André Forjaz

The paper quantifies PanIN burden and pancreatic composition across age to identify high-risk demographics associated with increased precancer burden.

This study enhances CAR-T cell migration through synthetic cytokine receptors, reducing metastasis in TNBC mouse models.

TiSAM improves whole-slide image segmentation by fusing spatial and histopathology features, achieving high accuracy across diverse datasets and scanners.

CODAvision provides a user-friendly interface for rapid, customizable medical image segmentation using deep learning, enabling non-experts to train and evaluate models across diverse imaging modalities.

The paper investigates muscle loss as a key evolutionary step in turtle shell development using multi-modal imaging and histology-based deep learning to analyze turtle embryos.

This paper introduces SMILE, a diffusion model for converting H&E stains to multiplex IHC images, showing superior performance in pancreatic islet analysis and breast cancer stain conversion.

The paper uses 3D imaging to analyze vascular and nervous systems in embryos, finding shared structural principles but distinct architectures shaped by biophysical constraints.

STAPLE automates spatial transcriptomics analysis by integrating multiple tools into a modular framework and provides AI-driven interpretation of results.

The paper develops a 3D multi-omic pipeline using deep learning to analyze chemotherapy response in pancreatic cancer, identifying molecular signatures of resistance and fibroblast-cancer interactions.

This study uses 3D multi-omic imaging to identify biomarkers of the pre-metastatic niche in lung cancer, revealing myeloid and senescent cell signatures associated with metastasis risk.

The paper identifies Tbx5 as a gene critical for forming a compartment boundary in the interventricular septum, and shows its disruption leads to congenital heart defects.

The paper presents a 3D multi-omic framework to detect and characterize ovarian cancer precursors in fallopian tubes, identifying TP53 mutations in microscopic lesions.

This paper develops a 3D multi-compartment assembloid that mimics human endometrial tissue and its menstrual cycle phases, enabling study of compartment-specific hormonal responses and paracrine signaling.

The paper introduces a framework for mathematical modeling of multicellular systems using interpretable cell behavior rules derived from biological knowledge and multi-omics data.

PIVOT is an open-source tool for nonlinear registration of multi-omic spatial data, demonstrating improved throughput compared to existing workflows.

This study shows that 3D assessments are necessary to accurately determine tissue composition and neoplastic content, as 2D methods under-sample spatial heterogeneity.

The paper integrates 3D imaging with nuclear segmentation to analyze nuclear morphology in human tissue, revealing spatial patterns and interactions in disease progression.

The paper profiles the immune microenvironment of PanINs in 3D at single-cell resolution to understand inflammation's role in cancer progression and finds immune heterogeneity and correlations with PanIN grade.

This study identifies high-motility tumor-associated monocytes (TAMos) that drive macrophage infiltration and cancer cell proliferation via IL-6 and MAPK pathways, suggesting IL-6 as a therapeutic target.

This paper uses a generative AI model to improve 3D tissue imaging by interpolating and restoring images, enhancing resolution and reducing artifacts across multiple modalities and species.

This paper develops velocity receptors (VRs) to enhance CAR T cell migration through solid tumors, improving tumor infiltration and survival.

This paper uses deep learning to label 17 kidney microstructures in 3D fetal rhesus macaque kidneys, revealing spatial relationships between glomeruli, arteries, and nephrons.