Biology subjects

Hordacre, B.

Publications and source records attributed to Hordacre, B..

8 recordsLinked to original sources

bioRxiv2026

CALM-VLM: CALIBRATION AND SELECTIVE PREDICTION IN VISION-LANGUAGE MODELS FOR RELIABLE BRAIN MRI CLASSIFICATION

AO_SCPLOWBSTRACTC_SCPLOWRecent advances in vision-language models (VLMs) have demonstrated strong multimodal capabilities for medical image analysis. However, their confidence in diagnostic predictions is often unclear, limiting adoption in clinical settings. We introduce CALM-VLM (CALibration Mechanism for Vision-Language Models), which integrates confidence calibration and selective prediction into a generative 3D VLM. To create CALM-VLM, we fine-tuned the Med3DVLM architecture for Alzheimers disease (AD) and stroke classification as initial test cases. To improve reliability, we incorporated temperature scaling on the VLMs generative outputs. The calibrated model then selectively abstained from predictions when uncertain; this also improved its diagnostic accuracy. Experiments across multi-site MRI datasets, from 10 countries worldwide, show that CALM-VLM improved confidence relative to uncalibrated VLMs. Coverage-adjusted test receiver-operator characteristic curve-area under the curve (ROC-AUC) increased by 5% to 13% for both diagnostic tasks across independent test sets. Our calibrated VLM achieved a test ROC-AUC of 0.951 for AD classification and 0.905 for stroke classification. These findings highlight the importance of calibrated, uncertainty-aware VLMs for trustworthy neuroimaging AI.

neuroscience↗

bioRxiv2023

Data-driven biomarkers outperform theory-based biomarkers in predicting stroke motor outcomes

Chronic motor impairments are a leading cause of disability after stroke. Previous studies have predicted motor outcomes based on the degree of damage to predefined structures in the motor system, such as the corticospinal tract. However, such theory-based approaches may not take full advantage of the information contained in clinical imaging data. The present study uses data-driven approaches to predict chronic motor outcomes after stroke and compares the accuracy of these predictions to previously-identified theory-based biomarkers. Using a cross-validation framework, regression models were trained using lesion masks and motor outcomes data from 789 stroke patients (293 female/496 male) from the ENIGMA Stroke Recovery Working Group (age 64.9{+/-}18.0 years; time since stroke 12.2{+/-}0.2 months; normalised motor score 0.7{+/-}0.5 (range [0,1]). The out-of-sample prediction accuracy of two theory-based biomarkers was assessed: lesion load of the corticospinal tract, and lesion load of multiple descending motor tracts. These theory-based prediction accuracies were compared to the prediction accuracy from three data-driven biomarkers: lesion load of lesion-behaviour maps, lesion load of structural networks associated with lesion-behaviour maps, and measures of regional structural disconnection. In general, data-driven biomarkers had better prediction accuracy - as measured by higher explained variance in chronic motor outcomes - than theory-based biomarkers. Data-driven models of regional structural disconnection performed the best of all models tested (R2 = 0.210, p < 0.001), performing significantly better than predictions using the theory-based biomarkers of lesion load of the corticospinal tract (R2 = 0.132, p< 0.001) and of multiple descending motor tracts (R2 = 0.180, p < 0.001). They also performed slightly, but significantly, better than other data-driven biomarkers including lesion load of lesion-behaviour maps (R2 =0.200, p < 0.001) and lesion load of structural networks associated with lesion-behaviour maps (R2 =0.167, p < 0.001). Ensemble models - combining basic demographic variables like age, sex, and time since stroke - improved prediction accuracy for theory-based and data-driven biomarkers. Finally, combining both theory-based and data-driven biomarkers with demographic variables improved predictions, and the best ensemble model achieved R2 = 0.241, p < 0.001. Overall, these results demonstrate that models that predict chronic motor outcomes using data-driven features, particularly when lesion data is represented in terms of structural disconnection, perform better than models that predict chronic motor outcomes using theory-based features from the motor system. However, combining both theory-based and data-driven models provides the best predictions.

