Adrian Vasile Dalca

Deep learning localizes focal biology implicated in therapeutic resistance within routine histology

Weakly supervised deep learning localizes focal tissue regions enriched for therapeutically relevant biology in routine histology, offering a scalable strategy to study therapeutic resistance across large patient populations.

Structural Connectome Analysis using a Graph-based Deep Model for Age and Dementia Prediction

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

Machine learning of dissection photographs and surface scanning for quantitative 3D neuropathology

The paper develops open-source tools for 3D analysis of brain dissection photographs and surface scans, achieving accurate reconstructions and segmentations comparable to MRI.

Mapping the subcortical connectivity of the human default mode network

This paper maps subcortical connectivity of the human default mode network using rs-fMRI and a novel tensor decomposition method, identifying key subcortical regions correlated with the DMN.

A multimodal imaging and analysis pipeline for creating a cellular census of the human cerebral cortex

The paper develops an imaging pipeline to create a cell census of the human cerebral cortex using MRI, immunohistochemistry, and light-sheet fluorescence microscopy.

MRI Radiomic Signature of White Matter Hyperintensities Is Associated with Clinical Phenotypes

This paper develops a radiomic signature from T2-FLAIR MRI images to predict white matter hyperintensities burden and links it to clinical phenotypes.

Reliability and sensitivity of two whole-brain segmentation approaches included in FreeSurfer - ASEG and SAMSEG

This paper compares two whole-brain segmentation methods, ASEG and SAMSEG, in FreeSurfer, finding SAMSEG provides more reliable and sensitive measurements for detecting longitudinal changes and Alzheimer's disease-related atrophy.

Sex-specific lesion topographies explain outcomesafter acute ischemic stroke

This study identifies sex-specific lesion patterns in acute ischemic stroke that correlate with stroke severity, highlighting differences in lesion distribution between men and women.

White Matter Hyperintensity Quantification in Large-Scale Clinical Acute Ischemic Stroke Cohorts - The MRI-GENIE Study

The paper presents an automated pipeline for quantifying white matter hyperintensity in acute ischemic stroke cohorts, showing improved accuracy and enabling large-scale analysis.

Effective reserve: a latent variable to improve outcome prediction in stroke

This paper introduces effective reserve (eR), a latent variable derived from clinical and imaging data, to improve prediction of functional outcomes after acute ischemic stroke.