https://hdl.handle.net/2072/452957 Mon, 06 Apr 2026 14:46:24 GMT 2026-04-06T14:46:24Z https://hdl.handle.net/10256/28408 Topology-aware multiclass segmentation of the Circle of Willis from MRA and CTA images Hamadache, Rachika E.; Lisazo, Clara; Yalcin, Cansu; Lal-Trehan Estrada, Uma M.; Abramova, Valeriia; Casamitjana, Adrià; Oliver i Malagelada, Arnau; Lladó Bardera, Xavier The Circle of Willis (CoW) is an essential network of arteries that ensures blood flow throughout the brain. From a clinical perspective, evaluating the vessels of the CoW is highly relevant as its angioarchitecture and variants are important biomarkers of neurovascular pathologies. However, achieving a topologically accurate segmentation of these vessels remains challenging due to their anatomical complexity. In this work, we propose a pipeline for the multiclass segmentation of the CoW vessels (13 possible classes), focusing on achieving both topology correctness and segmentation accuracy in magnetic resonance angiography (MRA) and computed tomography angiography (CTA) imaging techniques. We propose a deep learning framework based on the nnUNet model, together with a post-processing block that requires no additional training and that is adapted to the specific multiclass CoW segmentation task. We train and validate our framework using the publicly available TopCoW 2024 dataset (MRA and CTA) and evaluate it on the hidden test set (through an online system) and on an independent subset from the CROWN 2023 challenge dataset (MRA). The obtained results demonstrate the positive impact of our approach, achieving an average Dice (centerline Dice) scores of 0.90 (0.99) for MRA and 0.88 (0.99) for CTA on the in-domain test set, and 0.81 (0.97) on the out-of-domain test set for MRA. These high performances align with state-of-the-art methods, and rank among the top in the TopCoW 2024 challenge. The approach is publicly available for the research community at https://github.com/NIC-VICOROB/CoW-multiclass-segmentation-TopCoW24; Rachika E. Hamadache holds an IFUdG2024 grant from Universitat de Girona. Clara Lisazo holds an FI grant from the Catalan Government with reference number 2024 FI-1 00103. Cansu Yalcın holds an FI grant from the Catalan Government with reference number 2023 FI-1 00096. Uma M. Lal-Trehan Estrada holds an IFUdG2022 grant from Universitat de Girona. Valeriia Abramova holds an FPI grant from the Ministerio de Ciencia, Innovación y Universidades with reference number PRE2021-099121. Adrià Casamitjana holds a Ramón y Cajal grant from the Spanish Government with reference number RYC2024-050753-I. This work has been supported by PID2023-146187OB-I00 from the Ministerio de Ciencia, Innovación y Universidades and also by the ICREA Academia program. Open Access funding was provided thanks to the CRUE-CSIC agreement with Elsevier Sun, 01 Mar 2026 00:00:00 GMT https://hdl.handle.net/10256/28408 2026-03-01T00:00:00Z https://hdl.handle.net/10256/28381 Addressing the generalization of 3D registration methods with a featureless baseline and an unbiased benchmark Bojanic, David; Bartol, Kristijan; Forest Collado, Josep; Petkovic, Tomislav; Pribanic, Tomislav Recent 3D registration methods are mostly learning-based that either find correspondences in feature space and match them, or directly estimate the registration transformation from the given point cloud features. Therefore, these feature-based methods have difficulties with generalizing onto point clouds that differ substantially from their training data. This issue is not so apparent because of the problematic benchmark definitions that cannot provide any in-depth analysis and contain a bias toward similar data. Therefore, we propose a methodology to create a 3D registration benchmark, given a point cloud dataset, that provides a more informative evaluation of a method w.r.t. other benchmarks. Using this methodology, we create a novel FAUST-partial (FP) benchmark, based on the FAUST dataset, with several difficulty levels. The FP benchmark addresses the limitations of the current benchmarks: lack of data and parameter range variability, and allows to evaluate the strengths and weaknesses of a 3D registration method w.r.t. a single registration parameter. Using the new FP benchmark, we provide a thorough analysis of the current state-of-the-art methods and observe that the current method still struggle to generalize onto severely different out-of-sample data. Therefore, we propose a simple featureless traditional 3D registration baseline method based on the weighted cross-correlation between two given point clouds. Our method achieves strong results on current benchmarking datasets, outperforming most deep learning methods. Our source code is available on github.com/DavidBoja/exhaustive-grid-search.; Funding This work has been supported by the Croatian Science Foundation under the projects IP-2018-01-8118, DOK-2020-01 and IP2019-04-9157, and has been partially funded by the EU under project iToBoS (SC1-BHC-06-2020-965221) Sat, 23 Mar 2024 00:00:00 GMT https://hdl.handle.net/10256/28381 2024-03-23T00:00:00Z https://hdl.handle.net/10256/28184 Motiv-ARCHE: an augmented reality application to co-create cultural heritage resources with teenagers González Vargas, Juan Camilo; Fabregat Gesa, Ramon; Carrillo-Ramos, Angela; Jové Lagunas, Teodor Traditionally, the primary objective of a museum was to gather, study and preserve collections, and to put them on (do-not-touch) display for the public. Museums nowadays, however, are more concerned about how to make their collections and exhibitions accessible and hands-on, how to attract visitors and how to provide a forum for discussing, developing and encouraging intercultural dialogue and learning. This means that museums need to take into account their visitors’ experiences as well as their underlying motivation for going to the exhibitions in the first place (Dindler, Christian, Iversen 2009) Fri, 01 Jan 2021 00:00:00 GMT https://hdl.handle.net/10256/28184 2021-01-01T00:00:00Z https://hdl.handle.net/10256/28171 Motiv-ARCHE: co-creation of augmented reality educational content to motivate cultural and natural heritage learning González Vargas, Juan Camilo; Fabregat Gesa, Ramon; Carrillo-Ramos, Angela; Jové Lagunas, Teodor In the past, sites such as museums or archaeological sites focused primarily on the preservation, maintenance, and conservation of heritage elements for present and future generations. However, they now face a new challenge, the lack of motivation and public engagement in visiting and creating content about the exhibited elements. This lack of interest is, since the content presented does not address the interests or needs of the visitors, leading to cognitive overload with irrelevant information. Therefore, various applications have shown that the use of immersive technologies, such as augmented reality (AR), along with content co-creation strategies and information adaptation, can enhance users’ motivation to visit these sites. Moreover, these technologies also contribute to the preservation and conservation of heritage through the creation of virtual content. This article describes the design and implementation of a system called Motiv-ARCHE for the co-creation of educational content about cultural and natural heritage using AR. Its name combines three key elements: Motiv, referring to the motivation for learning; AR, for the use of augmented reality; and CHE, because it focuses on the education of cultural and natural heritage. Motiv-ARCHE is a system that integrates immersive technologies, co-creation, and information adaptation to enhance motivation for learning about cultural and natural heritage. Moreover, it enables both experts and users to generate content without requiring advanced technical knowledge, and this content can be displayed through AR activation by image recognition and geographic location. The system also provides access to various media formats, such as audio, video, 3D models, and AR documents. Thanks to its design, which is oriented toward delivering adaptive services, it aims to provide the user with the information they need according to their characteristics and context, which could enrich their experience at heritage sites by considering both their individual characteristics and those of their context. This increases their motivation to visit these sites and to learn about the heritage they contain. The development of Motiv-ARCHE follows the Design-Based Research (DBR) methodology, an iterative approach divided into three phases: design, implementation, and analysis. In the design phases, the characteristics of Motiv-ARCHE are identified based on the literature and user feedback. During the implementation phases, the core functionalities are developed and some experiments are conducted focusing on the co-creation of heritage elements, content, and routes, as well as on access to this content and in the analysis phases, each experiment is evaluated to improve the system. The article describes three co-creation experiments with 48, 16 and 8 participants respectively and one access experiment with 44 participants. In the three co-creation experiments, the IMMS (Instructional Materials Motivation Survey) motivation test and a demographic questionnaire were applied, while in the access experiment, the IMMS motivation test, the ARAM (Augmented Reality Acceptance Model) technology acceptance test, an augmented reality activation questionnaire, and a demographic questionnaire were used. The results showed that, thanks to the use of the methodology in the first experiment and the feedback provided by users, the application progressively improved, achieving better results in subsequent experiments. Furthermore, it was found that users feel motivated both in the co-creation of heritage elements, content, and routes, and in accessing content through AR; 4 Wed, 05 Nov 2025 00:00:00 GMT https://hdl.handle.net/10256/28171 2025-11-05T00:00:00Z