In 2019, a new virus, SARS-CoV-2, responsible for the COVID-19 disease, was discovered. Asymptomatic and mildly symptomatic patients were forced to quarantine and closely monitor their symptoms and vital signs, most of the time at home. This paper describes e-CoVig, a novel mHealth application, developed as an alternative to the current monitoring paradigm, where the patients are followed up by direct phone contact. The e-CoVig provides a set of functionalities for remote reporting of symptoms, vital signs, and other clinical information to the health services taking care of these patients. The application is designed to register and transmit the heart rate, blood oxygen saturation (${\mathrm{SpO}}_2$), body temperature, respiration, and cough. The system features a mobile application, a web/cloud platform, and a low-cost specific device to acquire the temperature and ${\mathrm{SpO}}_2$. The architecture of the system is flexible and can be configured for different operation conditions. Current commercial devices, such as oximeters and thermometers, can also be used and read using the optical character recognition (OCR) functionality of the system. The data acquired at the mobile application are sent automatically to the web/cloud application and made available in real-time to the medical staff, enabling the follow-up of several users simultaneously without the need for time consuming phone call interactions. The system was already tested for its feasibility and a preliminary deployment was performed on a nursing home showing promising results.

Ultrasound (US) images are corrupted by a type of signal-dependent noise, called speckle, difficult to remove or attenuate with the classical denoising methods. On the contrary, structural Magnetic Resonance Imaging (MRI) is usually a high resolution low noise image modality that involves complex and expensive equipment and long acquisition times. Herein, a deep learning-based pipeline for speckle removal in B-mode US medical images, based on cross modality transfer learning, is proposed. The architecture of the system is based on a pix2pix Generative Adversarial Network (GAN), D , able to denoise real B-mode US images by generating synthetic MRI-like versions by an image-to-image translation manner. The GAN D was trained using two classes of image pairs: i) a set consisting of authentic MRI images paired with synthetic US images generated through a dedicated US simulator based on another GAN, S , designed specifically for this purpose, and ii) a set comprising natural images paired with their corresponding noisy counterparts corrupted by Rayleigh noise. The denoising GAN proposed in this study demonstrates effective removal of speckle noise from B-mode US images. It successfully preserves the integrity of anatomical structures and avoids reconstruction artifacts, producing outputs that closely resemble typical MRI images. Comparative tests against other state-of-the-art methods reveal superior performance of the proposed denoising strategy across various reconstruction quality metrics.

The task of automatic text summarization produces a concise and fluent text summary while preserving key information and overall meaning. Recent approaches to document-level summarization have seen significant improvements in recent years by using models based on the Transformer architecture. However, the quadratic memory and time complexities with respect to the sequence length make them very expensive to use, especially with long sequences, as required by document-level summarization. Our work addresses the problem of document-level summarization by studying how efficient Transformer techniques can be used to improve the automatic summarization of very long texts. In particular, we will use the arXiv dataset, consisting of several scientific papers and the corresponding abstracts, as baselines for this work. Then, we propose a novel retrieval-enhanced approach based on the architecture which reduces the cost of generating a summary of the entire document by processing smaller chunks. The results were below the baselines but suggest a more efficient memory a consumption and truthfulness.