Abstract
Introduction: Clinical trials of blended Internet-based treatments deliver a wealth of data from various sources, such as self-report questionnaires, diagnostic interviews, treatment platform log files and Ecological Momentary Assessments (EMA). Mining these complex data for clinically relevant patterns is a daunting task for which no definitive best method exists. In this paper, we explore the expressive power of the multi-relational Inductive Logic Programming (ILP) data mining approach, using combined trial data of the EU E-COMPARED depression trial. Methods: We explored the capability of ILP to handle and combine (implicit) multiple relationships in the E-COMPARED data. This data set has the following features that favor ILP analysis: 1) Time reasoning is involved; 2) there is a reasonable amount of explicit useful relations to be analyzed; 3) ILP is capable of building comprehensible models that might be perceived as putative explanations by domain experts; 4) both numerical and statistical models may coexist within ILP models if necessary. In our analyses, we focused on scores of the PHQ-8 self-report questionnaire (which taps depressive symptom severity), and on EMA of mood and various other clinically relevant factors. Both measures were administered during treatment, which lasted between 9 to 16 weeks. Results: E-COMPARED trial data revealed different individual improvement patterns: PHQ-8 scores suggested that some individuals improved quickly during the first weeks of the treatment, while others improved at a (much) slower pace, or not at all. Combining self-reported Ecological Momentary Assessments (EMA), PHQ-8 scores and log data about the usage of the ICT4D platform in the context of blended care, we set out to unveil possible causes for these different trajectories. Discussion: This work complements other studies into alternative data mining approaches to E-COMPARED trial data analysis, which are all aimed to identify clinically meaningful predictors of system use and treatment outcome. Strengths and limitations of the ILP approach given this objective will be discussed.

Abstract
Human gait analysis is of utmost importance in understanding several aspects of human movement. In clinical practice, characterizing movement in order to obtain accurate and reliable information is a major challenge, and physicians usually rely on direct observation in order to evaluate a patient's motor abilities. In this contribution, a system that can objectively analyze the patients gait and generate an on the fly, targeted and optimized gait analysis report is presented. It is an extension to an existing system that could be used without interfering with the healthcare environment, which did not provide any on the fly feedback to physicians. Patient data are acquired using Kinect v2, followed by data processing, gait specific feature extraction, ending with the generation of a quantitative on the fly report. To the best of our knowledge, the complete system fills the gap as a proper gait analysis system, i.e., a low-cost tool that can be applied without interfering with the healthcare environment, provide quantitative gait information and on the fly feedback to physicians through a motion quantification report that can be useful in multiple areas. © 2018 IEEE.

Abstract
In medical image analysis applications, the availability of the large amounts of annotated data is becoming increasingly critical. However, annotated medical data is often scarce and costly to obtain. In this paper, we address the problem of synthesizing retinal color images by applying recent techniques based on adversarial learning. In this setting, a generative model is trained to maximize a loss function provided by a second model attempting to classify its output into real or synthetic. In particular, we propose to implement an adversarial autoencoder for the task of retinal vessel network synthesis. We use the generated vessel trees as an intermediate stage for the generation of color retinal images, which is accomplished with a generative adversarial network. Both models require the optimization of almost everywhere differentiable loss functions, which allows us to train them jointly. The resulting model offers an end-to-end retinal image synthesis system capable of generating as many retinal images as the user requires, with their corresponding vessel networks, by sampling from a simple probability distribution that we impose to the associated latent space. We show that the learned latent space contains a well-defined semantic structure, implying that we can perform calculations in the space of retinal images, e.g., smoothly interpolating new data points between two retinal images. Visual and quantitative results demonstrate that the synthesized images are substantially different from those in the training set, while being also anatomically consistent and displaying a reasonable visual quality.

Abstract
Background Changes in the retinal vessel caliber are associated with a variety of major diseases, namely diabetes, hypertension and atherosclerosis. The clinical assessment of these changes in fundus images is tiresome and prone to errors and thus automatic methods are desirable for objective and precise caliber measurement. However, the variability of blood vessel appearance, image quality and resolution make the development of these tools a non-trivial task. Metholodogy A method for the estimation of vessel caliber in eye fundus images via vessel cross-sectional intensity profile model fitting is herein proposed. First, the vessel centerlines are determined and individual segments are extracted and smoothed by spline approximation. Then, the corresponding cross-sectional intensity profiles are determined, post-processed and ultimately fitted by newly proposed parametric models. These models are based on Difference-of-Gaussians (DoG) curves modified through a multiplying line with varying inclination. With this, the proposed models can describe profile asymmetry, allowing a good adjustment to the most difficult profiles, namely those showing central light reflex. Finally, the parameters of the best-fit model are used to determine the vessel width using ensembles of bagged regression trees with random feature selection. Results and conclusions The performance of our approach is evaluated on the REVIEW public dataset by comparing the vessel cross-sectional profile fitting of the proposed modified DoG models with 7 and 8 parameters against a Hermite model with 6 parameters. Results on different goodness of fitness metrics indicate that our models are constantly better at fitting the vessel profiles. Furthermore, our width measurement algorithm achieves a precision close to the observers, outperforming state-of-the art methods, and retrieving the highest precision when evaluated using cross-validation. This high performance supports the robustness of the algorithm and validates its use in retinal vessel width measurement and possible integration in a system for retinal vasculature assessment.

Abstract
Background: Stress is a complex process with an impact on health and performance. The use of wearable sensor-based monitoring systems offers interesting opportunities for advanced health care solutions for stress analysis. Considering the stressful nature of firefighting and its importance for the community’s safety, this study was conducted for firefighters. Objectives: A biomonitoring platform was designed, integrating different biomedical systems to enable the acquisition of real time Electrocardiogram (ECG), computation of linear Heart Rate Variability (HRV) features and collection of perceived stress levels. This platform was tested using an experimental protocol, designed to understand the effect of stress on firefighter’s cognitive performance, and whether this effect is related to the autonomic response to stress. Method: The Trier Social Stress Test (TSST) was used as a testing platform along with a 2-Choice Reaction Time Task. Linear HRV features from the participants were acquired using an wearable ECG. Self-reports were used to assess perceived stress levels. Results: The TSST produced significant changes in some HRV parameters (AVNN, SDNN and LF/HF) and subjective measures of stress, which recovered after the stress task. Although these short-term changes in HRV showed a tendency to normalize, an impairment on cognitive performance was found after performing the stress event. Conclusion: Current findings suggested that stress compromised cognitive performance and caused a measurable change in autonomic balance. Our wearable biomonitoring platform proved to be a useful tool for stress assessment and quantification. Future studies will implement this biomonitoring platform for the analysis of stress in ecological settings. © 2018 Rodrigues et al.

Abstract
Breast cancer is one of the leading causes of female death worldwide. The histological analysis of breast tissue allows for the differentiation of the tissue suspected to be abnormal into four classes: normal tissue, benign tumor, in situ carcinoma and invasive carcinoma. Automatic diagnostic systems can help in that task. In this sense, this work propose a deep neural network approach using transfer learning to classify breast cancer histology images. First, the added top layers are trained and a second fine-tunning is done on some feature extraction layers that are frozen previously. The used network is an Inception Resnet V2. In order to overcome the lack of data, data augmentation is performed too. This work is a suggested solution for the ICIAR 2018 BACH-Challenge and the accuracy is 0.76 in the blind test set. © 2018, Springer International Publishing AG, part of Springer Nature.