Abstract
Neuroblastoma (NB) is the most common extracranial tumor in pediatric cases. The MYCN oncogene amplification (MNA) is knowingly correlated with a poor prognosis, making detecting this biomarker crucial for treatment selection and survival prediction. The current clinical protocol for MNA detection includes invasive procedures, such as biopsy. The proposed work aims to develop non-invasive techniques for predicting MNA in patients with diagnosed NB, using AI-based models and Computerized Tomography (CT) scans. Machine learning methods that use the imaging features extracted from the tumor on the CT slices were developed and compared with deep learning (DL) models. Additionally, agnostic explainable methods for imaging were applied to create explanations about the relevant information used by the DL models in the prediction. The results show a better performance for the DL approach, which achieved an AUC of 0.94 ± 0.04. The similarity in the explanations produced by the models trained with different data splits showed that feature extraction remains somewhat invariant to shifts in training data, which is relevant given the small amount of data available. Learning models were shown to have predictive potential that, with further improvements, can be integrated into predictive, explainable, and, thus, trustworthy systems to aid clinicians in the decision-making process. © 2025 IEEE.

Abstract
Segmentation of the lungs in Computed Tomography (CT) is very challenging due to changes in lung shape, size, and parenchyma pattern, as well as differences in imaging acquisition protocols. As a consequence, these models may not be robust and may decrease their performance when deployed in a clinical setting. The Continual Learning paradigm holds great promise since learning models continually acquire incoming knowledge, having the ability to adapt to changing environments. In this work, experience replay with random sampling of past data was implemented, using the original CT images and the corresponding ground-truths. Data from four different institutions were used to develop the experiments, and the models were evaluated on a cross-cohort dataset. Using raw data, the goal was to study how the datasets and their imaging patterns were related and what impact the training datasets have on one another. The catastrophic forgetting effect diminished for almost all datasets. For two of the in-domain test datasets there was forward and backward transfer, results that could be linked to a possible similarity between them. A mean DSC of 0.94 was obtained across all datasets. The results showed how the similarity or disparity between data from different institutions can influence the performance of learning models. © 2025 IEEE.

Abstract
Algorithms based on computer vision are commonly used in pre-operative procedures to help health professionals detecting blood vessels, which is also the case with the Deep Inferior Epigastric Perforators (DIEPs). These blood vessels are essential to produce a viable autologous DIEP flap, and the analysis of characteristics such as their location, diameter and course is essential to ensure the success of surgeries. This analysis is made by a team of radiology technicians and then validated by a surgeon, making it a complex process that can take up to 2 hours. The proposed algorithm called Assisted Vascular Analysis (AVA) was developed to ensure a faster alternative to the conventional methods, using automation to identify structures of interest such as the skin, umbilicus and fascia, while also requiring minimum input from the user to segment each DIEP (2 points for the subcutaneous portion and 2 for the intramuscular portion). The AVA feasibility tests where conducted using 6 Computed Tomography Angiographies (CTAs), with a total of 28 DIEP calibers obtained during surgery (ground truths) from patients that underwent breast reconstruction with a DIEP flap. The algorithm was evaluated for its capability to segment the DIEPs and measure their caliber, comparing the results with the ground truth calibers and the manual mapping done by the radiology technicians. The Root Mean Square Error (RMSE) metric shows that the calibers obtained by the AVA algorithm (0.57 millimeters) and the radiology technicians (0.46 millimeters) are very similar, with the radiology technicians gaining a smaller edge of 0.11 millimeters. These results are very promising, since the errors are inferior to the average image resolution (0.88 millimeters). It was also demonstrated that the AVA algorithm is a faster alternative to manual segmentation, taking around 10 minutes to fully analyze each CTA, while the radiology technicians takes around 1 hour to do the DIEP mapping and caliber measurements. In conclusion, AVA is a validated algorithm to segment DIEP vessels and a faster alternative compared with conventional methods. © 2025 IEEE.

Abstract
Telecommunications and computer vision solutions have evolved significantly in recent years, allowing a huge advance in the functionalities and applications offered. However, these two fields have been making their way as separate areas, not exploring the potential benefits of merging the innovations brought from each of them. In challenging environments, for example, combining radio sensing and computer vision can strongly contribute to solving problems such as those introduced by obstructions or limited lighting. Machine learning algorithms, able to fuse heterogeneous and multi-modal data, are also a key element for understanding and inferring additional knowledge from raw and low-level data, able to create a new abstracting level that can significantly enhance many applications. This paper introduces the CONVERGE vision-radio concept, a new paradigm that explores the benefits of integrating two fields of knowledge towards the vision of View-to-Communicate, Communicate-to-View. The main concepts behind this vision, including supporting use cases and the proposed architecture, are presented. CONVERGE introduces a set of tools integrating wireless communications and computer vision to create a novel experimental infrastructure that will provide open datasets to the scientific community of both experimental and simulated data, enabling new research addressing various 6 G verticals, including telecommunications, automotive, manufacturing, media, and health.

Abstract
Breast cancer remains one of the most prevalent and deadly cancers worldwide, making accurate evaluation of molecular markers important for effective disease management. Biomarkers such as ER, PR, and HER2 are typically assessed because they help inform prognosis and guide treatment decisions. Predicting these characteristics from imaging can support earlier clinical intervention, reduce reliance on invasive procedures, and contribute to more personalized care. While radiomics and deep learning approaches have demonstrated potential, comprehensive comparisons across these methods are still limited. This study evaluated handcrafted features, deep features, and end-to-end deep learning models for predicting ER, PR, and HER2 status from DCE-MRI. Each feature type was first assessed individually and then combined using early and late fusion. Handcrafted and deep features were processed through a pipeline that included resampling, dimensionality reduction, and model selection, while end-to-end models were trained using different initialization strategies and loss functions. The best models achieved AUCs of 0.659 for ER, 0.679 for PR, and 0.686 for HER2. Although late fusion generally improved performance, bias toward the majority classes persisted. Overall, the results suggest that combining different modeling strategies may enhance robustness in breast cancer characterization. © 2025 IEEE.

Abstract