Abstract
Diabetic retinopathy (DR) detection is a critical retinal image analysis task in the context of early blindness prevention. Unfortunately, in order to train a model to accurately detect DR based on the presence of different retinal lesions, typically a dataset with medical expert's annotations at the pixel level is needed. In this paper, a new methodology based on the multiple instance learning (MIL) framework is developed in order to overcome this necessity by leveraging the implicit information present on annotations made at the image level. Contrary to previous MIL-based DR detection systems, the main contribution of the proposed technique is the joint optimization of the instance encoding and the image classification stages. In this way, more useful mid-level representations of pathological images can be obtained. The explainability of the model decisions is further enhanced by means of a new loss function enforcing appropriate instance and mid-level representations. The proposed technique achieves comparable or better results than other recently proposed methods, with 90% area under the receiver operating characteristic curve (AUC) on Messidor, 93% AUC on DR1, and 96% AUC on DR2, while improving the interpretability of the produced decisions.

Abstract
The segmentation and characterization of the ovarian structures are important tasks in gynecological and reproductive medicine. Ultrasound imaging is typically used for the medical diagnosis within this field but the understanding of the images can be difficult due to their characteristics. Furthermore, the complexity of ultrasound data may lead to a heavy image processing, which makes the application of classical methods of computer vision difficult. This work presents the first supervised fully convolutional neural network (fCNN) for the automatic segmentation of ovarian structures in B-mode ultrasound images. Due to the small dataset available, only 57 images were used for training. In order to overcome this limitation, several regularization techniques were used and are discussed in this paper. The experiments show the ability of the fCNN to learn features to distinguish ovarian structures, achieving a Dice similarity coefficient (DSC) of 0.855 for the segmentation of the stroma and a DSC of 0.955 for the follicles. When compared with a semi-automatic commercial application for follicle segmentation, the proposed fCNN achieved an average improvement of 19%. © Springer Nature Switzerland AG 2019.

Abstract
Deep learning models have been successfully used in medical image analysis problems but they require a large amount of labeled images to obtain good performance. However, such large labeled datasets are costly to acquire. Active learning techniques can be used to minimize the number of required training labels while maximizing the model's performance. In this work, we propose a novel sampling method that queries the unlabeled examples that maximize the average distance to all training set examples in a learned feature space. We then extend our sampling method to define a better initial training set, without the need for a trained model, by using Oriented FAST and Rotated BRIEF (ORB) feature descriptors. We validate MedAL on 3 medical image datasets and show that our method is robust to different dataset properties. MedAL is also efficient, achieving 80% accuracy on the task of Diabetic Retinopathy detection using only 425 labeled images, corresponding to a 32% reduction in the number of required labeled examples compared to the standard uncertainty sampling technique, and a 40% reduction compared to random sampling.

Abstract
The majority of computer-Aided diagnosis methods for Alzheimer's disease (AD) from brain images either address only two stages of the disease at a time (and reduce the problem to binary classification) or do not exploit the ordinal nature of the different classes. An exception is the work by Fan et al. [1], which proposed an ordinal method that obtained better performance than traditional multiclass classification. Still, special care should be taken when data is class imbalanced, i.e. when some classes are overly represented when compared to others. Building on top of [1], this work makes use of a recently published ordinal classifier, which transforms the problem into sets of pairwise ranking problems, in order to address the class imbalance in the data [2]. Several methods were experimented with, using a Support Vector Machine as the underlying estimator. The pairwise ranking approach has shown promising results, both for traditional and imbalance metrics. © 2018 IEEE.

Abstract
Firefighting is a hazardous profession commonly exposed to high stress that can interfere with firefighter's health and performance. Nevertheless, on-duty stress levels quantitative evaluations are very rare in the literature. In order to investigate firefighters' occupational health in terms of stress perceptions, symptoms, and quantified physiological reactions under real-world conditions, an ambulatory assessment protocol was developed. Therefore, cardiac signal from firefighters (N =6) was continuously monitored during two shifts within a working week with a medical clinically certified equipment (VitalJacket®), allowing continuous electrocardiogram (ECG) and actigraphy measurement. Psychological data were collected with an android application, collecting potential stressful events, stress symptoms, and stress appraisal. A total of 130 hours of medical-quality ECG were collected, from which heart rate variability (HRV) metrics were extracted and analyzed. Statistical significant differences were found in some HRV metrics - AVNN, RMSSD, pNN50 and LF/HF - between events and non-events, showing higher levels of physiological stress during events (p<0.05). Stress symptoms increase from the beginning to the end of the shift (from 1.54 ± 0.52 to 2.01 ± 0.73), however the mean stress self-perception of events was very low (3.22 ± 2.38 in a scale ranging from 0 to 10). Negative and strong correlations were also found between stress symptoms and some time-domain ECG measures (AVNN, SDNN and pNN50). It can be concluded that stress may not always be detected when using merely self-reports. These results enhance the importance of combining both self-report and ambulatory high-quality physiological stress measures in occupational health settings. Future studies should investigate not only what causes stress but also its impact on health and well-being of these professionals, in order to contribute to the design of efficient stress-management interventions. © 2018 IEEE.

Abstract
Background: The tip of an optical fiber has been considered an attractive platform in Biology. The simple cleaved end of an optical fiber can be machined, patterned and/or functionalized, acquiring unique properties enabling the exploitation of novel optical phenomena. Prompted by the constant need to measure and manipulate nanoparticles, the invention of the Scanning Near-field Optical Microscopy (SNOM) triggered the optimization and development of novel fiber tip microfabrication methods. In fact, the fiber tip was soon considered a key element in SNOM by confining light to sufficiently small extensions, challenging the diffraction limit. As result and in consequence of the newly proposed "Lab On Tip" concept, several geometries of fiber tips were applied in three main fields: imaging (in Microscopy/Spectroscopy), biosensors and micromanipulation (Optical Fiber Tweezers, OFTs). These are able to exert forces on microparticles, trap and manipulate them for relevant applications, as biomolecules mechanical study or protein aggregates unfolding. Scope of review: This review presents an overview of the main achievements, most impactful studies and limitations of fiber tip-based configurations within the above three fields, along the past 10 years. Major conclusions: OFTs could be in future a valuable tool for studying several cellular phenomena such as neurodegeneration caused by abnormal protein fibrils or manipulating organelles within cells. This could contribute to understand the mechanisms of some diseases or biophenomena, as the axonal growth in neurons.