This paper describes PARADIM, a digital infrastructure designed to support research at the interface of data science and medical imaging, with a focus on Research Data Management best practices. The platform is built from open-source components and rooted in the FAIR principles through strict compliance with the DICOM standard. It addresses key needs in data curation, governance, privacy, and scalable resource management. Supporting every stage of the data science discovery cycle, the platform offers robust functionalities for user identity and access management, data de-identification, storage, annotation, as well as model training and evaluation. Rich metadata are generated all along the research lifecycle to ensure the traceability and reproducibility of results. PARADIM hosts several medical image collections and allows the automation of large-scale, computationally intensive pipelines (e.g., automatic segmentation, dose calculations, AI model evaluation). The platform fills a gap at the interface of data science and medical imaging, where digital infrastructures are key in the development, evaluation, and deployment of innovative solutions in the real world.
Category: Hard Questions: Health
Hard Questions: Health
-
A labeled clinical-MRI dataset of Nigerian brains
There is currently a paucity of neuroimaging data from the African continent, limiting the diversity of data from a significant proportion of the global population. This in turn diminishes global health research and innovation. To address this issue, we present and describe the first Magnetic Resonance Imaging (MRI) dataset from individuals in the African nation of Nigeria. This dataset contains pseudonymized structural MRI (T1w, T2w, FLAIR) data of clinical quality, with 35 images from healthy control subjects, 31 images from individuals diagnosed with age-related dementia, and 22 from individuals with Parkinson’s Disease. Given the potential for Africa to contribute to the global neuroscience community, this unique MRI dataset represents both an opportunity and benchmark for future studies to share data from the African continent.
-
Trainees’ perspectives and recommendations for catalyzing the next generation of NeuroAI researchers
At this critical juncture in the development of NeuroAI, we outline challenges and training needs of junior researchers working across AI and neuroscience. We also provide advice and resources to help trainees plan their NeuroAI careers.
-
From Crisis Management to the crisis of management: Accountability and Liberal Democracies in the Outbreak of the Covid-19 Pandemic
The outbreak of the COVID-19 pandemic shocked societies around the world. In their efforts to tailor their responses to the crisis to their own conditions for survival, from the outset governments tended to resort to arguments that limited accountability before their populations. Liberal democracies were no exception to this approach. In this context, their leaders used the metaphor of war to describe their position as guarantors of the population’s survival in the face of the new threat. Caught between uncertainty and the need to predict the nature and evolution of the invisible enemy, their responses called into question the political, professional and personal responsibility of leaders. This article offers a reflection on the level of responsibility of governments in liberal democracies in managing the pandemic. During the crisis, decision-makers tended to be driven by the narratives that were most beneficial to them in order to escape their responsibilities, thereby underpinning their short-term political needs through the use of bellicose metaphors, the blame game, competition with other countries, and the dispersion of sources in the decision-making process. This reality now calls for reflection by social actors, including experts, intellectuals and the media, to transcend the prevailing rhetoric in management of the pandemic and the “new normal” that followed, so that the dynamics of constant alterations in the rules of the game and responsibilities can give way, in the future, to a scenario with less arbitrariness and more accountability.
-
De la gestión de crisis a la crisis de gestión: Responsabilidad y democracias liberales en el estallido de la pandemia de la COVID-19
El estallido de la pandemia de la COVID-19 conmocionó a las sociedades de todo el mundo. En su esfuerzo por adaptar sus respuestas a la crisis a sus propias condiciones de supervivencia, los gobiernos tendieron desde el principio a recurrir a argumentos que limitaban la rendición de cuentas frente a la población. Las democracias liberales no fueron ajenas a esta forma de abordar el problema. En ese contexto, sus dirigentes esgrimieron la metáfora de la guerra para describir su posición como garantes de la supervivencia de la población frente a la nueva amenaza. Atenazados entre la incertidumbre y la necesidad de predecir la naturaleza y la evolución del enemigo invisible, sus respuestas pusieron en entredicho la responsabilidad política, profesional y personal de los dirigentes. En este artículo se ofrece una reflexión sobre el nivel de responsabilidad de los gobiernos de las democracias liberales en la gestión de la pandemia. Durante la crisis, los decisores tendieron a dejarse llevar por las narrativas que les resultaban más beneficiosas para escabullirse de sus responsabilidades, apuntalando así sus necesidades políticas a corto plazo a través del uso de metáforas belicistas, el juego de culpas, la competición con otros países y la dispersión de las fuentes en el proceso de toma de decisiones. Esta realidad supone hoy un llamado a la reflexión a los actores sociales, incluidos los expertos, intelectuales y medios de comunicación, para trascender la retórica predominante en la gestión de la pandemia y la “nueva normalidad” que le siguió, de manera que la dinámica de alteraciones constantes de las reglas del juego y las responsabilidades pueda dar paso, en el futuro, a un escenario con menos arbitrariedad y más rendición de cuentas.
-
Parameter efficient fine tuning: A comprehensive analysis across applications
The rise of deep learning has marked significant progress in fields such as computer vision, natural language processing, and medical imaging, primarily through the adaptation of pre-trained models for specific tasks. Traditional fine-tuning methods, involving adjustments to all parameters, face challenges due to high computational and memory demands. This has led to the development of Parameter Efficient Fine-Tuning (PEFT) techniques, which selectively update parameters to balance computational efficiency with performance. This review examines PEFT approaches, offering a detailed comparison of various strategies highlighting applications across different domains, including text generation, medical imaging, protein modeling, and speech synthesis. By assessing the effectiveness of PEFT methods in reducing computational load, speeding up training, and lowering memory usage, this paper contributes to making deep learning more accessible and adaptable, facilitating its wider application and encouraging innovation in model optimization. Ultimately, the paper aims to contribute towards insights into PEFT’s evolving landscape, guiding researchers and practitioners in overcoming the limitations of conventional fine-tuning approaches.
