Iman Aganj

The paper predicts age and MMSE scores from brain connectivity graphs using a graph-based deep learning model, showing improved performance over existing methods.

This paper introduces a deep-learning method that improves cortical registration by integrating structural and diffusion MRI data with connectivity features, showing better functional alignment than FreeSurfer.

This paper presents a Hybrid-Fusion Transformer model that refines myocardium segmentation in cardiac CT by combining CT images with semi-automatic labels to remove papillary muscles.

This paper evaluates Graph Neural Networks for brain cortex segmentation using structural MRI and diffusion MRI data, finding GAT models perform competitively with non-graph methods.

This paper estimates spatial image gradients from diffusion MRI signals by modeling relaxation-time properties, showing significant correlation with gold-standard gradients across multiple datasets.

This study uses high-resolution fMRI to map resting-state functional connectivity in human ocular dominance columns, revealing depth- and subfield-specific patterns linked to perceptual biases.

This paper introduces a distribution-matching method to harmonize structural brain connectivity across sites and scanners, showing competitive performance compared to existing methods.

This study uses high-resolution functional MRI to show that ocular dominance columns with similar ocular preference are more functionally connected than those with different preferences in the human primary visual cortex.

This paper evaluates two methods for automatically estimating the locus coeruleus region from standard T1-weighted MRI scans using non-contrast neuroanatomical data.

The paper explores correlations between human structural brain connectivity and non-MRI variables in Alzheimer's disease, finding stronger associations with augmented connectivity and age-related decreases in connectivity.

The paper introduces a cortical surface-informed volumetric spatial smoothing method for fMRI data using graph signal processing to adapt smoothing to brain morphology.

This study quantifies volumetric morphometry and optical properties of human cerebellar cortex at micrometer resolution using as-PSOCT, revealing layer-specific variations and cross-subject variability.

This paper introduces a radius-optimized template matching method for brain lesion detection, reducing computational complexity while maintaining performance comparable to existing techniques.

This paper quantifies structural brain connectivity using diffusion MRI in aging and dementia, finding age-related trends and regional effects that suggest potential for age prediction and studying structural connections.

This paper introduces an anisotropic spatial filtering method for smoothing fMRI data in white matter, showing improved detection of anisotropic activations compared to isotropic Gaussian filters.

This study uses diffusion-informed white matter harmonics to analyze spatial dynamics of fMRI data, revealing subtle spatial modulations under functional load.

This paper introduces a new structural connectivity measure that better correlates with functional connectivity and improves Alzheimer's disease staging compared to streamline tractography.