Individual Brain Charting dataset extension, third release for movie watching and retinotopy data.

The Individual Brain Charting (IBC) is a multi-task functional Magnetic Resonance Imaging dataset acquired at high spatial-resolution and dedicated to the cognitive mapping of the human brain. It consists in the deep phenotyping of twelve individuals, covering a broad range of psychological domains suitable for functional-atlasing applications. Here, we present the inclusion of task data from both naturalistic stimuli and trial-based designs, to uncover structures of brain activation. We rely on the Fast Shared Response Model (FastSRM) to provide a data-driven solution for modelling naturalistic stimuli, typically containing many features. We show that data from left-out runs can be reconstructed using FastSRM, enabling the extraction of networks from the visual, auditory and language systems. We also present the topographic organization of the visual system through retinotopy. In total, six new tasks were added to IBC, wherein four trial-based retinotopic tasks contributed with a mapping of the visual field to the cortex. IBC is open access: source plus derivatives imaging data and meta-data are available in public repositories.

Non-Cartesian 3D-SPARKLING vs Cartesian 3D-EPI encoding schemes for functional Magnetic Resonance Imaging at 7 Tesla.

The quest for higher spatial and/or temporal resolution in functional MRI (fMRI) while preserving a sufficient temporal signal-to-noise ratio (tSNR) has generated a tremendous amount of methodological contributions in the last decade ranging from Cartesian vs. non-Cartesian readouts, 2D vs. 3D acquisition strategies, parallel imaging and/or compressed sensing (CS) accelerations and simultaneous multi-slice acquisitions to cite a few. In this paper, we investigate the use of a finely tuned version of 3D-SPARKLING. This is a non-Cartesian CS-based acquisition technique for high spatial resolution whole-brain fMRI. We compare it to state-of-the-art Cartesian 3D-EPI during both a retinotopic mapping paradigm and resting-state acquisitions at 1mm3 (isotropic spatial resolution). This study involves six healthy volunteers and both acquisition sequences were run on each individual in a randomly-balanced order across subjects. The performances of both acquisition techniques are compared to each other in regards to tSNR, sensitivity to the BOLD effect and spatial specificity. Our findings reveal that 3D-SPARKLING has a higher tSNR than 3D-EPI, an improved sensitivity to detect the BOLD contrast in the gray matter, and an improved spatial specificity. Compared to 3D-EPI, 3D-SPARKLING yields, on average, 7% more activated voxels in the gray matter relative to the total number of activated voxels.

Continuous evaluation of denoising strategies in resting-state fMRI connectivity using fMRIPrep and Nilearn.

Reducing contributions from non-neuronal sources is a crucial step in functional magnetic resonance imaging (fMRI) connectivity analyses. Many viable strategies for denoising fMRI are used in the literature, and practitioners rely on denoising benchmarks for guidance in the selection of an appropriate choice for their study. However, fMRI denoising software is an ever-evolving field, and the benchmarks can quickly become obsolete as the techniques or implementations change. In this work, we present a denoising benchmark featuring a range of denoising strategies, datasets and evaluation metrics for connectivity analyses, based on the popular fMRIprep software. The benchmark prototypes an implementation of a reproducible framework, where the provided Jupyter Book enables readers to reproduce or modify the figures on the Neurolibre reproducible preprint server (https://neurolibre.org/). We demonstrate how such a reproducible benchmark can be used for continuous evaluation of research software, by comparing two versions of the fMRIprep. Most of the benchmark results were consistent with prior literature. Scrubbing, a technique which excludes time points with excessive motion, combined with global signal regression, is generally effective at noise removal. Scrubbing was generally effective, but is incompatible with statistical analyses requiring the continuous sampling of brain signal, for which a simpler strategy, using motion parameters, average activity in select brain compartments, and global signal regression, is preferred. Importantly, we found that certain denoising strategies behave inconsistently across datasets and/or versions of fMRIPrep, or had a different behavior than in previously published benchmarks. This work will hopefully provide useful guidelines for the fMRIprep users community, and highlight the importance of continuous evaluation of research methods.

