image denoising.

Various types of noise artifacts inevitably exist in some medical imaging modalities due to limitations of imaging techniques, which impair either clinical diagnosis or subsequent analysis. Recently, deep learning approaches have been rapidly developed and applied on medical images for noise removal or image quality enhancement. Nevertheless, due to complexity and diversity of noise distribution representations in different medical imaging modalities, most of the existing deep learning frameworks are incapable to flexibly remove noise artifacts while retaining detailed information. As a result, it remains challenging to design an effective and unified medical image denoising method that will work across a variety of noise artifacts for different imaging modalities without requiring specialized knowledge in performing the task. In this paper, we propose a novel encoder-decoder architecture called Swin transformer-based residual u-shape Network (StruNet), for medical image denoising. Our StruNet adopts a well-designed block as the backbone of the encoder-decoder architecture, which integrates Swin Transformer modules with residual block in parallel connection. Swin Transformer modules could effectively learn hierarchical representations of noise artifacts via self-attention mechanism in non-overlapping shifted windows and cross-window connection, while residual block is advantageous to compensate loss of detailed information via shortcut connection. Furthermore, perceptual loss and low-rank regularization are incorporated into loss function respectively in order to constrain the denoising results on feature-level consistency and low-rank characteristics. To evaluate the performance of the proposed method, we have conducted experiments on three medical imaging modalities including computed tomography (CT), optical coherence tomography (OCT) and optical coherence tomography angiography (OCTA). The results demonstrate that the proposed architecture yields a promising performance of suppressing multiform noise artifacts existing in different imagingmodalities.

Multi-level uncertainty aware learning for semi-supervised dental panoramic caries segmentation

Dental caries segmentation based on oral panoramic medical images is a demanding medical task. However, it is challenging to determine imaging diagnosis results as the actual pathological changes under certain conditions, especially in the suspected pathological locations that distinguish the artifacts from the lesions. This paper proposes introducing the semi-supervised learning framework to redistribute the collected cases to set up exact lesion areas and divide suspected areas with uncertainties into unlabeled data instead of reducing dataset labeling costs. Consistent regularization learning allows us to exploit the feature of ambiguous lesions to optimize decision boundaries. Unfortunately, the labels generated by the general SSL method for fuzzy regions are volatile, especially encountering no specific morphological rules and various scales that fluctuate more seriously, making a devastating impact on the regularization training relying on steady prediction. For such a challenge, we consider places that always form stable predictions under various disorders are often highly deterministic. Therefore, we propose introducing multi-level disturbances, including noise, iterative, and multi-scale disturbances. We simultaneously present in-depth supervision training on the multi-layer decoder to form stable and consistent multi-scale intermediate predictions, which significantly enrich the number of samples gathered in the following integration process. Then, Monte Carlo sampling is applied to integrate multi-level prediction results to assemble a more robust uncertainty mask map, which gradually clarifies the inter-class feature representation of actual lesions and artifacts. The extended experiment shows that we have successfully and effectively improved the performance of the caries segmentation task by using such uncertain lesion sample features. The dataset is now public, and the code is available at https://github.com/Zzz512/MLUA.

Narrative discourse in postmodern fiction

Narrative and language are closely related so much that theorists have played their interdependence. Postmodern fiction has achieved a pure spatiality by eliminating time and sequence from narrative, that is, the representation of time in narrative. The reader is forced to concentrate on the stylistic devices that retard the narrative progression such as, the amalgamation of different genres, parody, irony self-reflexivity and historiographic metafiction. Although postmodern fiction eschews historical time and treats history as a text, it retrieves the various styles of the past and represents them, yet postmodern historiography records the history as a text since it is a human construct and uses this realization to displace the forms and contents of the past concurrently. Postmodernism is a continuous literary theory in which the study of narrative discourse is transcendental to life and to the different approaches of literature. What is inherent in postmodernism is the augmentation of the different historical, psychoanalytical metaphysical, structural and deco structural approaches that dominate the narrative structure of postmodernity. All these critical theories have pursued their own parameters and devices towards the representation of artifacts in general.

A functional and semantic analysis of artifact representation schemata in folklore museum websites

A functional and semantic analysis of artifact representation schemata in folklore museum websites

High resolution flow with glazing flow for optimized flow detection in transjugular intrahepatic portosystemic stent shunt (TIPS): First results.

Ultrasound follow-up of transjugular intrahepatic portosystemic shunt (TIPS) is challenging due to the bent course of the stent-graft. Aim of this retrospective study was to assess to which extent the combination of HR flow with Glazing Flow improves hemodynamic assessment in the ultrasound follow-up of TIPS. Comparative studies with CCDS and High Resolution (HR)-Flow with Glazing Flow were evaluated regarding image quality and artifacts on a 5-point scale (0 = cannot be assessed up to 5 = maximum image quality without artifacts). In all cases, an experienced examiner performed the examinations with a 1-6 MHz probe (Resona 7, Mindray). 61 ultrasound examinations in 48 patients were performed; the mean patient age was 54±14.2 years. The use of HR-Flow with Glazing Flow resulted in an improved flow display in 55/61 cases (90.2%). Both methods correlated well (r = 0.71), but HR flow with Glazing flow values were in general higher than CCDS values. The reading resulted in an average value of 2.52±0.54 for CCDS and 3.52±0.57 for HR flow with Glazing flow (p = 0.013). The combination of HR-Flow and Glazing Flow results in improved flow representation and reduction of artifacts in the ultrasound follow-up of TIPS.

A Model-Driven Deep Unfolding Method for JPEG Artifacts Removal.

Deep learning-based methods have achieved notable progress in removing blocking artifacts caused by lossy JPEG compression on images. However, most deep learning-based methods handle this task by designing black-box network architectures to directly learn the relationships between the compressed images and their clean versions. These network architectures are always lack of sufficient interpretability, which limits their further improvements in deblocking performance. To address this issue, in this article, we propose a model-driven deep unfolding method for JPEG artifacts removal, with interpretable network structures. First, we build a maximum posterior (MAP) model for deblocking using convolutional dictionary learning and design an iterative optimization algorithm using proximal operators. Second, we unfold this iterative algorithm into a learnable deep network structure, where each module corresponds to a specific operation of the iterative algorithm. In this way, our network inherits the benefits of both the powerful model ability of data-driven deep learning method and the interpretability of traditional model-driven method. By training the proposed network in an end-to-end manner, all learnable modules can be automatically explored to well characterize the representations of both JPEG artifacts and image content. Experiments on synthetic and real-world datasets show that our method is able to generate competitive or even better deblocking results, compared with state-of-the-art methods both quantitatively and qualitatively.