Abstract
The importance of X-Ray imaging analysis is paramount for healthcare institutions since it is the main imaging modality for patient diagnosis, and deep learning can be used to aid clinicians in image diagnosis or structure segmentation. In recent years, several articles demonstrate the capability that deep learning models have in classifying and segmenting chest x-ray images if trained in an annotated dataset. Unfortunately, for segmentation tasks, only a few relatively small datasets have annotations, which poses a problem for the training of robust deep learning strategies. In this work, a semi-supervised approach is developed which consists of using available information regarding other anatomical structures to guide the segmentation when the groundtruth segmentation for a given structure is not available. This semi-supervised is compared with a fully-supervised approach for the tasks of lung segmentation and for multi-structure segmentation (lungs, heart and clavicles) in chest x-ray images. The semi-supervised lung predictions are evaluated visually and show relevant improvements, therefore this approach could be used to improve performance in external datasets with missing groundtruth. The multi-structure predictions show an improvement in mean absolute and Hausdorff distances when compared to a fully supervised approach and visual analysis of the segmentations shows that false positive predictions are removed. In conclusion, the developed method results in a new strategy that can help solve the problem of missing annotations and increase the quality of predictions in new datasets.

Abstract
Biofouling is the major factor that limits long-term monitoring studies with automated optical instruments. Protection of the sensing areas, surfaces, and structural housing of the sensors must be considered to deliver reliable data without the need for cleaning or maintenance. In this work, we present the design and field validation of different techniques for biofouling protection based on different housing materials, biocides, and transparent coatings. Six optical turbidity probes were built using polylactic acid (PLA), acrylonitrile butadiene styrene (ABS), PLA with copper filament, ABS coated with PDMS, ABS coated with epoxy and ABS assembled with a system for in situ chlorine production. The probes were deployed in the sea for 48 days and their anti-biofouling efficiency was evaluated using the results of the field experiment, visual inspections, and calibration signal loss after the tests. The PLA and ABS were used as samplers without fouling protection. The probe with chlorine production outperformed the other techniques, providing reliable data during the in situ experiment. The copper probe had lower performance but still retarded the biological growth. The techniques based on transparent coatings, epoxy, and PDMS did not prevent biofilm formation and suffered mostly from micro-biofouling.

Abstract

Abstract
Bone marrow edema (BME) or bone marrow lesion is the term attributed to an observed signal change within the bone marrow in magnetic resonance imaging (MRI). BME can be originated from multiple mechanisms, with pain being the main symptom. The presence of BME is an unspecific but sensitive sign with a wide differential diagnosis, that may act as a guide that leads to a systematic and correct interpretation of the magnetic resonance examination. An automatic approach for BME detection and quantification aims to reduce the overload of clinicians, decreasing human error and accelerating the time to the correct diagnosis. In this work, the bone region on the MRI slice was split into several patches and a CNN-based model was trained to detect BME in each patch from the MRI slice. The learning model developed achieved an AUC of 0.853 ± 0.056, showing that the CNN-based model can be used to detect BME in the MRI and confirming the patch strategy implemented to deal with the small data size and allowing the neural network to learn the specific information related with the classification task by reducing the region of the image to be considered. A learning model that can help clinicians with BME identification will decrease the time and the error for the diagnosis, and represent the first step for a more objective assessment of the BME.

Abstract
The smart cities paradigm covers multiple domains which span from citizens' accessibility and mobility to general infrastructures and services. Hence, smart cities can be seen as an excellent showcase of heterogeneity, namely at the data level. For this reason, they are a perfect candidate for linked data and semantic web concept applications. This powerful combination leads to interoperability at the data level which is one of the ultimate goals of the Internet of Things (IoT). In this reference frame, NGSI-LD is an open framework for context information processing consisting of both a semantic information model and a RESTful Application Programming Interface (API). This paper proposes a methodology for creating semantic data models in the context of IoT, namely to represent and describe data associated with digital twins. The methodology is presented in a practical way, through the process of creating an NGSI-LD semantic data model for the VALLPASS project, inserted in the traffic domain, which is one of the most popular in smart cities.

Abstract
Explanations of a model's biases or predictions are essential to medical image analysis. Yet, explainable machine learning approaches for medical image analysis are challenged by needs to preserve privacy of patient data, and by current trends in deep learning to use unsustainably large models and large datasets. We propose DeepFixCX for explainable and privacy-preserving medical image compression that is nimble and performant. We contribute a review of the field and a conceptual framework for simultaneous privacy and explainability via tools of compression. DeepFixCX compresses images without learning by removing or obscuring spatial and edge information. DeepFixCX is ante-hoc explainable and gives privatized post hoc explanations of spatial and edge bias without accessing the original image. DeepFixCX privatizes images to prevent image reconstruction and mitigate patient re-identification. DeepFixCX is nimble. Compression can occur on a laptop CPU or GPU to compress and privatize 1700 images per second of size 320 x 320. DeepFixCX enables use of low memory MLP classifiers for vision data; permitting small performance loss gives end-to-end MLP performance over 70x faster and batch size over 100x larger. DeepFixCX consistently improves predictive classification performance of a Deep Neural Network (DNN) by 0.02 AUC ROC on Glaucoma and Cervix Type detection datasets, and can improve multi-label chest x-ray classification performance in seven of 10 tested settings. In all three datasets, compression to less than 5% of original number of pixels gives matching or improved performance. Our main novelty is to define an explainability versus privacy problem and address it with lossy compression.This article is categorized under:Fundamental Concepts of Data and Knowledge > Explainable AICommercial, Legal, and Ethical Issues > Security and PrivacyFundamental Concepts of Data and Knowledge > Big Data Mining