Verbal fluency predicts work resumption after awake surgery in low-grade glioma patients.

BACKGROUND: Resuming professional activity after awake surgery for diffuse low-grade glioma (DLGG) is an important goal, which is not reached in every patient. Cognitive deficits can occur and persist after surgery. In this study, we analyzed the impact of mild cognitive impairments on the work resumption. METHODS: Fifty-four surgeries (including five redo surgeries) performed between 2012 and 2020 for grade 2 (45) and 3 (nine) DLGG in 49 professionally active patients (mean age 40 [range 23-58.) were included. We retrospectively extracted the results of semantic and phonemic verbal fluency tests from preoperative and 4-month postoperative cognitive assessments. Patients were interviewed about their working life after surgery, between April and June 2021. RESULTS: Patients (85%) returned to work, most within 3 to 6 months. Patients (76%) reported subjective complaints (primarily fatigue). Self-reported symptoms and individual and clinical variables had no impact on the work resumption. Late-postoperative average Z-scores in verbal fluency tasks were significantly lower than preoperative for the entire cohort (Wilcoxon test, p < 0.001 for semantic and p = 0.008 for phonemic fluency). The decrease in Z-scores was significantly greater (Mann Whitney U-test, semantic, p = 0.018; phonemic, p = 0.004) in the group of patients who did not return to work than in the group of patients who did. CONCLUSION: The proportion of patients returning to work was comparable to similar studies. A decrease in verbal fluency tasks could predict the inability to return to work.

Should one go for individual- or group-level brain parcellations? A deep-phenotyping benchmark.

The analysis and understanding of brain characteristics often require considering region-level information rather than voxel-sampled data. Subject-specific parcellations have been put forward in recent years, as they can adapt to individual brain organization and thus offer more accurate individual summaries than standard atlases. However, the price to pay for adaptability is the lack of group-level consistency of the data representation. Here, we investigate whether the good representations brought by individualized models are merely an effect of circular analysis, in which individual brain features are better represented by subject-specific summaries, or whether this carries over to new individuals, i.e., whether one can actually adapt an existing parcellation to new individuals and still obtain good summaries in these individuals. For this, we adapt a dictionary-learning method to produce brain parcellations. We use it on a deep-phenotyping dataset to assess quantitatively the patterns of activity obtained under naturalistic and controlled-task-based settings. We show that the benefits of individual parcellations are substantial, but that they vary a lot across brain systems.

Impact of B 0 $$ {\mathrm{B}}_0 $$ field imperfections correction on BOLD sensitivity in 3D-SPARKLING fMRI data.

PURPOSE: Static and dynamic B 0 $$ {\mathrm{B}}_0 $$ field imperfections are detrimental to functional MRI (fMRI) applications, especially at ultra-high magnetic fields (UHF). In this work, a field camera is used to assess the benefits of retrospectively correcting B 0 $$ {\mathrm{B}}_0 $$ field perturbations on Blood Oxygen Level Dependent (BOLD) sensitivity in non-Cartesian three-dimensional (3D)-SPARKLING fMRI acquisitions. METHODS: fMRI data were acquired at 1 mm 3 $$ {}^3 $$ and for a 2.4s-TR while concurrently monitoring in real-time field perturbations using a Skope Clip-on field camera in a novel experimental setting involving a shorter TR than the required minimal TR of the field probes. Measurements of the dynamic field deviations were used along with a static Δ B 0 $$ \Delta {\mathrm{B}}_0 $$ map to retrospectively correct static and dynamic field imperfections, respectively. In order to evaluate the impact of such a correction on fMRI volumes, a comparative study was conducted on healthy volunteers. RESULTS: Correction of B 0 $$ {\mathrm{B}}_0 $$ deviations improved image quality and yielded between 20% and 30% increase in median temporal signal-to-noise ratio (tSNR).Using fMRI data collected during a retinotopic mapping experiment, we demonstrated a significant increase in sensitivity to the BOLD contrast and improved accuracy of the BOLD phase maps: 44% (resp., 159%) more activated voxels were retrieved when using a significance control level based on a p-value of 0.001 without correcting for multiple comparisons (resp., 0.05 with a false discovery rate correction). CONCLUSION: 3D-SPARKLING fMRI hugely benefits from static and dynamic B 0 $$ {\mathrm{B}}_0 $$ imperfections correction. However, the proposed experimental protocol is flexible enough to be deployed on a large spectrum of encoding schemes, including arbitrary non-Cartesian readouts.

