Abstract
Epilepsy is a major neurological disorder affecting approximately 1% of the world population, where seizure semiology is an essential tool for clinical evaluation of seizures. This includes qualitative visual inspection of videos from the seizures in epilepsy monitoring units by epileptologists. In order to support this clinical diagnosis process, promising deep learning-based systems were proposed. However, these indicate that video datasets of epileptic seizures are still rare and limited in size. In order to enable the full potential of AI systems for epileptic seizure diagnosis support and research, a novel collaborative development framework is proposed for a scalable DL-assisted clinical research and diagnosis support of epileptic seizures. The designed cloud-based approach integrates our deployed and tested NeuroKinect data acquisition pipeline into an MLOps framework to scale data set extension and analysis to a multi-clinical utilization. The proposed development framework incorporates an MLOps approach, to ensure convenient collaboration between clinicians and data scientists, providing continuous advantages to both user groups. It addresses methods for efficient utilization of HW, SW and human resources. In the future, the system is going to be expanded with several AI-based tools. Such as DL-based automated 3D motion capture (MoCap), 3D movement analysis support, quantitative seizure semiology analysis tools, video-based MOI and seizure classification. © 2021 IEEE

Abstract
For the first time in Europe hundreds of rare disease (RD) experts team up to actively share and jointly analyse existing patient’s data. Solve-RD is a Horizon 2020-supported EU flagship project bringing together >300 clinicians, scientists, and patient representatives of 51 sites from 15 countries. Solve-RD is built upon a core group of four European Reference Networks (ERNs; ERN-ITHACA, ERN-RND, ERN-Euro NMD, ERN-GENTURIS) which annually see more than 270,000 RD patients with respective pathologies. The main ambition is to solve unsolved rare diseases for which a molecular cause is not yet known. This is achieved through an innovative clinical research environment that introduces novel ways to organise expertise and data. Two major approaches are being pursued (i) massive data re-analysis of >19,000 unsolved rare disease patients and (ii) novel combined -omics approaches. The minimum requirement to be eligible for the analysis activities is an inconclusive exome that can be shared with controlled access. The first preliminary data re-analysis has already diagnosed 255 cases form 8393 exomes/genome datasets. This unprecedented degree of collaboration focused on sharing of data and expertise shall identify many new disease genes and enable diagnosis of many so far undiagnosed patients from all over Europe.

Abstract

Abstract
Lower limb amputation is a condition affecting millions of people worldwide. Patients are often prescribed with lower limb prostheses to aid their mobility, but these prostheses require frequent adjustments through an iterative and manual process, which heavily depends on patient feedback and on the prosthetist's experience. New computer-aided design and manufacturing technologies have been emerging as a way to improve the fitting process by creating virtual socket models. Statistical Shape modelling was used to create 3D models of transtibial (TT) and transfemoral (TF) sockets. Their generalization errors were, respectively, 6.8 +/- 1.8 mm and 10.5 +/- 1.6 mm, while specificity errors were 9.7 +/- 0.6 mm and 9.8 +/- 0.2 mm. In both models, a visual analysis showed that biomechanically meaningful features were captured: the largest variations found for both types were in the length of the residual limb and in the perimeter variation along the limb. The results obtained proved that statistical shape modelling methods can be applied to TF and TT sockets, with several potential applications in the orthoprosthetic field: generation of new plausible shapes and on-demand socket design adjustments.

Abstract
Statistics have demonstrated that one of the main factors responsible for the high mortality rate related to lung cancer is the late diagnosis. Precision medicine practices have shown advances in the individualized treatment according to the genetic profile of each patient, providing better control on cancer response. Medical imaging offers valuable information with an extensive perspective of the cancer, opening opportunities to explore the imaging manifestations associated with the tumor genotype in a non-invasive way. This work aims to study the relevance of physiological features captured from Computed Tomography images, using three different 2D regions of interest to assess the Epidermal growth factor receptor (EGFR) mutation status: nodule, lung containing the main nodule, and both lungs. A Convolutional Autoencoder was developed for the reconstruction of the input image. Thereafter, the encoder block was used as a feature extractor, stacking a classifier on top to assess the EGFR mutation status. Results showed that extending the analysis beyond the local nodule allowed the capture of more relevant information, suggesting the presence of useful biomarkers using the lung with nodule region of interest, which allowed to obtain the best prediction ability. This comparative study represents an innovative approach for gene mutations status assessment, contributing to the discussion on the extent of pathological phenomena associated with cancer development, and its contribution to more accurate Artificial Intelligence-based solutions, and constituting, to the best of our knowledge, the first deep learning approach that explores a comprehensive analysis for the EGFR mutation status classification.

Abstract
Lung cancer is the deadliest form of cancer, accounting for 20% of total cancer deaths. It represents a group of histologically and molecularly heterogeneous diseases even within the same histological subtype. Moreover, accurate histological subtype diagnosis influences the specific subtype's target genes, which will help define the treatment plan to target those genes in therapy. Deep learning (DL) models seem to set the benchmarks for the tasks of cancer prediction and subtype classification when using gene expression data; however, these methods do not provide interpretability, which is great concern from the perspective of cancer biology since the identification of the cancer driver genes in an individual provides essential information for treatment and prognosis. In this work, we identify some limitations of previous work that showed efforts to build algorithms to extract feature weights from DL models, and we propose using tree-based learning algorithms that address these limitations. Preliminary results show that our methods outperform those of related research while providing model interpretability.