Ricardo Henriques

The paper tracks the adoption of bioimage-analysis software across 1.7 million microscopy papers from 2010 to 2025, finding increased usage and concentration on general-purpose platforms like ImageJ/Fiji.

This paper evaluates how reducing image resolution affects deep learning performance in bioimage segmentation, finding that lower resolution can improve accuracy or cause minimal degradation.

mAIcrobe provides an open-source framework for bacterial image analysis using deep learning models, enabling analysis of diverse bacterial species and microscopy modalities.

The paper discusses AI4Life's Open Calls and Public Challenges, highlighting the state of bioimage analysis, tool availability, and the need for better data and infrastructure.

VLab4Mic predicts structural resolvability in super-resolution microscopy by simulating imaging configurations and comparing results to experimental data.

NucleiSky registers microscopy images across scales and modalities by aligning nuclei constellations, achieving accurate localization with minimal landmarks.

PhotoFiTT quantifies phototoxicity in live-cell microscopy by analyzing mitotic timing, cell size, and activity, showing near-UV light causes significant mitotic delays at low doses.

This paper introduces SMOLM-LFM, a method for 3D single-molecule orientation and localization microscopy using ratiometric intensity estimation without polarization projections, enabling 6D molecular analysis.

This paper introduces a contrastive learning framework for nanoscale spatial-omics, enabling analysis of single-molecule localisation data to study protein architecture and its changes under various conditions.

Nano-org provides a curated resource of single-molecule localisation microscopy data for studying protein nanoscale distributions and their relationships across cell types and conditions.

The paper identifies non-synaptic exocytosis along axon shafts and shows how the submembrane actin-spectrin skeleton regulates this process.

The paper investigates how guidance cues coordinate multipolar migration in developing retinal neurons, revealing repulsive and attractive signaling pathways that guide proper lamination.

FeatureForest uses foundation model embeddings with random forests to enable fast, accurate segmentation of complex biological images with minimal labeling.

The paper introduces SReD, an unsupervised framework for detecting repetitive biological structures in microscopy images, demonstrating its use on three datasets.

The paper introduces VP-CLEM-Kit, a cost-effective SR-vCLEM pipeline for visual proteomics, achieving 5-fold resolution improvement at 7-fold lower cost.

NanoPyx improves bioimage analysis speed using adaptive machine learning to optimize algorithm selection and execution.

CellTracksColab is a platform for compiling, analyzing, and exploring tracking data from biological movies, enabling holistic dataset analysis and identification of behavioral patterns.

Fast4DReg corrects drift in 3D microscopy datasets using 2D cross-correlations, outperforming existing tools in speed and accuracy.

The BioImage Model Zoo provides a community standard, infrastructure, and open repository for sharing, testing, and deploying pre-trained deep learning microscopy models across multiple bioimage analysis tools.

ZeroCostDL4Mic provides a platform to use deep learning in microscopy, enabling tasks like segmentation and denoising through Google Colab.

NanoJ provides a high-performance open-source toolbox for super-resolution microscopy, offering tools for data alignment, image reconstruction, quality assessment, structural modeling, and sample control.

This paper demonstrates how deep learning-based image restoration extends fluorescence microscopy's capabilities by improving resolution, reducing photon exposure, and increasing frame rates.