Information-Restricted Neural Language Models Reveal Different Brain Regions' Sensitivity to Semantics, Syntax, and Context.

A fundamental question in neurolinguistics concerns the brain regions involved in syntactic and semantic processing during speech comprehension, both at the lexical (word processing) and supra-lexical levels (sentence and discourse processing). To what extent are these regions separated or intertwined? To address this question, we introduce a novel approach exploiting neural language models to generate high-dimensional feature sets that separately encode semantic and syntactic information. More precisely, we train a lexical language model, GloVe, and a supra-lexical language model, GPT-2, on a text corpus from which we selectively removed either syntactic or semantic information. We then assess to what extent the features derived from these information-restricted models are still able to predict the fMRI time courses of humans listening to naturalistic text. Furthermore, to determine the windows of integration of brain regions involved in supra-lexical processing, we manipulate the size of contextual information provided to GPT-2. The analyses show that, while most brain regions involved in language comprehension are sensitive to both syntactic and semantic features, the relative magnitudes of these effects vary across these regions. Moreover, regions that are best fitted by semantic or syntactic features are more spatially dissociated in the left hemisphere than in the right one, and the right hemisphere shows sensitivity to longer contexts than the left. The novelty of our approach lies in the ability to control for the information encoded in the models' embeddings by manipulating the training set. These "information-restricted" models complement previous studies that used language models to probe the neural bases of language, and shed new light on its spatial organization.

Open design of a reproducible videogame controller for MRI and MEG.

Videogames are emerging as a promising experimental paradigm in neuroimaging. Acquiring gameplay in a scanner remains challenging due to the lack of a scanner-compatible videogame controller that provides a similar experience to standard, commercial devices. In this paper, we introduce a videogame controller designed for use in the functional magnetic resonance imaging as well as magnetoencephalography. The controller is made exclusively of 3D-printed and commercially available parts. We evaluated the quality of our controller by comparing it to a non-MRI compatible controller that was kept outside the scanner. The comparison of response latencies showed reliable button press accuracies of adequate precision. Comparison of the subjects' motion during fMRI recordings of various tasks showed that the use of our controller did not increase the amount of motion produced compared to a regular MR compatible button press box. Motion levels during an ecological videogame task were of moderate amplitude. In addition, we found that the controller only had marginal effect on temporal SNR in fMRI, as well as on covariance between sensors in MEG, as expected due to the use of non-magnetic building materials. Finally, the reproducibility of the controller was demonstrated by having team members who were not involved in the design build a reproduction using only the documentation. This new videogame controller opens new avenues for ecological tasks in fMRI, including challenging videogames and more generally tasks with complex responses. The detailed controller documentation and build instructions are released under an Open Source Hardware license to increase accessibility, and reproducibility and enable the neuroimaging research community to improve or modify the controller for future experiments.

Continuous Evaluation of Denoising Strategies in Resting-State fMRI Connectivity Using fMRIPrep and Nilearn.

