António Luís Sousa

Abstract
AbstractWith the rapid growth of Deep Learning models and neural networks, the medical data available for training – which is already significantly less than other types of data – is becoming scarce. For that purpose, Generative Adversarial Networks (GANs) have received increased attention due to their ability to synthesize new realistic images. Our preliminary work shows promising results for brain MRI images; however, there is a need to distribute the workload, which can be supported by High-Performance Computing (HPC) environments. In this paper, we generate 256×256 MRI images of the brain in a distributed setting. We obtained an FIDRadImageNetof 10.67 for the DCGAN and 23.54 for the WGAN-GP, which are consistent with results reported in several works published in this scope. This allows us to conclude that distributing the GAN generation process is a viable option to overcome the computational constraints imposed by these models and, therefore, facilitate the generation of new data for training purposes.

Abstract
Medical imaging, mainly Magnetic Resonance Imaging (MRI), plays a predominant role in healthcare diagnosis. Nevertheless, the diagnostic process is prone to errors and is conditioned by available medical data, which might be insufficient. A novel solution is resorting to image generation algorithms to address these challenges. Thus, this paper presents a Deep Learning model based on a Deep Convolutional Generative Adversarial Network (DCGAN) architecture. Our model generates 2D MRI images of size 256x256, containing an axial view of the brain with a tumor. The model was implemented using ChainerMN, a scalable and flexible framework that enables faster and parallel training of Deep Learning networks. The images obtained provide an overall representation of the brain structure and the tumoral area and show considerable brain-tumor separation. For this purpose, and owing to their previous state-of-the-art results in general image-generation tasks, we conclude that GAN-based models are a promising approach for medical imaging.

Abstract
Healthcare environments are generating a deluge of sensitive data. Nonetheless, dealing with large amounts of data is an expensive task, and current solutions resort to the cloud environment. Additionally, the intersection of the cloud environment and healthcare data opens new challenges regarding data privacy. With this in mind, we propose MEDCLOUDCARE (MCC), a healthcare application offering medical image viewing and processing tools while integrating cloud computing and AI. Moreover, MCC provides security and privacy features, scalability and high availability. The system is intended for two user groups: health professionals and researchers. The former can remotely view, process and share medical imaging information in the DICOM format. Also, it can use pre-trained Machine Learning (ML) models to aid the analysis of medical images. The latter can remotely add, share, and deploy ML models to perform inference on DICOM images. MCC incorporates a DICOM web viewer enabling users to view and process DICOM studies, which they can also upload and store. Regarding the security and privacy of the data, all sensitive information is encrypted at rest and in transit. Furthermore, MCC is intended for cloud environments. Thus, the system is deployed using Kubernetes, increasing the efficiency, availability and scalability of the ML inference process.

Abstract
When dealing with electrocardiography (ECG) the main focus relies on the classification of the heart's electric activity and deep learning has been proving its value over the years classifying the heartbeats, exhibiting great performance when doing so. Following these assumptions, we propose a deep learning model based on a ResNet architecture with convolutional ID layers to classes the beats into one of the 4 classes: normal, atrial premature contraction, premature ventricular contraction and others. Experimental results with MIT-BIH Arrhythmia Database confirmed that the model is able to perform well, obtaining an accuracy of 96% when using stochastic gradient descent (SGD) and 83% when using adaptive moment estimation (Adam), SGD also obtained F1-scores over 90% for the four classes proposed. A larger dataset was created and tested as unforeseen data for the trained model, proving that new tests should be done to improve the accuracy of it.

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.