Abstract
Deep Inferior Epigastric Perforator (DIEP) flap breast reconstruction relies on the precise identification of perforator vessels supplying blood to transferred tissue. Traditional manual mapping from preoperative imaging is timeconsuming and subjective. To address this, AVA, a semi-automated perforator detection algorithm, was developed to analyze angiography images. AVA follows a three-step process: automated anatomical segmentation, manual annotation of perforators, and segmentation of perforator courses. This approach enhances accuracy, reduces subjectivity, and accelerates the mapping process while generating quantitative reports for surgical planning. To streamline integration into clinical workflows, AVA has been embedded into PACScenter, a medical imaging platform, leveraging DICOM encapsulation for seamless data exchange within a Vendor Neutral Archive (VNA). This integration allows surgeons to interactively annotate perforators, adjust parameters iteratively, and visualize detailed anatomical structures. AVA-PACScenter integration eliminates workflow disruptions by providing real-time perforator analysis within the surgical environment, ultimately improving preoperative planning and intraoperative guidance. Currently undergoing clinical feasibility testing, this integration aims to enhance DIEP flap reconstruction efficiency by reducing manual inputs, improving mapping precision, and facilitating long-term report storage within Dicoogle. By automating perforator analysis, AVA represents a significant advancement toward data-driven, patient-centered surgical planning.

Abstract
The topology of low-voltage (LV) distribution grids is often partially known or inaccurately documented by grid operators, including line and cable characteristics, hindering the effective integration and management of Distributed Energy Resources (DERs). This paper presents a data-driven method to reconstruct LV grid topologies using only voltage measurements from customers' smart meters. The approach relies on an adapted genetic algorithm (GA) that iteratively explores candidate configurations, guided by a score function that evaluates both the physical plausibility of estimated line impedances and their consistency with noisy voltage data, which is progressively corrected throughout the process, i.e., the method also filters out errors affecting the initial measurements. The method requires no prior information on grid connectivity and demonstrates robustness to measurement noise, making it well suited for real-world deployment. © 2025 IEEE.

Abstract
Wireless communication over the ocean surface is challenged by the absence of infrastructure, dynamic propagation conditions, variations in node position and orientation, and signal degradation from reflections, scattering, and absorption. To evaluate the feasibility of long-range, low-power communication in such environments, field trials were conducted using LoRa's Chirp Spread Spectrum (CSS) modulation with E22-900T22S modules operating at 868 MHz. Tests were performed over nearshore ocean water using omnidirectional antennas. One antenna was mounted on a buoy close to the surface, and the other on a movable station, while varying transmission power, bit rate, and distance. Performance was assessed through signal quality, Packet Delivery Ratio (PDR), and throughput measurements, with results indicating that a log-distance Received Signal Strength Indicator (RSSI) model, with fitted parameters showing high correlation, can describe the observed behavior across configurations. LoRa achieved up to 1.7 km range with over 60% PDR at 10 dBm and 2.4kbs-1, demonstrating its potential for ocean-surface communication and aiding in optimal configuration for maritime applications. © 2025 Marine Technology Society.

Abstract
Polarization-based fiber sensors rely on the dynamics of the Stokes vector at the output of the optical fiber to probe stimuli that induce polarization variations. However, these sensors often suffer from limitations in sensitivity, precision, and reproducibility. In this work, we address these challenges by incorporating concepts from the Mueller matrix formalism to enhance the capabilities of such sensors. Specifically, we measure the Mueller matrix in the polarization basis that describes how the polarization evolves inside the optical fiber. Leveraging this formalism, we configure the system as a precise sensor to detect deformations along the fiber. By utilizing the Fisher Information framework, we significantly improve accuracy and resolution, enabling the detection of subtle perturbations with greater precision. This study introduces a novel approach for precise polarization control and advanced fiber-based sensing applications.

Abstract
Students spend 30 % of their lives indoors; therefore, a healthy indoor air quality (IAQ) is crucial for their well-being and academic performance in Higher Education Institutions. This review highlights the interventions for improving Indoor Enviclassrooms considering climate change by discussing ventilation techniques, phytoremediation, and building features designed to improve noise levels, thermal comfort, lighting and to reduce odor. Awareness and literacy are enhanced through the student's engagement by offering real-time monitoring knowledge of Indoor Environmental Quality using inexpensive smart sensors combined with IoT technology. Eco-friendly strategies are also highlighted to promote sustainability.

Abstract
Lung cancer remains the leading cause of cancer related deaths globally, responsible for approximately 1.8 million deaths each year. A key contributor to this high mortality rate is the late-stage diagnosis of the disease, underscoring the urgent need for effective early detection strategies. Low-dose computed tomography (CT) has shown great value in early screening, particularly when paired with clinical information. Clinical data, while valuable, lacks spatial and morphological insights essential for comprehensive evaluation. Combining both modalities offers a more holistic approach for lung cancer classification. This study presents AI-based methods for lung cancer classification using unimodal approaches - structured clinical data and chest CT imaging - alongside a novel multimodal deep learning framework that integrates both data types to classify lung nodules as malignant or benign. For the clinical modality, machine learning models including logistic regression, random forests, LightGBM, XGBoost, and multilayer perceptrons were evaluated with extensive hyperparameter tuning. In the imaging modality, ResNet18 and ResNet34 convolutional neural networks were used, with and without data augmentation. The study explored both intermediate and late fusion strategies to combine modality-specific representations. Results show that multimodal models consistently outperformed their unimodal counterparts, achieving a best-case area under the ROC curve (AUC) of 0.9138, with an accuracy of 0.8424 and an F1-score of 0.8422. These findings highlight the complementary strengths of imaging and clinical data and support the growing potential of multimodal deep learning in improving diagnostic accuracy in lung cancer classification. © 2025 IEEE.