Reducing contributions from non-neuronal sources is a crucial step in functional magnetic resonance imaging (fMRI) connectivity analyses. Many viable strategies for denoising fMRI are used in the literature, and practitioners rely on denoising benchmarks for guidance in the selection of an appropriate choice for their study. However, fMRI denoising software is an ever-evolving field, and the benchmarks can quickly become obsolete as the techniques or implementations change. In this work, we present a denoising benchmark featuring a range of denoising strategies, datasets and evaluation metrics for connectivity analyses, based on the popular fMRIprep software. The benchmark is implemented in a fully reproducible framework, where the provided research objects enable readers to reproduce or modify core computations, as well as the figures of the article using the Jupyter Book project and the Neurolibre reproducible preprint server (https://neurolibre.org/). We demonstrate how such a reproducible benchmark can be used for continuous evaluation of research software, by comparing two versions of the fMRIprep software package. The majority of benchmark results were consistent with prior literature. Scrubbing, a technique which excludes time points with excessive motion, combined with global signal regression, is generally effective at noise removal. Scrubbing however disrupts the continuous sampling of brain images and is incompatible with some statistical analyses, e.g. auto-regressive modeling. In this case, a simple strategy using motion parameters, average activity in select brain compartments, and global signal regression should be preferred. Importantly, we found that certain denoising strategies behave inconsistently across datasets and/or versions of fMRIPrep, or had a different behavior than in previously published benchmarks. This work will hopefully provide useful guidelines for the fMRIprep users community, and highlight the importance of continuous evaluation of research methods. Our reproducible benchmark infrastructure will facilitate such continuous evaluation in the future, and may also be applied broadly to different tools or even research fields.

Empirical facts from search for replicable associations between cortical thickness and psychometric variables in healthy adults.

The study of associations between inter-individual differences in brain structure and behaviour has a long history in psychology and neuroscience. Many associations between psychometric data, particularly intelligence and personality measures and local variations of brain structure have been reported. While the impact of such reported associations often goes beyond scientific communities, resonating in the public mind, their replicability is rarely evidenced. Previously, we have shown that associations between psychometric measures and estimates of grey matter volume (GMV) result in rarely replicated findings across large samples of healthy adults. However, the question remains if these observations are at least partly linked to the multidetermined nature of the variations in GMV, particularly within samples with wide age-range. Therefore, here we extended those evaluations and empirically investigated the replicability of associations of a broad range of psychometric variables and cortical thickness in a large cohort of healthy young adults. In line with our observations with GMV, our current analyses revealed low likelihood of significant associations and their rare replication across independent samples. We here discuss the implications of these findings within the context of accumulating evidence of the general poor replicability of structural-brain-behaviour associations, and more broadly of the replication crisis.

Notip: Non-parametric true discovery proportion control for brain imaging.

Cluster-level inference procedures are widely used for brain mapping. These methods compare the size of clusters obtained by thresholding brain maps to an upper bound under the global null hypothesis, computed using Random Field Theory or permutations. However, the guarantees obtained by this type of inference - i.e. at least one voxel is truly activated in the cluster - are not informative with regards to the strength of the signal therein. There is thus a need for methods to assess the amount of signal within clusters; yet such methods have to take into account that clusters are defined based on the data, which creates circularity in the inference scheme. This has motivated the use of post hoc estimates that allow statistically valid estimation of the proportion of activated voxels in clusters. In the context of fMRI data, the All-Resolutions Inference framework introduced in Rosenblatt et al. (2018) provides post hoc estimates of the proportion of activated voxels. However, this method relies on parametric threshold families, which results in conservative inference. In this paper, we leverage randomization methods to adapt to data characteristics and obtain tighter false discovery control. We obtain Notip, for Non-parametric True Discovery Proportion control: a powerful, non-parametric method that yields statistically valid guarantees on the proportion of activated voxels in data-derived clusters. Numerical experiments demonstrate substantial gains in number of detections compared with state-of-the-art methods on 36 fMRI datasets. The conditions under which the proposed method brings benefits are also discussed.

Comprehensive decoding mental processes from Web repositories of functional brain images.

Associating brain systems with mental processes requires statistical analysis of brain activity across many cognitive processes. These analyses typically face a difficult compromise between scope-from domain-specific to system-level analysis-and accuracy. Using all the functional Magnetic Resonance Imaging (fMRI) statistical maps of the largest data repository available, we trained machine-learning models that decode the cognitive concepts probed in unseen studies. For this, we leveraged two comprehensive resources: NeuroVault-an open repository of fMRI statistical maps with unconstrained annotations-and Cognitive Atlas-an ontology of cognition. We labeled NeuroVault images with Cognitive Atlas concepts occurring in their associated metadata. We trained neural networks to predict these cognitive labels on tens of thousands of brain images. Overcoming the heterogeneity, imbalance and noise in the training data, we successfully decoded more than 50 classes of mental processes on a large test set. This success demonstrates that image-based meta-analyses can be undertaken at scale and with minimal manual data curation. It enables broad reverse inferences, that is, concluding on mental processes given the observed brain activity.

