Peer Herholz

Facial expressions are central to human social interaction, yet reliably quantifying how faces move over time remains challenging. Here, we address these limitations in three ways. First, we leverage photorealistic MetaHuman animations with precisely specified facial motion to systematically evaluate two widely used AU detection systems: AFAR and OpenFace. Four avatars were animated with identical motion parameters to generate 72 videos comprising single-AU and AU-combination sequences. Although both systems performed above chance, their performance varied substantially across AUs and avatars. Second, we introduce and validate a complementary landmark-displacement approach that directly quantifies nonrigid facial motion from tracked geometry, yielding consistent and robust motion estimates across avatars and animations. Third, we provide FACET, an open-source toolbox that integrates AU detection and landmark-based motion analysis within a unified and reproducible framework. Together, our findings reveal systematic biases in current AU-detection systems, highlight the potential of landmark-based analysis to characterize facial motion directly, and provide an open, reproducible framework for quantifying facial motion and evaluating the methods used to capture it.

Topographic organization, whereby neighboring cortical locations encode neighboring features in sensory or cognitive space, is a fundamental principle of brain function. Existing approaches for obtaining individual-specific topographic maps either require resource-intensive functional neuroimaging or, when relying on population atlases, lack precision for individual-level inference. Here, we introduce deepRetinotopy toolbox, a deep learning-based application for predicting the functional topographic organization of human visual cortex from cortical anatomy alone. DeepRetinotopy toolbox produces accurate retinotopic maps across diverse experimental conditions, imaging sites, and scanner types. We demonstrate how predicted maps can be utilized to automatically generate individual-specific visual area boundaries, overcoming common biases in manual annotations. Finally, we applied our method to 11,060 anatomical scans, which allowed us to quantify age-related changes in the functional organization of visual cortex predictable from anatomy alone, underscoring the method’s broad utility for scalable, anatomy-based functional brain mapping.

Topographic organization, whereby neighboring cortical locations encode neighboring features in sensory or cognitive space, is a fundamental principle of brain function. Existing approaches for obtaining individual-specific topographic maps either require resource-intensive functional neuroimaging or, when relying on population atlases, lack precision for individual-level inference. Here, we introduce deepRetinotopy toolbox , a deep learning-based application for predicting the functional topographic organization of human visual cortex from cortical anatomy alone. DeepRetinotopy toolbox produces accurate retinotopic maps across diverse experimental conditions, imaging sites, and scanner types. We demonstrate how predicted maps can be utilized to automatically generate individual-specific visual area boundaries, overcoming common biases in manual annotations. Finally, we applied our method to 11,060 anatomical scans, which allowed us to quantify age-related changes in the functional organization of visual cortex predictable from anatomy alone, underscoring the method’s broad utility for scalable, anatomy-based functional brain mapping.

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.

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. New developing area of NeuroAI at the intersection of neuroscience and artificial intelligence has many open challenges, one of which is training the new generation of experts. In this Comment, the authors provide resources and outline training needs and recommendations for junior researchers working across artificial intelligence and neuroscience.

OHBM Brainhack 2022 took place in June 2022. The first hybrid OHBM hackathon, it had an in-person component taking place in Glasgow and three hubs around the globe to improve inclusivity and fit as many timezones as possible. In the buzzing setting of the Queen Margaret Union and of the virtual platform, 23 projects were presented after development. Following are the reports of 14 of those, as well as a recapitulation of the organisation of the event.

Real-world generalization, e.g., deciding to approach a never-seen-before animal, relies on contextual information as well as previous experiences. Such a seemingly easy behavioral choice requires the interplay of multiple neural mechanisms, from integrative encoding to category-based inference, weighted differently according to the circumstances. Here, we argue that a comprehensive theory of the neuro-cognitive substrates of real-world generalization will greatly benefit from empirical research with three key elements. First, the ecological validity provided by multimodal, naturalistic paradigms. Second, the model stability afforded by deep sampling. Finally, the statistical rigor granted by predictive modeling and computational controls.

Multimodal neuroimaging grants a powerful window into the structure and function of the human brain at multiple scales. Recent methodological and conceptual advances have enabled investigations of the interplay between large-scale spatial trends (also referred to as gradients) in brain microstructure and connectivity, offering an integrative framework to study multiscale brain organization. Here, we share a multimodal MRI dataset for Microstructure-Informed Connectomics (MICA-MICs) acquired in 50 healthy adults (23 women; 29.54 ± 5.62 years) who underwent high-resolution T1-weighted MRI, myelin-sensitive quantitative T1 relaxometry, diffusion-weighted MRI, and resting-state functional MRI at 3 Tesla. In addition to raw anonymized MRI data, this release includes brain-wide connectomes derived from (i) resting-state functional imaging, (ii) diffusion tractography, (iii) microstructure covariance analysis, and (iv) geodesic cortical distance, gathered across multiple parcellation scales. Alongside, we share large-scale gradients estimated from each modality and parcellation scale. Our dataset will facilitate future research examining the coupling between brain microstructure, connectivity, and function. MICA-MICs is available on the Canadian Open Neuroscience Platform data portal (https://portal.conp.ca) and the Open Science Framework (https://osf.io/j532r/).

Functional magnetic resonance imaging (fMRI) has revolutionized cognitive neuroscience, but methodological barriers limit the generalizability of findings from the lab to the real world. Here, we present Neuroscout, an end-to-end platform for analysis of naturalistic fMRI data designed to facilitate the adoption of robust and generalizable research practices. Neuroscout leverages state-of-the-art machine learning models to automatically annotate stimuli from dozens of fMRI studies using naturalistic stimuli—such as movies and narratives—allowing researchers to easily test neuroscientific hypotheses across multiple ecologically-valid datasets. In addition, Neuroscout builds on a robust ecosystem of open tools and standards to provide an easy-to-use analysis builder and a fully automated execution engine that reduce the burden of reproducible research. Through a series of meta-analytic case studies, we validate the automatic feature extraction approach and demonstrate its potential to support more robust fMRI research. Owing to its ease of use and a high degree of automation, Neuroscout makes it possible to overcome modeling challenges commonly arising in naturalistic analysis and to easily scale analyses within and across datasets, democratizing generalizable fMRI research.

Empirical observations of how labs conduct research indicate that the adoption rate of open practices for transparent, reproducible, and collaborative science remains in its infancy. This is at odds with the overwhelming evidence for the necessity of these practices and their benefits for individual researchers, scientific progress, and society in general. To date, information required for implementing open science practices throughout the different steps of a research project is scattered among many different sources. Even experienced researchers in the topic find it hard to navigate the ecosystem of tools and to make sustainable choices. Here, we provide an integrated overview of community-developed resources that can support collaborative, open, and reproducible neuroimaging throughout the entire research cycle from inception to publication and across different neuroimaging modalities. We review tools and practices supporting study inception and planning, data acquisition, research data management, data processing and analysis, and research dissemination. We believe it will prove helpful for researchers and institutions to make a successful and sustainable move towards open and reproducible science and to eventually take an active role in its future development.