A5014813060- Cell Image Analysis Techniques
- AI in cancer detection
- Cancer Cells and Metastasis
- Gaze Tracking and Assistive Technology
- Single-cell and spatial transcriptomics
- Radiomics and Machine Learning in Medical Imaging
- Parkinson's Disease Mechanisms and Treatments
- RNA regulation and disease
- Cancer Genomics and Diagnostics
- Neutrophil, Myeloperoxidase and Oxidative Mechanisms
- 3D Printing in Biomedical Research
- Mental Health and Psychiatry
- Immune cells in cancer
- Ginkgo biloba and Cashew Applications
- Lung Cancer Diagnosis and Treatment
- Face recognition and analysis
- Digital Imaging for Blood Diseases
- Hand Gesture Recognition Systems
- Diet and metabolism studies
- Pancreatic function and diabetes
- Metabolism, Diabetes, and Cancer
- Schizophrenia research and treatment
- Medical Imaging Techniques and Applications
- Remote-Sensing Image Classification
- Neurological diseases and metabolism
Universidad Publica de Navarra
2011-2024
Universidad de Navarra
2011-2024
Navarre Institute of Health Research
2021-2024
Centro de Investigación Biomédica en Red
2023
Centro de Investigación Biomédica en Red de Cáncer
2021
Servicio Navarro de Salud
2021
Foundation for Medical Research
2018
Abstract Neutrophil extracellular traps (NETs) are webs of nuclear DNA extruded by dying neutrophils infiltrating tissue. NETs constitute a defence mechanism to entrap and kill fungi bacteria. Tumours induce the formation advantage malignancy via variety mechanisms shown in mouse models. Here, we investigated presence human solid tumours their association with IL‐8 (CXCL8) protein expression CD8 + T‐cell density tumour microenvironment. Multiplex immunofluorescence panels were developed...
The migration of cancer cells is highly regulated by the biomechanical properties their local microenvironment. Using 3D scaffolds simple composition, several aspects cell mechanosensing (signal transduction, EMC remodeling, traction forces) have been separately analyzed in context migration. However, a combined study these factors that more closely resemble complex microenvironment ECM still missing. Here, we present comprehensive, quantitative analysis role cell-ECM interactions within...
A multistage procedure to detect eye features is presented. Multiresolution and topographic classification are used the iris center. The corner calculated combining valley detection eyelid curve extraction. algorithm tested in BioID database a proprietary containing more than 1200 images. results show that suggested robust accurate. Regarding center our method obtains best average behavior for compared other available algorithms. Additional contributions functions real time does not require...
Understanding the spatial interactions between elements of tumor microenvironment -i.e. cells. fibroblasts, immune cells- and how these relate to diagnosis or prognosis a is one goals computational pathology. We present NaroNet, deep learning framework that models multi-scale from multiplex-stained cancer tissue images provides patient-level interpretable predictions using seamless end-to-end pipeline. Trained only with their corresponding clinical labels, NaroNet unsupervisedly learns which...
We present a dynamic atlas composed of neuromelanin-enhanced magnetic resonance brain images 40 healthy subjects. The performance this is evaluated on the fully automated segmentation two paired neuromelanin-rich brainstem structures: substantia nigra pars compacta and locus coeruleus. show that our requires in average 60% less and, therefore, computation time than static multi-image while achieving similar performance. Then, we by applying atlas, subjects, to neuromelanin quantification set...
Abstract Predicting recurrence in low-grade, early-stage endometrial cancer (EC) is both challenging and clinically relevant. We present a weakly-supervised deep learning framework, NaroNet, that can learn, without manual expert annotation, the complex tumor-immune interrelations at three levels: local phenotypes, cellular neighborhoods, tissue areas. It uses multiplexed immunofluorescence for simultaneous visualization quantification of CD68 + macrophages, CD8 T cells, FOXP3 regulatory...
Neuromelanin (NM) loss in substantia nigra pars compacta (SNc) and locus coeruleus (LC) reflects neuronal death Parkinson's disease (PD). Since genetically-determined PD shows varied clinical expressivity, we wanted to accurately quantify locate brainstem NM iron, discover whether specific MRI patterns are linked Leucine-rich repeat kinase 2 G2019S (LRRK2-PD) or idiopathic (iPD). A 3D automated atlas-based segmentation pipeline (3D-ABSP) for NM/iron-sensitive images topographically...
Astrocytes are considered an essential source of blood-borne glucose or its metabolites to neurons. Nonetheless, the necessity main astrocyte transporter, i.e., GLUT1, for brain metabolism has not been defined. Unexpectedly, we found that was paradoxically augmented in mice with astrocytic GLUT1 reduction (GLUT1 ΔGFAP mice). These also exhibited improved peripheral especially obesity, rendering them metabolically healthier. Mechanistically, observed GLUT1-deficient astrocytes increased...
Abstract Motivation Recent advances in multiplex immunostaining and multispectral cytometry have opened the door to simultaneously visualizing an unprecedented number of biomarkers both liquid solid samples. Properly unmixing fluorescent emissions is a challenging task, which normally requires characterization individual fluorochromes from control As increases, cost time use reagents becomes prohibitively high. Here, we present fully unsupervised blind spectral method for separation highly...