How to remove or control confounds in predictive models, with applications to brain biomarkers.

BACKGROUND: With increasing data sizes and more easily available computational methods, neurosciences rely more and more on predictive modeling with machine learning, e.g., to extract disease biomarkers. Yet, a successful prediction may capture a confounding effect correlated with the outcome instead of brain features specific to the outcome of interest. For instance, because patients tend to move more in the scanner than controls, imaging biomarkers of a disease condition may mostly reflect head motion, leading to inefficient use of resources and wrong interpretation of the biomarkers. RESULTS: Here we study how to adapt statistical methods that control for confounds to predictive modeling settings. We review how to train predictors that are not driven by such spurious effects. We also show how to measure the unbiased predictive accuracy of these biomarkers, based on a confounded dataset. For this purpose, cross-validation must be modified to account for the nuisance effect. To guide understanding and practical recommendations, we apply various strategies to assess predictive models in the presence of confounds on simulated data and population brain imaging settings. Theoretical and empirical studies show that deconfounding should not be applied to the train and test data jointly: modeling the effect of confounds, on the training data only, should instead be decoupled from removing confounds. CONCLUSIONS: Cross-validation that isolates nuisance effects gives an additional piece of information: confound-free prediction accuracy.

Network-level prediction of set-shifting deterioration after lower-grade glioma resection.

OBJECTIVE: The aim of this study was to predict set-shifting deterioration after resection of low-grade glioma. METHODS: The authors retrospectively analyzed a bicentric series of 102 patients who underwent surgery for low-grade glioma. The difference between the completion times of the Trail Making Test parts B and A (TMT B-A) was evaluated preoperatively and 3-4 months after surgery. High dimensionality of the information related to the surgical cavity topography was reduced to a small set of predictors in four different ways: 1) overlap between surgical cavity and each of the 122 cortical parcels composing Yeo's 17-network parcellation of the brain; 2) Tractotron: disconnection by the cavity of the major white matter bundles; 3) overlap between the surgical cavity and each of Yeo's networks; and 4) disconets: signature of structural disconnection by the cavity of each of Yeo's networks. A random forest algorithm was implemented to predict the postoperative change in the TMT B-A z-score. RESULTS: The last two network-based approaches yielded significant accuracies in left-out subjects (area under the receiver operating characteristic curve [AUC] approximately equal to 0.8, p approximately equal to 0.001) and outperformed the two alternatives. In single tree hierarchical models, the degree of damage to Yeo corticocortical network 12 (CC 12) was a critical node: patients with damage to CC 12 higher than 7.5% (cortical overlap) or 7.2% (disconets) had much higher risk to deteriorate, establishing for the first time a causal link between damage to this network and impaired set-shifting. CONCLUSIONS: The authors' results give strong support to the idea that network-level approaches are a powerful way to address the lesion-symptom mapping problem, enabling machine learning-powered individual outcome predictions.

The effects of repeated brain MRI on chromosomal damage.

