Jose Inacio Costa-Filho

SpatialDINO: A Self-Supervised 3D Vision Transformer that enables Segmentation and Tracking in Crowded Cellular Environments

SpatialDINO enables automated segmentation and tracking of crowded cellular objects using self-supervised 3D vision transformers without manual annotations or retraining.

Tau seeding in neurons enabled by transient endolysosomal perforations are confined within endolysosomes

This study shows that tau seeding in neurons occurs via transient endolysosomal perforations that remain confined within endolysosomes and require PIKfyve activity.

Close-Up of vesicular ER Exit Sites by Volume Electron Imaging using FIB-SEM

The paper uses FIB-SEM and ASEM to identify and characterize vesicular ER exit sites in mammalian cells, revealing their abundance and organization.

CryoSamba: self-supervised deep volumetric denoising for cryo-electron tomography data

CryoSamba improves cryo-ET image quality by denoising 3D volumes through self-supervised deep learning without requiring labels or synthetic data.