Head pose estimation (HPE) is currently a growing research field, mainly because of the proliferation human–computer interfaces (HCI) in last decade. It offers wide variety applications, including human behavior analysis, driver assistance systems or gaze systems. This article aims to contribute development robust and accurate HPE methods based on 2D tracking face, enhancing performance both point 3D estimation. We start with baseline method for POSIT algorithm. A novel weighted variant then...
Achilles tendon rupture is a frequent injury with an increasing incidence. After clinical surgical repair, aimed at suturing the stumps back into their original position, repaired often plastically deformed and mechanically less strong than pre-injured tissue, muscle fatty degeneration contributing to function loss. Despite outcomes, pre-clinical research has mainly focused on structural lack of knowledge regarding progression from its consequences degenerative/regenerative processes...
There is a lack of automated tools for the segmentation and quantification neuromelanin (NM) iron in nigrosome-1 (N1). Existing evaluate N1 sign, i.e., presence or absence "swallow-tail" iron-sensitive MRI, globally analyze MRI signal an area containing N1, without providing volumetric delineation.
A new system is presented that enhances the interoperability between a video-oculographic (VOG) for mouse movement control and an electromyographic (EMG) click detection.The proposed VOG-EMG combines gaze muscle information to minimize number of undesired clicks due involuntary activations environmental noise.We tested with 24 subjects, comparing three different configurations: one in which VOG EMG systems worked independently two we used improve detection.Results show false-positive...
Eye tracking technology in low resolution scenarios is not a completely solved issue to date. The possibility of using eye mobile gadget challenging objective that would permit spread this non-explored fields. In paper, knowledge based approach presented solve gaze estimation settings. understanding the high paradigm permits propose alternative models estimation. manner, three are presented: geometrical model, an interpolation model and compound as solutions for remote systems. Since work...
Abstract The dopaminergic neuronal loss in the substantia nigra pars compacta (SNc) has been related to a reduction of neuromelanin (NM) and accumulation iron nigrosome-1 (N1) Parkinson’s disease (PD). This suggests that N1 degeneration could be promising early biomarker PD. To date, only qualitative visual scales have used assess its iron-sensitive images. Here we present first fully-automatic method for quantification NM content N1. Our uses multi-image atlas populated with healthy...
The first contribution of this paper is the presentation a synthetic video database where groundtruth 2D facial landmarks and 3D head poses available to be used for training evaluating Head Pose Estimation (HPE) methods. publicly contains videos users performing guided natural movements. second main submission hybrid method HPE based on from Ortography Scaling by Iterations (POSIT). landmark detection performed using Random Cascaded-Regression Copse (R-CR-C). For stage we use, state art...
Low cost iris tracking is one of the most challenging research topics for eye-tracking community. To this end, accurate detection centre in images captured by a web cam major goal. We propose novel method that based on image topography using multi-resolution to detect stable "valley" over different resolutions, which assumed be centre. Our algorithm was tested BioID database obtaining best average behavior. functions real time and does not require complex post processing stages.
New machine learning models designed to capture the histopathology of tissues should account not only for phenotype and morphology cells, but also learn complex spatial relationships between them. To achieve this, we represent tissue as an interconnected graph, where previously segmented cells become nodes graph. Then are learned embedded into a low-dimensional vector, using Graph Neural Network. We name this Representation Learning based strategy NARO (NAtural biological Objects),...
Abstract Astrocytes are considered an essential source of blood-borne glucose or its metabolites to neurons. Nonetheless, the necessity main astrocyte transporter, i.e. GLUT1, for brain metabolism has not been defined. Unexpectedly, we found that was paradoxically augmented in mice with astrocytic GLUT1 ablation (GLUT1 1′GFAP mice). These also exhibited improved peripheral especially obesity, rendering them metabolically healthier. Importantly, did present cognitive alterations....
Multiplex immunofluorescence is a novel, high-content imaging technique that allows simultaneous in situ labeling of multiple tissue antigens. This growing relevance the study tumor microenvironment, and discovery biomarkers disease progression or response to immune-based therapies. Given number markers potential complexity spatial interactions involved, analysis these images requires use machine learning tools rely for their training on availability large image datasets, extremely laborious...
ABSTRACT Standardized clinical procedures for antibiotic administration rely on pathogen identification and susceptibility testing, often performed single-colony bacterial isolates. For respiratory pathogens, this could be questionable, as chronic patients may persistently colonized by multiple clones or lineages from the same species. Indeed, strains of nontypeable Haemophilus influenzae , with different profiles, can co-isolated cystic fibrosis obstructive pulmonary disease sputum...
Chronic obstructive pulmonary disease (COPD) patients undergo infectious exacerbations whose frequency identifies a clinically meaningful phenotype. Mouse models have been mostly used to separately study both COPD and the processes, but reliable model of frequent exacerbator phenotype is still lacking. Accordingly, we first established single bacterial exacerbation by nontypeable Haemophilus influenzae (NTHi) infection on mice with emphysema-like lesions. We characterized this combining...
Multiplex tissue immunostaining is a novel technology of growing relevance as it can capture in situ the complex interactions existing between multiple elements tumor microenvironment. The existence and availability large, annotated image datasets key for objective development, training benchmarking bioimage analysis algorithms, especially those based on machine learning. Manual annotations multiplex images are, however, extremely laborious, often impracticable. In this paper, we present...