Abstract
Skin cancer is one of the most common types of cancer and, with its increasing incidence, accurate early diagnosis is crucial to improve prognosis of patients. In the process of visual inspection, dermatologists follow specific dermoscopic algorithms and identify important features to provide a diagnosis. This process can be automated as such characteristics can be extracted by computer vision techniques. Although deep neural networks can extract useful features from digital images for skin lesion classification, performance can be improved by providing additional information. The extracted pseudo-features can be used as input (multimodal) or output (multi-tasking) to train a robust deep learning model. This work investigates the multimodal and multi-tasking techniques for more efficient training, given the single optimization of several related tasks in the latter, and generation of better diagnosis predictions. Additionally, the role of lesion segmentation is also studied. Results show that multi-tasking improves learning of beneficial features which lead to better predictions, and pseudo-features inspired by the ABCD rule provide readily available helpful information about the skin lesion.

Abstract
Ca2+ imaging is a widely used microscopy technique to simultaneously study cellular activity in multiple cells. The desired information consists of cell-specific time series of pixel intensity values, in which the fluorescence intensity represents cellular activity. For static scenes, cellular signal extraction is straightforward, however multiple analysis challenges are present in recordings of contractile tissues, like those of the enteric nervous system (ENS). This layer of critical neurons, embedded within the muscle layers of the gut wall, shows optical overlap between neighboring neurons, intensity changes due to cell activity, and constant movement. These challenges reduce the applicability of classical segmentation techniques and traditional stack alignment and regions-of-interest (ROIs) selection workflows. Therefore, a signal extraction method capable of dealing with moving cells and is insensitive to large intensity changes in consecutive frames is needed. Here we propose a b-spline active contour method to delineate and track neuronal cell bodies based on local and global energy terms. We develop both a single as well as a double-contour approach. The latter takes advantage of the appearance of GCaMP expressing cells, and tracks the nucleus' boundaries together with the cytoplasmic contour, providing a stable delineation of neighboring, overlapping cells despite movement and intensity changes. The tracked contours can also serve as landmarks to relocate additional and manually-selected ROIs. This improves the total yield of efficacious cell tracking and allows signal extraction from other cell compartments like neuronal processes. Compared to manual delineation and other segmentation methods, the proposed method can track cells during large tissue deformations and high-intensity changes such as during neuronal firing events, while preserving the shape of the extracted Ca2+ signal. The analysis package represents a significant improvement to available Ca2+ imaging analysis workflows for ENS recordings and other systems where movement challenges traditional Ca2+ signal extraction workflows.

Abstract
The recent Covid-19 pandemic and the fact that wearing masks in public is now mandatory in several countries, created challenges in the use of face recognition systems (FRS). In this work, we address the challenge of masked face recognition (MFR) and focus on evaluating the verification performance in FRS when verifying masked vs unmasked faces compared to verifying only unmasked faces. We propose a methodology that combines the traditional triplet loss and the mean squared error (MSE) intending to improve the robustness of an MFR system in the masked-unmasked comparison mode. The results obtained by our proposed method show improvements in a detailed step-wise ablation study. The conducted study showed significant performance gains induced by our proposed training paradigm and modified triplet loss on two evaluation databases.

Abstract
Occupational stress is a complex process affecting health and performance. Air Traffic Control is a complex and demanding profession. The current study demonstrates the concept of using a biomonitoring wearable platform (BWP), that combines self-report measures with biomarkers, to track stress among Air Traffic Controllers. A wearable ECG device was used to gather continuously medical-grade ECG data along with a mobile app for daily stress perception, symptoms and events annotation. A total of 256 hours of data from 32 routine work shifts and 5 days-off, from 5 ATCs was recorded with 35 tagged events using Heart Rate Variability metrics- AVNN, RMSSD, pNN50 and LF/HF were computed from ECG data and analyzed during a) shifts vs days off; b) events vs non-events and c) before and after working pauses. ATCs showed low levels of chronic stress using self-reports. Results showed that stress symptomatology slightly increase from the beginning to the end of the shift (Md=1 to Md=2; p<0.05). Statistical significant physiological changes were found between shifts and days off for AVNN and LF/HF (p<0.05), showing higher physiological activation during shifts. A significant reduction of physiological arousal was verified after working pauses, particularly for AVNN and LF/IIF (p<0.001). Self-reported data also suggests the same trend (p<0.005). Findings reinforced the discriminatory power of AVNN and LF/HF for short-term stress classification using HRV measurements. Results suggest that the rotating working system, with pause/resting periods included, effective acted as a recovery period.

Abstract
A non-parametric identification algorithm is proposed to identify Linear Time Periodic (LTP) systems. The period is unknown and can be any real positive number. The system is modelled as an ARX Linear Parameter Varying (LPV) system with a virtual scheduling signal consisting of two orthogonal sinusoids (a sine and a cosine) with a period equal to the system period. Hence, the system parameters are polynomial functions of the scheduling vector. As these polynomials may have infinite degree, a non-parametric model is adopted to describe the LPV system. This model is identified by a Gaussian Process Regression (GPR) algorithm where the system period is a hyperparameter. The performance of the proposed identification algorithm is illustrated through the identification of a simulated LTP continuous system described by a state-space model. The ARX-LTP discrete-time model estimated in the noiseless case was taken as the true model. Copyright (C) 2021 The Authors.

Abstract
Lung cancer is the type of cancer with highest mortality worldwide. Low-dose computerized tomography is the main tool used for lung cancer screening in clinical practice, allowing the visualization of lung nodules and the assessment of their malignancy. However, this evaluation is a complex task and subject to inter-observer variability, which has fueled the need for computer-aided diagnosis systems for lung nodule malignancy classification. While promising results have been obtained with automatic methods, it is often not straightforward to determine which features a given model is basing its decisions on and this lack of explainability can be a significant stumbling block in guaranteeing the adoption of automatic systems in clinical scenarios. Though visual malignancy assessment has a subjective component, radiologists strongly base their decision on nodule features such as nodule spiculation and texture, and a malignancy classification model should thus follow the same rationale. As such, this study focuses on the characterization of lung nodules as a means for the classification of nodules in terms of malignancy. For this purpose, different model architectures for nodule characterization are proposed and compared, with the final goal of malignancy classification. It is shown that models that combine direct malignancy prediction with specific branches for nodule characterization have a better performance than the remaining models, achieving an Area Under the Curve of 0.783. The most relevant features for malignancy classification according to the model were lobulation, spiculation and texture, which is found to be in line with current clinical practice.