Rafael Molina
YOU?
Author Swipe
View article: Rice husk silica as a platform for iron biocatalysts via silanol group confinement
Rice husk silica as a platform for iron biocatalysts via silanol group confinement Open
View article: Endoscopy is a Resource With Diagnostic/Therapeutic Power
Endoscopy is a Resource With Diagnostic/Therapeutic Power Open
Introduction: endoscopy is in a unique position at the interface between various medical and surgical disciplines. Endoscopy is a medical procedure that allows the interior of the entire gastrointestinal tract to be visualized by means of …
View article: Automate tissue processing with STEMprep™ for versatile sample preparation 3334
Automate tissue processing with STEMprep™ for versatile sample preparation 3334 Open
Description Tissue environments are specialized to support distinct functions. Analyzing cell interactions and gene expression within tissues is essential for advancing tissue research and understanding disease mechanisms. Tissue samples m…
View article: torchmil: A PyTorch-based library for deep Multiple Instance Learning
torchmil: A PyTorch-based library for deep Multiple Instance Learning Open
Multiple Instance Learning (MIL) is a powerful framework for weakly supervised learning, particularly useful when fine-grained annotations are unavailable. Despite growing interest in deep MIL methods, the field lacks standardized tools fo…
View article: Anterior right hepatic artery pseudoaneurysm secondary to biliary tract instrumentation treated by angioembolization
Anterior right hepatic artery pseudoaneurysm secondary to biliary tract instrumentation treated by angioembolization Open
Hepatic artery pseudoaneurysm is a rare complication following biliary tract instrumentation. Clinical presentation may range from asymptomatic course to catastrophic hemorrhage with high morbidity and mortality. We report a case of anteri…
View article: Probabilistic smooth attention for deep multiple instance learning in medical imaging
Probabilistic smooth attention for deep multiple instance learning in medical imaging Open
View article: A fusocelular skin dataset with whole slide images for deep learning models
A fusocelular skin dataset with whole slide images for deep learning models Open
View article: Probabilistic Smooth Attention for Deep Multiple Instance Learning in Medical Imaging
Probabilistic Smooth Attention for Deep Multiple Instance Learning in Medical Imaging Open
View article: Spatially-Aware Loss Functions for GAN-Driven Super-Resolution
Spatially-Aware Loss Functions for GAN-Driven Super-Resolution Open
Generative Adversarial Networks (GANs) have shown great performance on super-resolution problems since they can generate more visually realistic images and video frames. However, these models often introduce side effects into the outputs, …
View article: Using Variational Autoencoders for Out of Distribution Detection in Histological Multiple Instance Learning
Using Variational Autoencoders for Out of Distribution Detection in Histological Multiple Instance Learning Open
In the context of histological image classification, Multiple Instance Learning (mil) methods only require labels at Whole Slide Image (wsi) level, effectively reducing the annotation bottleneck. However, for their deployment in real scena…
View article: Evidence of Synergistic Effect in Spinel-Type Co-Mn Mixed Oxides Supported on 3dom-Al2o3 in the Catalytic Oxidation Reaction of Toluene
Evidence of Synergistic Effect in Spinel-Type Co-Mn Mixed Oxides Supported on 3dom-Al2o3 in the Catalytic Oxidation Reaction of Toluene Open
View article: The CrowdGleason dataset: Learning the Gleason grade from crowds and experts
The CrowdGleason dataset: Learning the Gleason grade from crowds and experts Open
The experiments show that the CrowdGleason dataset can be successfully used for training and validating supervised and crowdsourcing methods. Furthermore, the crowdsourcing methods trained on this dataset obtain competitive results against…
View article: Sm: enhanced localization in Multiple Instance Learning for medical imaging classification
Sm: enhanced localization in Multiple Instance Learning for medical imaging classification Open
Multiple Instance Learning (MIL) is widely used in medical imaging classification to reduce the labeling effort. While only bag labels are available for training, one typically seeks predictions at both bag and instance levels (classificat…
View article: Robust blind color deconvolution and blood detection on histological images using Bayesian K-SVD
Robust blind color deconvolution and blood detection on histological images using Bayesian K-SVD Open
View article: Focused Active Learning for Histopathological Image Classification
Focused Active Learning for Histopathological Image Classification Open
Active Learning (AL) has the potential to solve a major problem of digital pathology: the efficient acquisition of labeled data for machine learning algorithms. However, existing AL methods often struggle in realistic settings with artifac…
View article: A General Method to Incorporate Spatial Information into Loss Functions for GAN-based Super-resolution Models
A General Method to Incorporate Spatial Information into Loss Functions for GAN-based Super-resolution Models Open