neuroscience↗

bioRxiv2022

Global brain health modulates the impact of lesion damage on post-stroke sensorimotor outcomes

Sensorimotor performance after stroke is strongly related to focal injury measures such as corticospinal tract lesion load. However, the role of global brain health is less clear. Here, we examined the impact of brain age, a measure of neurobiological aging derived from whole brain structural neuroimaging, on sensorimotor outcomes. We hypothesized that stroke lesion damage would result in older brain age, which would in turn be associated with poorer sensorimotor outcomes. We also expected that brain age would mediate the impact of lesion damage on sensorimotor outcomes and that these relationships would be driven by post-stroke secondary atrophy (e.g., strongest in the ipsilesional hemisphere in chronic stroke). We further hypothesized that structural brain resilience, which we define in the context of stroke as the brains ability to maintain its global integrity despite focal lesion damage, would differentiate people with better versus worse outcomes. We analyzed cross-sectional high-resolution brain MRI and outcomes data from 963 people with stroke from 38 cohorts worldwide using robust linear mixed-effects regressions to examine the relationship between sensorimotor behavior, lesion damage, and brain age. We used a mediation analysis to examine whether brain age mediates the impact of lesion damage on stroke outcomes and if associations are driven by ipsilesional measures in chronic ([≥]180 days) stroke. We assessed the impact of brain resilience on sensorimotor outcome using logistic regression with propensity score matching on lesion damage. Stroke lesion damage was associated with older brain age, which in turn was associated with poorer sensorimotor outcomes. Brain age mediated the impact of corticospinal tract lesion load on sensorimotor outcomes most strongly in the ipsilesional hemisphere in chronic stroke. Greater brain resilience, as indexed by younger brain age, explained why people have better versus worse sensorimotor outcomes when lesion damage was fixed. We present novel evidence that global brain health is associated with superior post-stroke sensorimotor outcomes and modifies the impact of focal damage. This relationship appears to be due to post-stroke secondary degeneration. Brain resilience provides insight into why some people have better outcomes after stroke, despite similar amounts of focal injury. Inclusion of imaging-based assessments of global brain health may improve prediction of post-stroke sensorimotor outcomes compared to focal injury measures alone. This investigation is important because it introduces the potential to apply novel therapeutic interventions to prevent or slow brain aging from other fields (e.g., Alzheimers disease) to stroke.

neuroscience↗

bioRxiv2021

Chronic stroke sensorimotor impairment is related to smaller hippocampal volumes: An ENIGMA analysis

Persistent sensorimotor impairments after stroke can negatively impact quality of life. The hippocampus is involved in sensorimotor behavior but has not been widely studied within the context of post-stroke upper limb sensorimotor impairment. The hippocampus is vulnerable to secondary degeneration after stroke, and damage to this region could further weaken sensorimotor circuits, leading to greater chronic sensorimotor impairment. The purpose of this study was to investigate the cross-sectional association between non-lesioned hippocampal volume and upper limb sensorimotor impairment in people with chronic stroke. We hypothesized that smaller ipsilesional hippocampal volumes would be associated with worse upper-limb sensorimotor impairment. Cross-sectional T1-weighted brain MRIs were pooled from 357 participants at the chronic stage after stroke (>180 days post-stroke) compiled from 18 research cohorts worldwide in the ENIGMA Stroke Recovery Working Group (age: median = 61 years, interquartile range = 18, range = 23-93; 135 women and 222 men). Sensorimotor impairment was estimated from the Fugl-Meyer Assessment of Upper Extremity scores. Robust mixed-effects linear models were used to test associations between post-stroke sensorimotor impairment and hippocampal volumes (ipsilesional and contralesional separately; Bonferroni-corrected, p-value < 0.025), controlling for age, sex, lesion volume, and lesioned hemisphere. We also performed an exploratory analysis to test whether sex differences influence the relationship between sensorimotor impairment and hippocampal volume. Upper limb sensorimotor impairment was positively associated with ipsilesional (p = 0.005; d = 0.33) but not contralesional (p = 0.96; d = 0.01) hippocampal volume, such that impairment was worse for participants with smaller ipsilesional hippocampal volume. This association remained significant independent of lesion volume or other covariates (p = 0.001; d = 0.36). Evidence indicates an interaction between sensorimotor impairment and sex for both ipsilesional (p = 0.008; d = -0.29) and contralesional (p = 0.006; d = -0.30) hippocampal volumes, whereby women showed progressively worsening sensorimotor impairment with smaller hippocampal volumes compared to men. The present study has identified a novel association between chronic post-stroke sensorimotor impairment and ipsilesional, but not contralesional, hippocampal volume. This finding was not due to lesion size and may be stronger in women. We also provide supporting evidence that smaller hippocampal volume post-stroke is likely a consequence of ipsilesional damage, which could provide a link between vascular disease and other disorders, such as dementia.