BACKGROUND: Magnetic resonance imaging (MRI) is currently considered a safe imaging technique because, unlike computed tomography, MRI does not expose patients to ionising radiation. However, conflicting literature reports possible genotoxic effects of MRI. We herein examine the chromosomal effects of repeated MRI scans by performing a longitudinal follow-up of chromosomal integrity in volunteers. METHODS: This ethically approved study was performed on 13 healthy volunteers (mean age 33 years) exposed to up to 26 3-T MRI sessions. The characterisation of chromosome damage in peripheral blood lymphocytes was performed using the gold-standard biodosimetry technique augmented with telomere and centromere staining. RESULTS: Cytogenetic analysis showed no detectable effect after a single MRI scan. However, repeated MRI sessions (from 10 to 20 scans) were associated with a small but significant increase in chromosomal breaks with the accumulation of cells with chromosomal terminal deletions with a coefficient of 9.5% (95% confidence interval 6.5-12.5%) per MRI (p < 0.001). Additional exposure did not result in any further increase. This plateauing of damage suggests lymphocyte turnover. Additionally, there was no significant induction of dicentric chromosomes, in contrast to what is observed following exposure to ionising radiation. CONCLUSIONS: Our study showed that MRI can affect chromosomal integrity. However, the amount of damage per cell might be so low that no chromosomal rearrangement by fusion of two deoxyribonucleic breaks is induced, unlike that seen after exposure to computed tomography. This study confirms that MRI is a safe imaging technique.

Synthetic FLAIR as a Substitute for FLAIR Sequence in Acute Ischemic Stroke.

Background In acute ischemic stroke (AIS), fluid-attenuated inversion recovery (FLAIR) is used for treatment decisions when onset time is unknown. Synthetic FLAIR could be generated with deep learning from information embedded in diffusion-weighted imaging (DWI) and could replace acquired FLAIR sequence (real FLAIR) and shorten MRI duration. Purpose To compare performance of synthetic and real FLAIR for DWI-FLAIR mismatch estimation and identification of patients presenting within 4.5 hours from symptom onset. Materials and Methods In this retrospective study, all pretreatment and early follow-up (<48 hours after symptom onset) MRI data sets including DWI (b = 0-1000 sec/mm2) and FLAIR sequences obtained in consecutive patients with AIS referred for reperfusion therapies between January 2002 and May 2019 were included. On the training set (80%), a generative adversarial network was trained to produce synthetic FLAIR with DWI as input. On the test set (20%), synthetic FLAIR was computed without real FLAIR knowledge. The DWI-FLAIR mismatch was evaluated on both FLAIR data sets by four independent readers. Interobserver reproducibility and DWI-FLAIR mismatch concordance between synthetic and real FLAIR were evaluated with κ statistics. Sensitivity and specificity for identification of AIS within 4.5 hours were compared in patients with known onset time by using McNemar test. Results The study included 1416 MRI scans (861 patients; median age, 71 years [interquartile range, 57-81 years]; 375 men), yielding 1134 and 282 scans for training and test sets, respectively. Regarding DWI-FLAIR mismatch, interobserver reproducibility was substantial for real and synthetic FLAIR (κ = 0.80 [95% CI: 0.74, 0.87] and 0.80 [95% CI: 0.74, 0.87], respectively). After consensus, concordance between real and synthetic FLAIR was almost perfect (κ = 0.88; 95% CI: 0.82, 0.93). Diagnostic value for identifying AIS within 4.5 hours did not differ between real and synthetic FLAIR (sensitivity: 107 of 131 [82%] vs 111 of 131 [85%], P = .2; specificity: 96 of 104 [92%] vs 96 of 104 [92%], respectively, P > .99). Conclusion Synthetic fluid-attenuated inversion recovery (FLAIR) had diagnostic performances similar to real FLAIR in depicting diffusion-weighted imaging-FLAIR mismatch and in helping to identify early acute ischemic stroke, and it may accelerate MRI protocols. © RSNA, 2022 Online supplemental material is available for this article. See also the editorial by Carroll and Hurley in this issue.

Tackling the Complexity of Lesion-Symptoms Mapping: How to Bridge the Gap Between Data Scientists and Clinicians?

Accurate and predictive lesion-symptoms mapping is a major goal in the field of clinical neurosciences. Recent studies have called for a reappraisal of the results given by the standard univariate voxel-based lesion-symptom mapping technique, emphasizing the need of developing multivariate methods. While the organization of large datasets and their analysis with machine learning (ML) approaches represents an opportunity to increase prediction accuracy, the complexity and dimensionality of the problem remain a major obstacle. Acknowledging the difficulty of inferring individual outcomes from the observation of spatial patterns of lesions, we propose here to base prediction on new individuals on models of brain connectivity, whereby the disruption of a given network predicts the occurrence of selective deficits. Well-suited ML tools are necessary to capture the relevant information from limited datasets and perform reliable inference.

