A5044731121- Extracellular vesicles in disease
- Cell Image Analysis Techniques
- Image Processing Techniques and Applications
- Advanced Fluorescence Microscopy Techniques
- Single-cell and spatial transcriptomics
- AI in cancer detection
- 3D Printing in Biomedical Research
- Genetics, Bioinformatics, and Biomedical Research
- bioluminescence and chemiluminescence research
- Diet and metabolism studies
- Congenital gastrointestinal and neural anomalies
- Gastrointestinal motility and disorders
- Cancer Genomics and Diagnostics
- Statistical Methods in Clinical Trials
- Advanced Biosensing Techniques and Applications
- Animal testing and alternatives
- Cellular Mechanics and Interactions
- Epigenetics and DNA Methylation
- RNA modifications and cancer
- Health Systems, Economic Evaluations, Quality of Life
- Advanced Electron Microscopy Techniques and Applications
- Meta-analysis and systematic reviews
- Data Analysis with R
- Cancer-related gene regulation
- Infrared Thermography in Medicine
Instituto Gulbenkian de Ciência
2021-2024
Universidad Carlos III de Madrid
2019-2024
Hospital General Universitario Gregorio Marañón
2020-2024
Abstract The Cell Tracking Challenge is an ongoing benchmarking initiative that has become a reference in cell segmentation and tracking algorithm development. Here, we present significant number of improvements introduced the challenge since our 2017 report. These include creation new segmentation-only benchmark, enrichment dataset repository with datasets increase its diversity complexity, silver standard corpus based on most competitive results, which will be particular interest for...
This work demonstrates and guides how to use a range of state-of-the-art artificial neural-networks analyse bacterial microscopy images using the recently developed ZeroCostDL4Mic platform. We generated database image datasets used train networks for various analysis tasks present strategies data acquisition curation, as well model training. showcase different deep learning (DL) approaches segmenting bright field fluorescence species, object detection classify growth stages in time-lapse...
Abstract Biomedical research has come to rely on p-values as a deterministic measure for data-driven decision-making. In the largely extended null hypothesis significance testing identifying statistically significant differences among groups of observations, single p-value is computed from sample data. Then, it routinely compared with threshold, commonly set 0.05, assess evidence against having non-significant groups, or hypothesis. Because estimated tends decrease when size increased,...
Abstract Deep learning-based approaches are revolutionizing imaging-driven scientific research. However, the accessibility and reproducibility of deep workflows for imaging scientists remain far from sufficient. Several tools have recently risen to challenge democratizing learning by providing user-friendly interfaces analyze new data with pre-trained or fine-tuned models. Still, few existing models interoperable between these tools, critically restricting a model’s overall utility...
ABSTRACT Fluorescence microscopy is essential for studying living cells, tissues and organisms. However, the fluorescent light that switches on molecules also harms samples, jeopardizing validity of results – particularly in techniques such as super-resolution microscopy, which demands extended illumination. Artificial intelligence (AI)-enabled software capable denoising, image restoration, temporal interpolation or cross-modal style transfer has great potential to rescue live imaging data...
Tissue stiffness is a critical prognostic factor in breast cancer and associated with metastatic progression. Here we show an alternative complementary hypothesis of tumor progression whereby physiologic matrix affects the quantity protein cargo small extracellular vesicles (EV) produced by cells, which turn aid cell dissemination. Primary patient tissue released cells on matrices that model human tumors (25 kPa; stiff EVs) feature increased adhesion molecule presentation (ITGα2β1, ITGα6β4,...
Abstract Optical microscopy is an indispensable tool in life sciences research, but conventional techniques require compromises between imaging parameters like speed, resolution, field of view and phototoxicity. To overcome these limitations, data‐driven microscopes incorporate feedback loops data acquisition analysis. This review overviews how machine learning enables automated image analysis to optimise real time. We first introduce key concepts methods relevant Subsequently, we highlight...
Cell migration is a critical contributor to metastasis. Cytokine production and its role in cancer cell have been traditionally associated with immune cells. We find that the histone methyltransferase Mixed-Lineage Leukemia 1 (MLL1) controls 3D via cytokines, IL-6, IL-8, TGF-β1, secreted by cells themselves. MLL1, scaffold protein Menin, actin filament assembly IL-6/8/pSTAT3/Arp3 axis myosin contractility TGF-β1/Gli2/ROCK1/2/pMLC2 axis, which together regulate dynamic protrusion generation...
Abstract Small extracellular vesicles (sEVs) are cell-derived of nanoscale size (~30–200 nm) that function as conveyors information between cells, reflecting the cell their origin and its physiological condition in content. Valuable on shape even composition individual sEVs can be recorded using transmission electron microscopy (TEM). Unfortunately, sample preparation for TEM image acquisition is a complex procedure, which often leads to noisy images renders automatic quantification an...
