Biology subjects

Cramer, S. C.

Publications and source records attributed to Cramer, S. C..

6 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↗

bioRxiv2024

Stroke and Motor Recovery are Associated with Regional and Age-Specific Changes in Periodic and Aperiodic Cortical Activity

Normal aging is associated with widespread changes in neuronal structure, function, and activity. The consequences of focal brain injury on global neuronal activity in aged individuals are poorly understood. Historically, stroke and aging have been associated with changes in narrow-band periodic neuronal activity, however recent work has highlighted the importance of broad-band aperiodic activity. Aperiodic activity is represented by the 1/f slope of power spectral density generated by cortical activity. Abnormalities in aperiodic activity have been identified in psychiatric disorders and stroke, are associated with cognitive dysfunction in aging, and have been hypothesized to reflect changes in excitation/inhibition balance. Here we sought to further explore changes in both periodic and aperiodic cortical activity in neurotypical intact young and aged healthy individuals and individuals with stroke. We compared "resting state" electroencephalograms from all participants after applying the specparam algorithm, which decomposes the power spectrum into aperiodic and periodic components. We also correlated stroke outcomes using previously obtained tests of motor outcome (box and block) to average whole cortex spectral slopes within the stroke group. Consistent with prior work we found a significant flattening (decrease in exponent) of power spectral slope with normal aging. We also found that both aging and stroke were associated with fewer periodic peaks within the power spectrum. Interestingly, we found that stroke was associated with a significant increase in spectral slope, but age moderated this effect. Younger stroke patients showed minimal difference in slope while older stroke patients had significantly steeper slopes (opposite to the direction in normal aging). Using MRIs from stroke participants we investigated the lesion locations most associated with changes in slope. Interestingly deep lesions were observed to have the greatest influence on cortical spectral slope. Finally, slope in the stroke group was correlated with performance on a test of manual dexterity, however this correlation was much more significant in aged individuals. Our data suggest that stroke in the aged brain has unique effects on aperiodic activity possibly reflecting unique influence of injury on cerebral excitation/inhibition balance in aged individuals and that the degree of these changes may be related to stroke outcomes.

neuroscience↗

bioRxiv2024

EEG-VLM Toolbox: Extending voxel-based lesion mapping to multi-dimensional EEG data

Focal brain lesions (such as with stroke) cause functional changes in local and distributed neural systems. While there is a long history of post-stroke neurophysiological assessment using electroencephalography (EEG), the observed neurophysiological changes have rarely been related to specific lesion locations. Therefore, the relationships between anatomical injury and physiological changes after stroke remain unclear. Voxel-based lesion symptom mapping (VLSM) is a tool for statistically relating stroke lesion locations to "symptoms", but current VLSM methods are restricted to symptoms that can be defined by a single value. Therefore, current VLSM techniques are unable to map the relationships between anatomical injury and multidimensional neurophysiological data such as EEG, which contains rich spatio-temporal information across different channels and frequency bands. Here we present a novel algorithm, EEG Voxel-based Lesion Mapping (EEG-VLM), that produces the set of significant relationships between precise neuroanatomical injury locations and neurophysiology (defined by a cluster of adjacent EEG channels and frequency bands). Further, the algorithm provides statistical analyses to define the overall significance of each neural structure-function relationship by correcting for multiple comparisons using a permutation test. Applying EEG-VLM to a dataset of recordings from chronic stroke patients performing a cued upper extremity movement task, we found that subjects with lesions in frontal subcortical white matter have reduced ipsilesional parietal cue-evoked EEG responses. These results are consistent with damage to a frontal-parietal network that has been associated with impairments in attention. EEG-VLM is a novel and unbiased method for relating neurophysiologic changes after stroke with neuroanatomic lesions. In the context of focal brain lesions associated with neurological impairments, we propose that this method will enable improved mechanistic understanding, facilitate biomarker development, and guide neurorehabilitation strategies.

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↗

bioRxiv2018

Timing of readiness potentials reflect a decision-making process in the human brain

Decision-making in two-alternative forced choice tasks has several underlying components including stimulus encoding, perceptual categorization, response selection, and response execution. Sequential sampling models of decision-making are based on an evidence accumulation process to a decision boundary. Animal and human studies have focused on perceptual categorization and provide evidence linking brain signals in parietal cortex to the evidence accumulation process. In this exploratory study, we use a task where the dominant contribution to response time is response selection and model the response time data with the drift-diffusion model. EEG measurement during the task show that the Readiness Potential (RP) recorded over motor areas has timing consistent with the evidence accumulation process. The duration of the RP predicts decision-making time, the duration of evidence accumulation, suggesting that the RP partly reflects an evidence accumulation process for response selection in the motor system. Thus, evidence accumulation may be a neural implementation of decision-making processes in both perceptual and motor systems. The contributions of perceptual categorization and response selection to evidence accumulation processes in decision-making tasks can be potentially evaluated by examining the timing of perceptual and motor EEG signals.

neuroscience↗

bioRxiv2017

The Anatomical Tracings of Lesions After Stroke (ATLAS) Dataset - Release 1.1

Stroke is the leading cause of adult disability worldwide, with up to two-thirds of individuals experiencing long-term disabilities. Large-scale neuroimaging studies have shown promise in identifying robust biomarkers (e.g., measures of brain structure) of long-term stroke recovery following rehabilitation. However, analyzing large rehabilitation-related datasets is problematic due to barriers in accurate stroke lesion segmentation. Manually-traced lesions are currently the gold standard for lesion segmentation on T1-weighted MRIs, but are labor intensive and require anatomical expertise. While algorithms have been developed to automate this process, the results often lack accuracy. Newer algorithms that employ machine-learning techniques are promising, yet these require large training datasets to optimize performance. Here we present ATLAS (Anatomical Tracings of Lesions After Stroke), an open-source dataset of 304 T1-weighted MRIs with manually segmented lesions and metadata. This large, diverse dataset can be used to train and test lesion segmentation algorithms and provides a standardized dataset for comparing the performance of different segmentation methods. We hope ATLAS release 1.1 will be a useful resource to assess and improve the accuracy of current lesion segmentation methods.

neuroscience↗