Abstract
Lung cancer treatments that are accurate and effective are urgently needed. The diagnosis of advanced-stage patients accounts for the majority of the cases, being essential to provide a specialized course of treatment. One emerging course of treatment relies on target therapy through the testing of biomarkers, such as the Epidermal Growth Factor Receptor (EGFR) gene. Such testing can be obtained from invasive methods, namely through biopsy, which may be avoided by applying machine learning techniques to the imaging phenotypes extracted from Computerized Tomography (CT). This study aims to explore the contribution of ensemble methods when applied to the prediction of EGFR mutation status. The obtained results translate in a direct correlation between the semantic predictive model and the outcome of the combined ensemble methods, showing that the utilized features do not have a positive contribution to the predictive developed models.

Abstract
The scarcity of balanced and annotated datasets has been a recurring problem in medical image analysis. Several researchers have tried to fill this gap employing dataset synthesis with adversarial networks (GANs). Breast magnetic resonance imaging (MRI) provides complex, texture-rich medical images, with the same annotation shortage issues, for which, to the best of our knowledge, no previous work tried synthesizing data. Within this context, our work addresses the problem of synthesizing breast MRI images from corresponding annotations and evaluate the impact of this data augmentation strategy on a semantic segmentation task. We explored variations of image-to-image translation using conditional GANs, namely fitting the generator's architecture with residual blocks and experimenting with cycle consistency approaches. We studied the impact of these changes on visual verisimilarity and how an U-Net segmentation model is affected by the usage of synthetic data. We achieved sufficiently realistic-looking breast MRI images and maintained a stable segmentation score even when completely replacing the dataset with the synthetic set. Our results were promising, especially when concerning to Pix2PixHD and Residual CycleGAN architectures.

Abstract
Biometric recognition and presentation attack detection (PAD) methods strongly rely on deep learning algorithms. Though often more accurate, these models operate as complex black boxes. Interpretability tools are now being used to delve deeper into the operation of these methods, which is why this work advocates their integration in the PAD scenario. Building upon previous work, a face PAD model based on convolutional neural networks was implemented and evaluated both through traditional PAD metrics and with interpretability tools. An evaluation on the stability of the explanations obtained from testing models with attacks known and unknown in the learning step is made. To overcome the limitations of direct comparison, a suitable representation of the explanations is constructed to quantify how much two explanations differ from each other. From the point of view of interpretability, the results obtained in intra and inter class comparisons led to the conclusion that the presence of more attacks during training has a positive effect in the generalisation and robustness of the models. This is an exploratory study that confirms the urge to establish new approaches in biometrics that incorporate interpretability tools. Moreover, there is a need for methodologies to assess and compare the quality of explanations.

Abstract
Introduction:The lack of engagement and the shortage of motivation and drive, also referred to as apathy, negatively impacts the effectiveness and adherence to treatment and the general well-being of people with neurocognitive disorders (NCDs), such as dementia. Methodology:The hypothesis raised states that the engagement of people with dementia during their non-invasive treatments for NCDs is affected by the noisy source levels and negative auditory stimuli present within environmental treatment settings. An online survey was conducted with the study objectives to assess 1) the engagement levels of dementia patients while interacting with others at home versus in therapy facilities, 2) the emotions perceived when interacting with people at home compared to therapy sessions, 3) the perceived loudness of the environment at home versus in therapy facilities, and 4) which source sounds negatively impact the patients at home and during therapy sessions. A purposive sampling (n=62) targeting relatives, friends, and caregivers of dementia patients was conducted via online community forums in the DACH region. Moreover, a recording session was conducted in a psychotherapist’s office to verify the answer tothe questionnaire on the noise sources perceived in therapy facilities. Results and Discussion:The raised hypothesis that disruptive auditory stimuli and noise levels influence the engagement levels of demented individuals during treatment is confirmed as the engagement is affected by the perceived noise disruptions when comparing perceived noise levels and engagement at home to those in treatment facilities.Significant statistical results were found between the lower engagement of demented individuals when interacting with people during therapy sessions compared to higher engagement in-home interactions. Furthermore, negatively perceived sound sources can be found in both therapy facilities and home settings. The noise sound sources identified, such as human voices, household appliances and household noises, while recording inthe psychotherapist’s office align with the questionnaire responses received on this topic. The findings indicate that the perceived heightened noise levels in therapy facilities stand in correlation with the lowered engagement rate perceived during the therapy session compared to the lower noise level and higher engagement encountered when demented individuals interact at home. Conclusion:If the identified noise elements are masked or replaced by other auditory stimuli that promote a soothing soundscape, the original disturbances encountered during therapy and the lack of engagement can possibly be minimized. Further studies need to be conducted in the prototyping of a noise intervention tool to analyze the impact on lack of engagement through noise disturbances.Keywords. Noise, Engagement, Dementia, Therapy, Apathy.INTRODUCTIONNeurocognitive disorders (NCDs) are a steadily rising global public health concern. In 2020, around 50 million people worldwide lived with major NCDs, specifically dementia, with nearly 10 million new cases per year1NCDs can be found in many diseases, including Alzheimer, Parkinson, Huntington, and Creutzfeldt-Jakob (Reith, 2018). The causes of NCDs are typically associated with advanced age. Still, it can occur from incidents such as traumatic brain injuries, infections, thyroid problems, damage to the blood vessels, and other causes (Kane et al., 2017), increasingly affecting a wide range of people and age groups. Successful treatment methods are limited and can be split into two main categories, invasive and non-invasive methods.Invasive treatment methods are surgical procedures, such as Deep Brain Stimulation (DBS), a neurosurgical procedure in which a neurotransmitter is placed in the brain to send electrical 1World Health Organization, Dementia [website] https://www.who.int/news-room/fact-sheets/detail/dementia(accessed 12 April 2021)

Abstract
The transport of patients from the inpatient service to the operating room is a recurrent task in a hospital routine. This task is repetitive, non-ergonomic, time consuming, and requires the labor of patient transporters. In this paper is presented a system, named Connected Driverless Wheelchair, that can receive transportation requests directly from the hospital information management system, pick up patients at their beds, navigate autonomously through different floors, avoid obstacles, communicate with elevators, and drop patients off at the designated operating room. As a result, a prototype capable of transporting patients autonomously in hospital environments was obtained. Although it was impossible to test the final developed system at the hospital as planned, due to the COVID-19 pandemic, the extensive tests conducted at the robotics laboratory facilities, and our previous experience in integrating mobile robots in hospitals, allowed to conclude that it is perfectly prepared for this integration to be carried out.The achieved results are relevant since this is a system that may be applied to support these types of tasks in the future, making the transport of patients more efficient (both from a cost and time perspective), without unpredictable delays and, in some cases, safer.

Abstract
The worldwide pandemic caused by the new coronavirus (COVID-19) has encouraged the development of multiple computer-aided diagnosis systems to automate daily clinical tasks, such as abnormality detection and classification. Among these tasks, the segmentation of COVID lesions is of high interest to the scientific community, enabling further lesion characterization. Automating the segmentation process can be a useful strategy to provide a fast and accurate second opinion to the physicians, and thus increase the reliability of the diagnosis and disease stratification. The current work explores a CNN-based approach to segment multiple COVID lesions. It includes the implementation of a U-Net structure with a ResNet34 encoder able to deal with the highly imbalanced nature of the problem, as well as the great variability of the COVID lesions, namely in terms of size, shape, and quantity. This approach yields a Dice score of 64.1%, when evaluated on the publicly available COVID-19-20 Lung CT Lesion Segmentation GrandChallenge data set. © 2021 IEEE