Abstract
The Douro Demarcated Region is fundamental to local cultural and economic identity. Despite its importance, the region faces the challenge of abandoned vineyard plots, caused, among other factors, by the high costs of maintaining vineyards on hilly terrain. To solve this problem, the European Union (EU) offers subsidies to encourage active cultivation, with the aim of protecting the region's cultural and environmental heritage. However, monitoring actively cultivated vineyards and those that have been abandoned presents considerable logistical challenges. With 43,843 vineyards spread over 250,000 hectares of rugged terrain, control of these plots is limited, which hampers the effectiveness of preservation and incentive initiatives. Currently, the EU only inspects 5 per cent of farmers annually, which results in insufficient coverage to ensure that subsidies are properly used and vineyards are actively maintained. To complement this limited monitoring, organisations such as the Instituto dos Vinhos do Douro e do Porto (IVDP) use aerial and satellite images, which are manually analysed to identify abandoned or active plots. To overcome these limitations, images can be analysed using deep learning methods, which have already shown great potential in agricultural applications. In this context, our research group has carried out some preliminary evaluations for the automatic detection of abandoned vineyards using deep learning models, which, despite showing promising results on the dataset used, proved to be limited when applied to images of the entire region. In this study, a new dataset was expanded to 137,000 images collected between 2018 and 2023, filling critical gaps in the previous datasets by including greater temporal and spatial diversity. Subsequently, a careful evaluation was carried out with various DL models. As a result, the ViT_b32 model demonstrated superior performance, achieving an average accuracy of 0.99 and an F1 score of 0.98, outperforming CNN-based models. In addition to the excellent results obtained, this dataset represents a significant contribution to advancing research in precision viticulture, providing a solid and relevant basis for future studies and driving the development of solutions applied to vineyard monitoring in the Douro Demarcated Region. These advances not only improve efficiency in detecting abandoned plots, but also contribute significantly to optimising the use of subsidies in the region.

Abstract
The Eurasian grapevine (Vitis vinifera L.) is one of the most extensively cultivated horticultural crop worldwide, with significant economic relevance, particularly in wine production. Accurate grapevine variety identification is essential for ensuring product authenticity, quality control, and regulatory compliance. Traditional identification methods have inherent limitations limitations; ampelography is subjective and dependent on skilled experts, while molecular analysis is costly and time-consuming. To address these challenges, recent research has focused on applying deep learning (DL) and machine learning (ML) techniques for grapevine variety identification. This study systematically analyses 37 recent studies that employed DL and ML models for this purpose. The objective is to provide a detailed analysis of classification pipelines, highlighting the strengths and limitations of each approach. Most studies use DL models trained on leaf images captured in controlled environments at distances of up to 1.2 m. However, these studies often fail to address practical challenges, such as the inclusion of a broader range of grapevine varieties, using data directly acquired in the vineyards, and the evaluation of models under adverse conditions. This review also suggests potential directions for advancing research in this field.

Abstract
The current progress of modern medicine is based on the resistance of malignant tumors in advanced medical treatments, as well as on the need to develop new therapeutic approaches. In the last few years, numerous studies have focused their attention on the promising use of nanomaterials, such as nanowires, zinc oxide, or mesoporous silica nanoparticles, among others. All these particles are studied in the treatment of cancer and metastasis prevention with the advantage of operating directly at the biomolecular scale. These are innovative designs of magnetic nanomaterials based on a core/shell approach that started to gain prominence due to their versatility to tailor properties of both core and shell and to offer multifunctionality, such as core protection, biofunctionalization platform, toxicity reduction, and enhanced biocompatibility. These nanowire structural improvements allow the development of new bioanalytical chemistry and medical diagnostics advanced tools that will bring about a new age of nanotechnology with widespread use of nanowires for biomedical applications.

Abstract
Great advances in stitching high-quality retinal images have been made in recent years. On the other hand, very few studies have been carried out on low-resolution retinal imaging. This work investigates the challenges of low-resolution retinal images obtained by the D-EYE smartphone-based fundus camera. The proposed method uses homography estimation to register and stitch low-quality retinal images into a cohesive mosaic. First, a Siamese neural network extracts features from a pair of images, after which the correlation of their feature maps is computed. This correlation map is fed through four independent CNNs to estimate the homography parameters, each specializing in different corner coordinates. Our model was trained on a synthetic dataset generated from the Microsoft Common Objects in Context (MSCOCO) dataset; this work added an important data augmentation phase to improve the quality of the model. Then, the same is evaluated on the FIRE retina and D-EYE datasets for performance measurement using the Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM). The obtained results are promising: the average PSNR was 26.14 dB, with an SSIM of 0.96 on the D-EYE dataset. Compared to the method that uses a single neural network for homography calculations, our approach improves the PSNR by 7.96 dB and achieves a 7.86% higher SSIM score.

Abstract
Precision agriculture (PA) has advanced agricultural practices, offering new opportunities for crop management and yield optimization. The use of unmanned aerial vehicles (UAVs) in PA enables high-resolution data acquisition, which has been adopted across different agricultural sectors. However, its application for decision support in chestnut plantations remains under-represented. This study presents the initial development of a methodology for segmenting chestnut burrs from UAV-based imagery to estimate its productivity in point cloud data. Deep learning (DL) architectures, including U-Net, LinkNet, and PSPNet, were employed for chestnut burr segmentation in UAV images captured at a 30 m flight height, with YOLOv8m trained for comparison. Two datasets were used for training and to evaluate the models: one newly introduced in this study and an existing dataset. U-Net demonstrated the best performance, achieving an F1-score of 0.56 and a counting accuracy of 0.71 on the proposed dataset, using a combination of both datasets during training. The primary challenge encountered was that burrs often tend to grow in clusters, leading to unified regions in segmentation, making object detection potentially more suitable for counting. Nevertheless, the results show that DL architectures can generate masks for point cloud segmentation, supporting precise chestnut tree production estimation in future studies.

Abstract
Magnetic resonance imaging (MRI) is a non-invasive technique used in cardiac diagnosis. Using it, specialists can measure the masses and volumes of the right ventricle (RV), left ventricular cavity (LVC), and myocardium (MYO). Segmenting these structures is an important step before this measurement. However, this process can be laborious and error-prone when done manually. This paper proposes a multi-stage method for cardiac segmentation in short-axis MRI based on fully convolutional networks (FCNs). This automatic method comprises three main stages: (1) the extraction of a region of interest (ROI); (2) MYO and LVC segmentation using a proposed FCN called EAIS-Net; and (3) the RV segmentation using another proposed FCN called IRAX-Net. The proposed method was tested with the ACDC and M&Ms datasets. The main evaluation metrics are end-diastolic (ED) and end-systolic (ES) Dice. For the ACDC dataset, the Dice results (ED and ES, respectively) are 0.960 and 0.904 for the LVC, 0.880 and 0.892 for the MYO, and 0.910 and 0.860 for the RV. For the M&Ms dataset, the ED and ES Dices are 0.861 and 0.805 for the LVC, 0.733 and 0.759 for the MYO, and 0.721 and 0.694 for the RV. These results confirm the feasibility of the proposed method.