Abstract

This study presents the first application-ready demonstration of radio-frequency (RF) switches based on memristors fabricated through a combination of electrochemical exfoliation and liquid-liquid interfacial assembly (EC-LL). This 2D layer fabrication method yields uniform, low-defect bilayer MoS2 nanosheet networks without relying on high-temperature processes or hazardous gases typical of chemical vapor deposition (CVD), offering a low-cost and environmentally friendly route towards CMOS-compatible integration. Remarkably, the resulting devices exhibit robust unipolar resistive switching which simplifies biasing requirements and reduces power consumption. Reproducibility with retention of 104 sec, and endurance of 100 cycles is reported. RF measurements confirm reliable operation at millimeter wave (mmWave) frequencies across 10–110 GHz, demonstrating low insertion loss (0.42–0.9 dB), isolation >18 dB, and an intrinsic cut-off frequency of ~5.4 THz. Integration into Reconfigurable Intelligent Surface Unit Cells (RIS-UCs) further showcases the technology’s utility in next-generation mmWave communication systems, including 5G/6G and satellite applications. Simulations of a 24×24-element RIS panel confirm high gain (>21.6 dBi) and efficient beam steering (-60º, 60º degrees) over the 26.8–29.1 GHz band, while the ultra-low switching energy (~330 pJ per unit cell) enables zero static power consumption—critical for scalable and sustainable 6G infrastructure. This work establishes a new benchmark by delivering the first solution-processed, application-suitable 2D material in solid-state RF switches combining non-volatility, high-frequency operation, and CMOS integration potential. It marks a significant step toward reconfigurable, energy-efficient wireless communication platforms.

Abstract
Chest CT scans are essential in diagnosing lung abnormalities, including lung cancer, but their utility in training deep learning models is often pushed back by limited data availability, high labeling costs, and privacy concerns. To address these challenges, this study explores the use of score-based diffusion models for the conditional generation of lung CT scans slices. Two generation scenarios are explored: one limited to lung segmentation masks and another incorporating both lung and nodule segmentation mappings to guide the synthesis process. The proposed methods are custom U-Net architecture models trained to predict the scores in Variance Preserving (VP) and Variance Exploding (VE) Stochastic Differential Equations (SDEs), composing the primary ground for comparison in conditional sample generation. The results demonstrate the VP SDEs model's superiority in generating high-fidelity images, as evidenced by high SSIM (0.894) and PSNR (28.6) values, as well as low domain-specific FID (173.4), MMD (0.0133) and ECS (0.78) scores. The generated images consistently followed the conditional mapping guidance during the generation process, effectively producing realistic lung and nodule structures, highlighting their potential for data augmentation in medical imaging tasks. While the models achieved notable success in generating accurate 2D lung CT scan slices given simple conditional image region mappings, future work surrounds the extension of these methods to 3D conditional generation and the use of richer conditional mappings to account for broader anatomical variations. Nevertheless, this study holds promise for improvement in computer-aided systems through the support in deep learning model training for lung disease diagnosis and classification.

Abstract
Lung cancer is one of the leading causes of cancer-related deaths worldwide, mainly due to late diagnosis. Screening programs can benefit from Computer-Aided Diagnosis (CAD) systems that detect and classify lung nodules using Computed Tomography (CT) scans. A great proportion of the literature proposes deep learning models based on single and private datasets with no evaluation of their generalisation capability. The main goal of this work is to study and address the lack of generalisation to out-of-domain data (source domain different from the target domain). In this work, we propose using a ResNet architecture with 2.5D inputs capable of maintaining the spatial information of the nodules (3 input channels based on the anatomical planes). Secondly, we apply domain-specific data augmentation tailored for CT scans. Combined with data augmentation, using 2.5D inputs achieves the best results, both in in-domain data (LIDC-IDRI: N=1377 nodules; and LNDb: N=183 nodules) and in out-of-domain data (LUNGx: N=73 nodules). In in-domain data, an Area Under the Curve (AUC) of 0.914 was achieved in the internal test set and 0.746 in one of the external test sets. Notably, in out-of-domain data, where the ground-truth labels have been confirmed by biopsy, whereas the training data only involved radiologist annotation regarding the "likelihood of malignancy", AUC improves from 0.576 to 0.695, reaching a performance close to that of radiology experts. In the future, strategies should be applied to deal with the level of uncertainty of lung nodule annotations based solely on the observation of the CT scans.Clinical relevance- This work provides an automatic method for lung nodule malignancy classification based on CT scans, combined with generalisation methods that allow a good performance across different cohort populations and hospitals.

Abstract

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.