Population modeling with machine learning can enhance measures of mental health.

BACKGROUND: Biological aging is revealed by physical measures, e.g., DNA probes or brain scans. In contrast, individual differences in mental function are explained by psychological constructs, e.g., intelligence or neuroticism. These constructs are typically assessed by tailored neuropsychological tests that build on expert judgement and require careful interpretation. Could machine learning on large samples from the general population be used to build proxy measures of these constructs that do not require human intervention? RESULTS: Here, we built proxy measures by applying machine learning on multimodal MR images and rich sociodemographic information from the largest biomedical cohort to date: the UK Biobank. Objective model comparisons revealed that all proxies captured the target constructs and were as useful, and sometimes more useful, than the original measures for characterizing real-world health behavior (sleep, exercise, tobacco, alcohol consumption). We observed this complementarity of proxy measures and original measures at capturing multiple health-related constructs when modeling from, both, brain signals and sociodemographic data. CONCLUSION: Population modeling with machine learning can derive measures of mental health from heterogeneous inputs including brain signals and questionnaire data. This may complement or even substitute for psychometric assessments in clinical populations.

An empirical evaluation of functional alignment using inter-subject decoding.

Inter-individual variability in the functional organization of the brain presents a major obstacle to identifying generalizable neural coding principles. Functional alignment-a class of methods that matches subjects' neural signals based on their functional similarity-is a promising strategy for addressing this variability. To date, however, a range of functional alignment methods have been proposed and their relative performance is still unclear. In this work, we benchmark five functional alignment methods for inter-subject decoding on four publicly available datasets. Specifically, we consider three existing methods: piecewise Procrustes, searchlight Procrustes, and piecewise Optimal Transport. We also introduce and benchmark two new extensions of functional alignment methods: piecewise Shared Response Modelling (SRM), and intra-subject alignment. We find that functional alignment generally improves inter-subject decoding accuracy though the best performing method depends on the research context. Specifically, SRM and Optimal Transport perform well at both the region-of-interest level of analysis as well as at the whole-brain scale when aggregated through a piecewise scheme. We also benchmark the computational efficiency of each of the surveyed methods, providing insight into their usability and scalability. Taking inter-subject decoding accuracy as a quantification of inter-subject similarity, our results support the use of functional alignment to improve inter-subject comparisons in the face of variable structure-function organization. We provide open implementations of all methods used.

Tissue outcome prediction in hyperacute ischemic stroke: Comparison of machine learning models.

Machine Learning (ML) has been proposed for tissue fate prediction after acute ischemic stroke (AIS), with the aim to help treatment decision and patient management. We compared three different ML models to the clinical method based on diffusion-perfusion thresholding for the voxel-based prediction of final infarct, using a large MRI dataset obtained in a cohort of AIS patients prior to recanalization treatment. Baseline MRI (MRI0), including diffusion-weighted sequence (DWI) and Tmax maps from perfusion-weighted sequence, and 24-hr follow-up MRI (MRI24h) were retrospectively collected in consecutive 394 patients AIS patients (median age = 70 years; final infarct volume = 28mL). Manually segmented DWI24h lesion was considered the final infarct. Gradient Boosting, Random Forests and U-Net were trained using DWI, apparent diffusion coefficient (ADC) and Tmax maps on MRI0 as inputs to predict final infarct. Tissue outcome predictions were compared to final infarct using Dice score. Gradient Boosting had significantly better predictive performance (median [IQR] Dice Score as for median age, maybe you can replace the comma with an equal sign for consistency 0.53 [0.29-0.68]) than U-Net (0.48 [0.18-0.68]), Random Forests (0.51 [0.27-0.66]), and clinical thresholding method (0.45 [0.25-0.62]) (P < 0.001). In this benchmark of ML models for tissue outcome prediction in AIS, Gradient Boosting outperformed other ML models and clinical thresholding method and is thus promising for future decision-making.