Abstract
Coronary artery calcium is a good indicator of coronary artery disease and can be used for cardiovascular risk stratification. Over the years, different deep learning approaches have been proposed to automatically segment coronary calcifications in computed tomography scans and measure their extent through calcium scores. However, most methodologies have focused on using 2D architectures which neglect most of the information present in those scans. In this work, we use a 3D convolutional neural network capable of leveraging the 3D nature of computed tomography scans and including more context in the segmentation process. In addition, the selected network is lightweight, which means that we can have 3D convolutions while having low memory requirements. Our results show that the predictions of the model, trained on the COCA dataset, are close to the ground truth for the majority of the patients in the test set obtaining a Dice score of 0.90 +/- 0.16 and a Cohen's linearly weighted kappa of 0.88 in Agatston score risk categorization. In conclusion, our approach shows promise in the tasks of segmenting coronary artery calcifications and predicting calcium scores with the objectives of optimizing clinical workflow and performing cardiovascular risk stratification.

Abstract
Training in a virtual environment can augment the current methods of professional's training, preparing them better for possible situations in the field of work while taking advantage of Virtual Reality (VR) benefits. This paper proposes a cost-effective immersive VR platform designed in real-context usage, consisting of an authoring tool that permits the creation and manipulation of training courses and the execution of these courses in an immersive environment. Accomplishing a good training experience in an immersive simulation requires an equilibrium between the simulator performance and the virtual world aesthetics quality. Thus, in addition to presenting the development of the proposed training platform based on Unity technologies, this paper describes an objective performance evaluation of a virtual training scene using the different render pipelines and across immersive and non-immersive setups. Results confirmed the platform's viability and revealed that the rendering pipeline should be defined according to the display device used.

Abstract
Case-based explanations are an intuitive method to gain insight into the decision-making process of deep learning models in clinical contexts. However, medical images cannot be shared as explanations due to privacy concerns. To address this problem, we propose a novel method for disentangling identity and medical characteristics of images and apply it to anonymize medical images. The disentanglement mechanism replaces some feature vectors in an image while ensuring that the remaining features are preserved, obtaining independent feature vectors that encode the images' identity and medical characteristics. We also propose a model to manufacture synthetic privacy-preserving identities to replace the original image's identity and achieve anonymization. The models are applied to medical and biometric datasets, demonstrating their capacity to generate realistic-looking anonymized images that preserve their original medical content. Additionally, the experiments show the network's inherent capacity to generate counterfactual images through the replacement of medical features.

Abstract
Higher Education Institutions (HEIs) are increasingly incorporating artificial i ntelligence (AI) into their learning setup. In this paper, we analyze the results of a survey posed to 152 Higher Education (HE) students and 136 HE educators, of different scientific b ackgrounds, to emphasize the current incorporation of AI in the teaching and learning processes. The results reveal distinct viewpoints from both parties, reflecting diversified l evels o f e xperience, presumptions, and uneasiness. Thirty two percent of the teachers, completing the survey, confirms using AI. Approximately 50% reveal they notice their students using AI to (i) automate routine tasks in or out-ofclass, including check correctness of answers, obtaining real-time feedback; (ii) personalize learning tasks, such as write essays or projects and to illustrate them, and create presentations. A smaller percentage reveals students using AI to produce video content and contrast information learned in class. Alternative means, encompassing using AI at home, to study, to gather information, to sum up ideas in texts, are identified by most teachers as being employed by their students. Students using AI outnumber the teachers, though there are significant d ifferences in some responses, when compared to the teachers' perceptions, for the sames questions. Most of the students prefer AI to study at home, to obtain information to improve or to check an answer. Then a significant number does not exploit AI either to create presentations, write an essay or project, illustrate a project, producing videos, or to contrast information obtained in classes with that collected by AI tools. Regardless of these differences, both parties agree and strongly agree (with 79% of students and 86% of teachers) that AI will affect the HEIs educational process in the future. © 2024 IEEE.

Abstract
Sustainable agri-food systems seek to deliver food affordably and sustainably, without compromising the economic, social, and environmental bases for current and coming generations. Food-energy systems integrating renewable energy sources contribute towards this sustainability, and new solutions are being proposed in the literature or implemented in real facilities. This work reviews the existing literature on the integration of renewable energy, cross-sector energy efficiency and flexibility approaches, circular economy, digital solutions, and energy communities' (EC) structures within the agri-food sector. It proposes a formal classification of the main solutions found and describes the associated Business Models (BMs) to support their actual development cost-effectively. The main roles, actors and value propositions are reviewed, and a case example of an EC to be developed in Portugal in the Tools4AgriEnergy project is also described. The EC is based on floating PV panels to power water distribution pumps and share the surplus with local agri-food industries.

Abstract
The increasing number of Distributed Energy Resources (DERs) provides new opportunities for increased interactions between prosumers and local distribution companies. Aggregating large numbers of prosumers through Home Energy Management Systems (HEMS) allows for easier control and coordination of these interactions. With the contribution of the dedicated end-users in fulfilling the required flexibility during the day, the network operator can easily handle the power mismatches to avoid fluctuations in the load-generation side. The bi-level optimization allows for a more comprehensive and systematic assessment of flexibility procurement strategies. By considering both the network operator's objectives and the preferences and capabilities of end-users, this approach enables a more nuanced and informed decision-making process. Hence, this article presents a bi-level optimization model to examine the potential for several groups of prosumers to offer flexibility services to distribution companies. The model is applied to the IEEE 33 bus test system and solved through distributed optimization techniques. The model considers various DERs, including Battery Energy Storage Systems (BESS). Results show that the groups of aggregated consumers can provide between +/- 7 to +/- 29 kW flexibility in each interval, which is significant. Furthermore, the aggregators' flexibility capacity is closely linked to the demand at each node.