neuroscience↗

bioRxiv2021

Age differences in aperiodic neural activity measured with resting EEG

Previous research using electroencephalography (EEG) and magnetoencephalography (MEG) has shown that neural oscillatory activity within the alpha band (8-12 Hz) becomes slower and lower in amplitude with advanced age. However, most studies have focused on quantifying age-related differences in periodic oscillatory activity with little consideration of the influence of aperiodic activity on these measures. The aim of this study was to investigate age differences in aperiodic activity inherent in the resting EEG signal. We assessed aperiodic activity in 85 healthy younger adults (mean age: 22.2 years, SD: 3.9, age range: 18-35, 37 male) and 92 healthy older adults (mean age: 66.1 years, SD: 8.2, age range 50-86, 53 male) by fitting the 1/f-like background activity evident in EEG power spectra using the fitting oscillations & one over f (FOOOF) toolbox. Across the scalp, the aperiodic exponent and offset were smaller in older compared to younger participants, reflecting a flatter 1/f-like slope and a downward broadband shift in the power spectra with age. Before correcting for aperiodic activity, older adults showed slower peak alpha frequency and reduced peak alpha power relative to younger adults. After correcting for aperiodic activity, peak alpha frequency remained slower in older adults; however, peak alpha power no longer differed statistically between age groups. The large sample size utilized in this study, as well as the depth of analysis, provides further evidence that the aperiodic component of the resting EEG signal is altered with aging and should be considered when investigating neural oscillatory activity.

neuroscience↗

bioRxiv2020

Non-lesioned subcortical brain volumes are associated with post-stroke sensorimotor behavior across 28 cohorts worldwide: An ENIGMA Stroke Recovery study