-
BrainStat: A toolbox for brain-wide statistics and multimodal feature associations
Analysis and interpretation of neuroimaging datasets has become a multidisciplinary endeavor, relying not only on statistical methods, but increasingly on associations with respect to other brain-derived features such as gene expression, histological data, and functional as well as cognitive architectures. Here, we introduce BrainStat – a toolbox for (i) univariate and multivariate linear models in volumetric and surface-based brain imaging datasets, and (ii) multidomain feature association of results with respect to spatial maps of post-mortem gene expression and histology, task-based fMRI meta-analysis, as well as resting-state fMRI motifs across several common surface templates. The combination of statistics and feature associations into a turnkey toolbox streamlines analytical processes and accelerates cross-modal research. The toolbox is implemented in both Python and MATLAB, two widely used programming languages in the neuroimaging and neuroinformatics communities. BrainStat is openly available and complemented by an expandable documentation.
-
fMRIflows: A Consortium of Fully Automatic Univariate and Multivariate fMRI Processing Pipelines
One of the most significant current discussions in the understanding of the human brain is the functional recruitment of some regions of the cortex for specific tasks, regardless of the sensory modality (e.g. visual, tactile or auditory) in which the stimuli is received. The ability to perceive motion, among other visual properties, is a fundamental faculty of the human brain. Brain lesions that impair the detection and processing of motion have a profound impact on daily activity. Consequently, visual motion processing is one of the most fundamental and well-studied systems in the human brain, canonically known to develop mainly for the purpose of visual perception. A great deal of study on the multisensory responses to motion processing in the human brain focused on the middle temporal complex and superior temporal sulcus. Several studies using both neurophysiological and neuroimaging techniques showed the multisensory properties of these areas, showing their recruitment during both tactile and auditory motion stimulation. Despite the large amount of study on the topic it is still unclear whether the recruitment of these areas directly mediates the perception of motion through the different sensory input or regulates responses within primary sensory areas involved in the task. This MSCA fellowship allowed me to lay the foundations on the neural substrate underlying multisensory motion perception. We discovered that hMT+, an area mainly involved in visual motion processing, encode motion via spatial features of the stimulation rather than its intrinsic speed and our preliminary results show that, together with other visual areas, is able to decode speed via auditory and tactile motion stimulation, proving its multisensory function.
-
The missing voices at AI conferences
Policymaking should be a society-wide effort, including elected officials, government employees, academics, business leaders, civil society groups and individuals. In theory, each of us should be able to participate.
-
Unveiling AI Concerns for Sub-Saharan Africa and its Vulnerable Groups
In Sub-Saharan Africa (SSA), artificial intelligence is still in its early stages of adoption. To ensure that the already existing class imbalance in SSA communities does not hinder the realization of the Sustainable Development Goals, such as data security, safety, and equitable access to AI technologies, acceptable reliability measures must be put in place (as policies). This paper identifies some of the vulnerabilities in AI and adds a voice to the risks and ethical concerns surrounding the use of AI and its impact on SSA and its vulnerable groups. Our systematic literature review of related research between January 2014 and June 2024 shows the current state of AI adoption in SSA and the socio-political challenges that impact its development, revealing key concerns in data Governance, safety privacy, educational and skill gaps, socioeconomic impacts, and stakeholder influence on AI adoption in SSA. We propose a framework for designing data governance policies for the inclusive use of AI in SSA.
-
Health chatbots in Africa: scoping review
Background
This scoping review explores and summarizes the existing literature on the use of chatbots to support and promote health in Africa.Objective
The primary aim was to learn where, and under what circumstances, chatbots have been used effectively for health in Africa; how chatbots have been developed to the best effect; and how they have been evaluated by looking at literature published between 2017 and 2022. A secondary aim was to identify potential lessons and best practices for others chatbots. The review also aimed to highlight directions for future research on the use of chatbots for health in Africa.Methods
Using the 2005 Arksey and O’Malley framework, we used a Boolean search to broadly search literature published between January 2017 and July 2022. Literature between June 2021 and July 2022 was identified using Google Scholar, EBSCO information services—which includes the African HealthLine, PubMed, MEDLINE, PsycInfo, Cochrane, Embase, Scopus, and Web of Science databases—and other internet sources (including gray literature). The inclusion criteria were literature about health chatbots in Africa published in journals, conference papers, opinion, or white papers.Results
In all, 212 records were screened, and 12 articles met the inclusion criteria. Results were analyzed according to the themes they covered. The themes identified included the purpose of the chatbot as either providing an educational or information-sharing service or providing a counselling service. Accessibility as a result of either technical restrictions or language … -
Global environmental health impacts of rare earth metals: Insights for research and policy making in Africa
The rise of globalization and industrialization has driven the demand for rare earth metals (REMs). These metals are widely used in various sectors of the global economy with various applications in medicine, renewable energy, electronics, agriculture, and the military. REMs are likely to remain an important part of our global future, and, as production increases, areas contaminated by REMs are expected to expand over the coming decades. Thus, triggering significant adverse environmental, animal, and human health impacts. Despite increased attention on REMs outside China in recent years, there are limited studies exploring REM production, deposits, and associated health impacts in the African context. Proper mine management, adequate safety protocols, sustainable processing methods, and waste handling systems have been identified and proposed globally; however, the nature and scale of implementing these management protocols on the African continent have been less clear. Therefore, planetary health-centered solutions are urgently needed to be undertaken by researchers, policy makers, and non-governmental actors in Africa and across the globe. This is with the overarching aim of ensuring eco-friendly alternatives and public health consciousness on REM exploitations and hazards for future generations to come.