This paper aims to introduce my PhD research project, which is focused on scalable deep learning and its applications in the medical context. This project aims to design new DL algorithms or to adapt existing ones, to scalable architectures (e.g., parallel computers, GPUs), to improve the performance of typical ML tasks, such as classifications, and to experiment with them in the analysis of biomedical data, such as bioimages or molecular data. These applications are widely present in current literature thus representing a challenging opportunity. In addition to common DL and HPC approaches, the use of edge devices (i.e., Nvidia Jetson) is being explored, since this may be useful in a medical context using some key features of the edge computing paradigm (such as keeping data near the source) that are significant, i.e., for privacy reasons or legal compliance (i.e., European GPDR). My main investigated applications are on bioimages, such as Computed Tomography (CT) or functional Magnetic resonance imaging (fMRI). Research is being carried out to investigate current methodologies and how to improve them possibly. Moreover, a lot of experiments are carried out to demonstrate the impact of these approaches on traditional medical strategies. This work resulted in some experiments on the classification of medical images (CTs), medical signals (ECG), and gene expression data. My current work’s primary focus, boosted by a three-month collaboration with the University of Groningen, involves an extensive project on classifying fMRIs using Machine Learning techniques and concepts from graph theory tailored to exploit High-Performance Computing (HPC) infrastructures.