Background and PurposeUp to two-thirds of stroke survivors experience persistent sensorimotor impairments. Recovery relies on the integrity of spared brain areas to compensate for damaged tissue. Subcortical regions play critical roles in the control and regulation of sensorimotor circuits. The goal of this work is to identify associations between volumes of spared subcortical nuclei and sensorimotor behavior at different timepoints after stroke. MethodsWe pooled high-resolution T1-weighted MRI brain scans and behavioral data in 828 individuals with unilateral stroke from 28 cohorts worldwide. Cross-sectional analyses using linear mixed-effects models related post-stroke sensorimotor behavior to non-lesioned subcortical volumes (Bonferroni-corrected, p<0.004). We tested subacute ([≤]90 days) and chronic ([≥]180 days) stroke subgroups separately, with exploratory analyses in early stroke ([≤]21 days) and across all time. Sub-analyses in chronic stroke were also performed based on class of sensorimotor deficits (impairment, activity limitations) and side of lesioned hemisphere. ResultsWorse sensorimotor behavior was associated with a smaller ipsilesional thalamic volume in both early (n=179; d=0.68) and subacute (n=274, d=0.46) stroke. In chronic stroke (n=404), worse sensorimotor behavior was associated with smaller ipsilesional putamen (d=0.52) and nucleus accumbens (d=0.39) volumes, and a larger ipsilesional lateral ventricle (d=-0.42). Worse chronic sensorimotor impairment specifically (measured by the Fugl-Meyer Assessment; n=256) was associated with smaller ipsilesional putamen (d=0.72) and larger lateral ventricle (d=-0.41) volumes, while several measures of activity limitations (n=116) showed no significant relationships. In the full cohort across all time (n=828), sensorimotor behavior was associated with the volumes of the ipsilesional nucleus accumbens (d=0.23), putamen (d=0.33), thalamus (d=0.33), and lateral ventricle (d=-0.23). ConclusionsWe demonstrate significant relationships between post-stroke sensorimotor behavior and reduced volumes of subcortical gray matter structures that were spared by stroke, which differ by time and class of sensorimotor measure. These findings may provide additional targets for improving post-stroke sensorimotor outcomes.

neuroscience↗

bioRxiv2018

Characterization of young and old adult brains: An EEG functional connectivity analysis

Brain connectivity studies have reported that functional networks change with older age. We aim to (1) investigate whether electroencephalography (EEG) data can be used to distinguish between individual functional networks of young and old adults; and (2) identify the functional connections that contribute to this classification. Two eyes-open resting-state EEG recording sessions with 64 electrodes for each of 22 younger adults (19-37 years) and 22 older adults (63-85 years) were conducted. For each session, imaginary coherence matrices in theta, alpha, beta and gamma bands were computed. A range of machine learning classification methods were utilized to distinguish younger and older adult brains. A support vector machine (SVM) classifier was 94% accurate in classifying the brains by age group. We report decreased functional connectivity with older age in theta, alpha and gamma bands, and increased connectivity with older age in beta band. Most connections involving frontal, temporal, and parietal electrodes, and approximately two-thirds of connections involving occipital electrodes, showed decreased connectivity with older age. Just over half of the connections involving central electrodes showed increased connectivity with older age. Functional connections showing decreased strength with older age had significantly longer electrode-to-electrode distance than those that increased with older age. Most of the connections used by the classifier to distinguish participants by age group belonged to the alpha band. Findings suggest a decrease in connectivity in key networks and frequency bands associated with attention and awareness, and an increase in connectivity of the sensorimotor functional networks with ageing during a resting state.

neuroscience↗

bioRxiv2018

Test-retest reliability of functional brain network characteristics using resting-state EEG and graph theory

Metrics of brain network organization can be derived from neuroimaging data using graph theory. We explored the test-retest reliability of graph metrics of functional networks derived from resting-state electroencephalogram (EEG) recordings. Data were collected within two designs: (1) within sessions (WS) design where EEG data were collected from 18 healthy participants in four trials within a few hours and (2) between sessions (BS) design where EEG data were collected from 19 healthy participants in three trials on three different days at least one week apart. Electrophysiological source activity was reconstructed and functional connectivity between pairs of sensors or brain regions was determined in different frequency bands. We generated undirected binary graphs and used intra-class correlation coefficient (ICC) to estimate reliability. We showed that reliabilities ranged from poor to good. Reliability at the sensor-level was significantly higher than source-level. The most reliable graph metric at the sensor-level was cost efficiency and at the source-level was global efficiency. At the sensor-level: WS reliability was significantly higher than BS reliability; high beta band in WS design had the highest reliability; in WS design reliability in gamma band was significantly lower than reliability in low and high beta bands. At the source-level: low beta band in BS design had the highest reliability; there was no significant main effect of frequency band on reliability; reliabilities of WS and BS designs were not significantly different. These results suggest that these graph metrics can provide reliable outcomes, depending on how the data were collected and analysed.

neuroscience↗