Guillermo Sapiro

An Evidence-Grounded Research Assistant for Functional Genomics and Drug Target Assessment

Alvessa improves accuracy in functional genomics and drug target assessment by integrating evidence-based reasoning and verification.

Deep-learning based fully automatic segmentation of the globus pallidus interna and externa using ultra-high 7 Tesla MRI

This paper introduces GP-net, a deep-learning model for automatic segmentation of the globus pallidus interna and externa using 7 Tesla MRI, showing improved results over atlas-based methods.

Measuring Robustness of Brain Networks in Autism Spectrum Disorder with Ricci Curvature

This study uses Ricci curvature to measure changes in brain network robustness in ASD patients after stem cell infusion, identifying regions not detected by traditional methods.

Multifaceted Changes in Synaptic Composition and Astrocytic Involvement in a Mouse Model of Fragile X Syndrome

This study examines synapse-type and astrocytic changes in a FXS mouse model, revealing layer-specific synaptic density alterations and reduced astrocytic association in excitatory synapses.

Development of algorithms for automated detection of cervical pre-cancers with a low-cost, point-of-care, Pocket Colposcope

The paper develops algorithms to automate cervical pre-cancer detection using cervigram images, achieving higher accuracy than expert physicians.

Automatic Localization of the Subthalamic Nucleus on Patient-Specific Clinical MRI by Incorporating 7T MRI and Machine Learning: Application in Deep Brain Stimulation

This paper develops an automatic method to localize the subthalamic nucleus on standard clinical MRI using 7T MRI data and machine learning, showing improved accuracy compared to existing atlases.

A Computational Synaptic Antibody Characterization and Screening Framework for Array Tomography

The paper introduces a framework for characterizing and screening antibodies against synaptic molecules for array tomography, providing objective metrics to evaluate antibody performance.

Active Learning of Cortical Connectivity from Two-Photon Imaging Data

The paper introduces an active learning method to infer sparse cortical connectivity from two-photon imaging data, showing it improves inference speed and provides confidence intervals.

Continuous Dice Coefficient: a Method for Evaluating Probabilistic Segmentations

This paper introduces the continuous Dice coefficient (cDC) to evaluate probabilistic segmentations, showing it is less biased to structure size and more robust to partial volume effects than the classical Dice coefficient.