Abstract
Due to inevitable differences between the data used for training modern CAD systems and the data encountered when they are deployed in clinical scenarios, the ability to automatically assess the quality of predictions when no expert annotation is available can be critical. In this paper, we propose a new method for quality assessment of retinal vessel tree segmentations in the absence of a reference ground-truth. For this, we artificially degrade expert-annotated vessel map segmentations and then train a CNN to predict the similarity between the degraded images and their corresponding ground-truths. This similarity can be interpreted as a proxy to the quality of a segmentation. The proposed model can produce a visually meaningful quality score, effectively predicting the quality of a vessel tree segmentation in the absence of a manually segmented reference. We further demonstrate the usefulness of our approach by applying it to automatically find a threshold for soft probabilistic segmentations on a per-image basis. For an independent state-of-the-art unsupervised vessel segmentation technique, the thresholds selected by our approach lead to statistically significant improvements in F1-score (+2.67%) and Matthews Correlation Coefficient (+3.11%) over the thresholds derived from ROC analysis on the training set. The score is also shown to correlate strongly with F1 and MCC when a reference is available.

Abstract
A new approach for robust edge detection on B-mode ultrasound images of the carotid artery is proposed in this paper. The proposed method uses anisotropic Gaussian derivative filters along with non-maximum suppression over the overall artery wall orientation in local regionS. The anisotropic filters allow using a wider integration scale along the edges while preserving the edge location precision. They also perform edge continuation, resulting in the connection of isolated edge points along linear segments, which is a valuable feature for the segmentation of the artery wall layerS. However, this usually results in false edges being detected near convex contours and isolated pointS. The use of non-maximum suppression over pooled local orientations is proposed to solve this issue. Experimental results are provided to demonstrate that the proposed edge detector outperforms other common methods in the detection of the lumen-intima and media-adventia layer interfaces of the carotid vessel wallS. Additionally, the resulting edges are more continuous and precisely located. © 2018 The Author(s).

Abstract
Health facilities produce an increasing and vast amount of data that must be efficiently analyzed. New approaches for healthcare monitoring are being developed every day and the Internet of Things (IoT) came to fill the still existing void on real-time monitoring. A new generation of mechanisms and techniques are being used to facilitate the practice of medicine, promoting faster diagnosis and prevention of diseases. We proposed a system that relies on IoT for storing and monitoring medical sensors data with analytic capabilities. To this end, we chose two approaches for storing this data which were thoroughly evaluated. Apache HBase presents a higher rate of data ingestion, when collaborating with the Kaa IoT platform, than Apache Cassandra, exhibiting good performance storing unstructured data, as presented in a healthcare environment. The outcome of this system has shown the possibility of a large number of medical sensors being simultaneously connected to the same platform (6000 records sent by the second or 48 ECG sensors with a frequency of 125Hz). The results presented in this paper are promising and should be further investigated as a comprehensive system would benefit the patient's diagnosis but also the physicians. © 2018 IEEE.

Abstract
In this work we propose a regression approach based on separability maximization (RASMa) for modeling a continuous-valued estimate of the stress level (we called it stress index) using some features extracted from electrocardiogram (ECG) data. Since no objective measure of the actual stress level (output) is available, finding the stress index cannot be addressed as a classical regression problem. Instead, the proposed approach finds the linear combination of features that maximizes the separability of stress index values for non-stress and stress events. In short, RASMa combines linear discriminant analysis with the Bhattacharyya distance, embedded in a leave-one-subject-out cross-validation scheme. A 26-case pilot study using 17 heart rate variability (HRV) features was conducted as a proof of concept. A near real-time application tool for monitoring stress level over time was also implemented based on the model obtained from the pilot study.

Abstract
We propose a deep learning-based pipeline that, given a low-dose computed tomography of a patient chest, recommends if a patient should be submitted to further lung cancer assessment. The algorithm is composed of a nodule detection block that uses the object detection framework YOLOv2, followed by a U-Net based segmentation. The found structures of interest are then characterized in terms of diameter and texture to produce a final referral recommendation according to the National Lung Screen Trial (NLST) criteria. Our method is trained using the public LUNA16 and LIDC-IDRI datasets and tested on an independent dataset composed of 500 scans from the Kaggle DSB 2017 challenge. The proposed system achieves a patient-wise recall of 89% while providing an explanation to the referral decision and thus may serve as a second opinion tool to speed-up and improve lung cancer screening.

Abstract
We propose UOLO, a novel framework for the simultaneous detection and segmentation of structures of interest in medical images. UOLO consists of an object segmentation module which intermediate abstract representations are processed and used as input for object detection. The resulting system is optimized simultaneously for detecting a class of objects and segmenting an optionally different class of structures. UOLO is trained on a set of bounding boxes enclosing the objects to detect, as well as pixel-wise segmentation information, when available. A new loss function is devised, taking into account whether a reference segmentation is accessible for each training image, in order to suitably backpropagate the error. We validate UOLO on the task of simultaneous optic disc (OD) detection, fovea detection, and OD segmentation from retinal images, achieving state-of-the-art performance on public datasets.