Generative Adversarial Networks (GANs) have shown great performance on super-resolution problems since they can generate more visually realistic images and video frames. However, these models often introduce side effects into the outputs, …
View article: Hyperbolic Secant representation of the logistic function: Application to probabilistic Multiple Instance Learning for CT intracranial hemorrhage detection
Hyperbolic Secant representation of the logistic function: Application to probabilistic Multiple Instance Learning for CT intracranial hemorrhage detection Open
View article: Advancing Content-Based Histopathological Image Retrieval Pre-Processing: A Comparative Analysis of the Effects of Color Normalization Techniques
Advancing Content-Based Histopathological Image Retrieval Pre-Processing: A Comparative Analysis of the Effects of Color Normalization Techniques Open
Content-Based Histopathological Image Retrieval (CBHIR) is a search technique based on the visual content and histopathological features of whole-slide images (WSIs). CBHIR tools assist pathologists to obtain a faster and more accurate can…
View article: Learning from crowds for automated histopathological image segmentation
Learning from crowds for automated histopathological image segmentation Open
Automated semantic segmentation of histopathological images is an essential task in Computational Pathology (CPATH). The main limitation of Deep Learning (DL) to address this task is the scarcity of expert annotations. Crowdsourcing (CR) h…
View article: Multicenter Validation of Expert Software Using Six Tumor Biomarkers to Stratify the Risk of Lung Cancer
Multicenter Validation of Expert Software Using Six Tumor Biomarkers to Stratify the Risk of Lung Cancer Open
View article: Are you sure it’s an artifact? Artifact detection and uncertainty quantification in histological images
Are you sure it’s an artifact? Artifact detection and uncertainty quantification in histological images Open
Modern cancer diagnostics involves extracting tissue specimens from suspicious areas and conducting histotechnical procedures to prepare a digitized glass slide, called Whole Slide Image (WSI), for further examination. These procedures fre…
View article: BCD-net: Stain separation of histological images using deep variational Bayesian blind color deconvolution
BCD-net: Stain separation of histological images using deep variational Bayesian blind color deconvolution Open
View article: Annotation protocol and crowdsourcing multiple instance learning classification of skin histological images: The CR-AI4SkIN dataset
Annotation protocol and crowdsourcing multiple instance learning classification of skin histological images: The CR-AI4SkIN dataset Open
View article: Introducing instance label correlation in multiple instance learning. Application to cancer detection on histopathological images
Introducing instance label correlation in multiple instance learning. Application to cancer detection on histopathological images Open
View article: Probabilistic Modeling of Inter- and Intra-observer Variability in Medical Image Segmentation
Probabilistic Modeling of Inter- and Intra-observer Variability in Medical Image Segmentation Open
Medical image segmentation is a challenging task, particularly
\ndue to inter- and intra-observer variability, even
\nbetween medical experts. In this paper, we propose a
\nnovel model, called Probabilistic Inter-Observer and iNtra-
\nObse…
View article: Project Meitner. Contributions of the pioneer women of radioactivity
Project Meitner. Contributions of the pioneer women of radioactivity Open
Project Meitner is an outreach initiative aiming at raising awareness on the situation of women in Physics. To this purpose, a series of actions have been carried out at the Instituto de Física Corpuscular (IFIC, Spain) with a double purpo…
View article: Learning Moore-Penrose based residuals for robust non-blind image deconvolution
Learning Moore-Penrose based residuals for robust non-blind image deconvolution Open
View article: Probabilistic Modeling of Inter- and Intra-observer Variability in Medical Image Segmentation
Probabilistic Modeling of Inter- and Intra-observer Variability in Medical Image Segmentation Open
Medical image segmentation is a challenging task, particularly due to inter- and intra-observer variability, even between medical experts. In this paper, we propose a novel model, called Probabilistic Inter-Observer and iNtra-Observer vari…
View article: Smooth Attention for Deep Multiple Instance Learning: Application to CT Intracranial Hemorrhage Detection
Smooth Attention for Deep Multiple Instance Learning: Application to CT Intracranial Hemorrhage Detection Open
Multiple Instance Learning (MIL) has been widely applied to medical imaging diagnosis, where bag labels are known and instance labels inside bags are unknown. Traditional MIL assumes that instances in each bag are independent samples from …
View article: Probabilistic Attention based on Gaussian Processes for Deep Multiple Instance Learning
Probabilistic Attention based on Gaussian Processes for Deep Multiple Instance Learning Open
Multiple Instance Learning (MIL) is a weakly supervised learning paradigm that is becoming increasingly popular because it requires less labeling effort than fully supervised methods. This is especially interesting for areas where the crea…