Search

Due to the promise of transforming healthcare and medicine that Artificial Intelligence (AI) has posed, the number of applications has increased exponentially. These applications range from screening and disease diagnosis to prognosis, treatment planning, and follow-up. In complex topics such as childhood cancer, these techniques are being expanded with the ambition of improving the quality of care by allowing healthcare professionals to make more informed decisions. However, the adequate application of such techniques heavily depends on the data, which creates a set of challenges including collection, bias, and scarcity among others. Furthermore, ethical, legal, and regulatory frameworks increase even more the difficulties to develop AI-powered solutions. In this paper, we present an exhaustive literature review to identify and analyse public datasets targeting two common childhood cancer types, such as neuroblastoma and nephroblastoma. Moreover, the complex context for the development of AI- based software solutions is outlined. It includes the description of the most relevant techniques to address problems associated with data sharing and training. Finally, a set of code snippets is provided to perform exploratory analysis for the available data.

Introduction: Data-driven research has improved paediatric cancer outcomes for children. However, challenges in sharing data between institutions prevent the use of artificial intelligence (AI) to address substantial unmet needs in children diagnosed with cancer. Harmonising collected data can enable the application of AI for a greater understanding of paediatric cancers. The main goal of the paper was to analyse the currently used childhood cancer databases to identify a core of variables able to capture the most relevant data on the diagnosis and treatment of children and adolescents with cancer. Methods: We arbitrarily identified different types of existing databases dedicated to collecting data of patients with solid tumours, Umbrella, FAR-RMS; PARTNER; ERN PAEDCAN Registry; INSTRUCT and INRG; the common data elements for Rare Disease by Joint Research Centre. The different elements of the CRFs were analysed and ranked “essential” and “good to have”. Domains that included a group of variables structurally connected were identified. Each variable was defined by name, data type, description, and permissible values. Results: We identified six structural domains: Patient registration, Personal information, Disease History, Diagnosis, Treatment, and Follow-up and Events. For each of them, “essential” and “good to have” variables were defined. Discussion: Data harmonisation is essential for enhancing integration and comparability in research. By standardizing data formats and variables, researchers can facilitate data sharing, collaboration, and analysis across multiple studies and datasets. Embracing data harmonization practices will advance application of AI, scientific knowledge, improve research reproducibility, and contribute to evidence-based decision-making in various fields.

Abstract This paper presents a framework for complete simulation and verification of Serial Digital Interface (SDI) video using a verilog test-bench and geared toward FPGAs. This framework permits simulating the entire process: from test video signal generation to protocol verification in the FPGA which implements the Device Under Test (DUT). The novelty in the design is the combination of a customized test video signal generator with an implementation clone of DUT transceiver for in-depth protocol debugging. Identical input test patterns of the video protocol under test are generated and fed to DUT for verification. Thus, the model not only permits to evaluate the SDI transport layer but also validates the implementation at ultra low pixel level of the video format. This approach provides two advantages: cost saving in terms of additional lab test equipment and delivering all-in-one test solution to verify design and implementation. A practical implementation using a test example of a macroblock processing chain using SDI video interface shows the viability of the proposed framework for video protocol testing.

An amendment to this paper has been published and can be accessed via the original article.

BackgroundIn this paper we present a model of parameters to aesthetically characterize films using a multi-disciplinary approach: by combining film theory, visual low-level video descriptors (modeled in order to supply aesthetic information) and classification techniques using machine and deep learning.MethodsFour different tests have been developed, each for a different application, proving the model's usefulness. These applications are: aesthetic style clustering, prediction of production year, genre detection and influence on film popularity.ResultsThe results are compared against high-level information to determine the accuracy of the model to classify films without knowing such information previously. The main difference with other film characterization approaches is that we are able to isolate the influence of high-level descriptors to really understand the relevance of low-level features and, accordingly propose a useful set of low-level visual descriptors for that purpose. This model has been tested with a representative number of films to prove that it can be used for different applications.

Elderly people care is a major challenge for the smart-cities of future. This represents a valuable opportunity to develop scalable applications to cover the special needs in terms of health monitoring and accessibility for people with cognitive impairments. In this paper, a complete system to support daily activities of elderly people based on a multi-sensor scheme is presented. This system is intended to be deployed not only at home, but also at crowded places, such as daily care centers. A multi-layer architecture is drawn to ensure system modularity and interoperability of heterogeneous data with concurrent services. The proposed system includes a set of algorithms for data gathering and processing to detect abnormal events in the considered scenarios. The experiments performed in real scenarios have led to a good performance of the algorithms proposed as well as high accuracy in event detection for both environments.

Despite its proven potential for systemic change, large-scale investment (both public and private) in sustainable homes still faces barriers, often caused by insecurity about personal, societal and financial returns on investment and a lack of clarity about concrete elements of sustainable age-friendly living environments and the choice of building, retrofitting and adaptation measures to be implemented. The projects that contributed to this workshop are developing solutions to tackle these barriers and propose a holistic and integrated approach to progress on implementation.