In life sciences, tracking objects from movies enables researchers to quantify the behavior of single particles, organelles, bacteria, cells, and even whole animals. While numerous tools now allow automated video, a significant challenge persists in compiling, analyzing, exploring large datasets generated by these approaches. Here, we introduce CellTracksColab, platform tailored simplify exploration analysis cell data. CellTracksColab facilitates compiling results across multiple fields...
We present DINOSim, a novel approach leveraging the DINOv2 pretrained encoder for zero-shot object detection and segmentation in electron microscopy datasets. By exploiting semantic embeddings, DINOSim generates pseudo-labels from patch distances to user-selected reference, which are subsequently employed k-nearest neighbors framework inference. Our method effectively detects segments previously unseen objects images without additional fine-tuning or prompt engineering. also investigate...
ABSTRACT DeepImageJ is a user-friendly solution that enables the generic use of pre-trained deep learn ing (DL) models for biomedical image analysis in ImageJ. The deepImageJ environment gives access to largest bioimage repository DL (BioImage Model Zoo). Hence, non-experts can easily perform common processing tasks life-science research with DL-based tools including pixel and object classification, instance segmentation, denoising or virtual staining. compatible existing state-of-the-art...
Abstract The enteric nervous system (ENS) plays an important role in coordinating gut function. ENS consists of extensive network neurons and glial cells within the wall gastrointestinal tract. Alterations neuronal distribution, function, type are strongly associated with neuropathies (GI) dysfunction can serve as biomarkers for disease. However, current methods assessing counts distribution suffer from undersampling. This is partly due to challenges imaging analyzing large tissue areas,...
The enteric nervous system (ENS) consists of an extensive network neurons and glial cells embedded within the wall gastrointestinal (GI) tract. Alterations in neuronal distribution function are strongly associated with GI dysfunction. Current methods for assessing suffer from undersampling, partly due to challenges imaging analyzing large tissue areas, operator bias manual analysis. We present Gut Analysis Toolbox (GAT), image analysis tool designed characterization their neurochemical...
Abstract Generative models, such as diffusion have made significant advancements in recent years, enabling the synthesis of high‐quality realistic data across various domains. Here, adaptation and training a model on super‐resolution microscopy images are explored. It is shown that generated resemble experimental images, generation process does not exhibit large degree memorization from existing set. To demonstrate usefulness generative for augmentation, performance deep learning‐based...
Through digital imaging, microscopy has evolved from primarily being a means for visual observation of life at the micro- and nano-scale, to quantitative tool with ever-increasing resolution throughput. Artificial intelligence, deep neural networks, machine learning are all niche terms describing computational methods that have gained pivotal role in microscopy-based research over past decade. This Roadmap is written collectively by prominent researchers encompasses selected aspects how...
Abstract In life sciences, tracking objects from movies enables researchers to quantify the behavior of single particles, organelles, bacteria, cells, and even whole animals. While numerous tools now allow automated video, a significant challenge persists in compiling, analyzing, exploring large datasets generated by these approaches. Here, we introduce CellTracksColab, platform tailored simplify exploration analysis data. CellTracksColab facilitates compiling results across multiple fields...
Deep learning has revolutionised the analysis of extensive microscopy datasets, yet challenges persist in widespread adoption these techniques. Many lack access to training data, computing resources, and expertise develop complex models. We introduce DL4MicEverywhere, advancing our previous ZeroCostDL4Mic platform, make deep more accessible. DL4MicEverywhere uniquely allows flexible deployment across diverse computational environments by encapsulating methods interactive Jupyter notebooks...
Abstract This manuscript showcases the latest advancements in deepImageJ, a pivotal Fiji/ImageJ plugin for bioimage analysis life sciences. The plugin, known its user-friendly interface, facilitates application of diverse pre-trained neural networks to custom data. demonstrates number deepImageJ capabilities, particularly executing complex pipelines, 3D analysis, and processing large images. A key development is integration Java Deep Learning Library (JDLL), expanding deepImageJ’s...
<title>Abstract</title> Phototoxicity in live-cell fluorescence microscopy can compromise experimental outcomes, yet quantitative methods to assess its impact remain limited. Here we present PhotoFiTT (Phototoxicity Fitness Time Trial), an integrated framework combining a standardised protocol with advanced image analysis quantify light-induced cellular stress label-free settings. leverages machine learning and cell cycle dynamics analyse mitotic timing, size changes, overall activity...
Background and purpose Few tools are available to predict tumor response treatment. This retrospective study assesses visual automatic heterogeneity from 18 F-FDG PET images as predictors of in locally advanced rectal cancer. Methods included 37 LARC patients who underwent an before their neoadjuvant therapy. One expert segmented the images. Blinded patient´s outcome, two experts established by consensus a score for heterogeneity. Metabolic texture parameters were extracted area....