A5025755800- Gastrointestinal Bleeding Diagnosis and Treatment
- Colorectal Cancer Screening and Detection
- Gastric Cancer Management and Outcomes
- Radiomics and Machine Learning in Medical Imaging
- Gastrointestinal motility and disorders
- Video Surveillance and Tracking Methods
- Remote Sensing and LiDAR Applications
- 3D Surveying and Cultural Heritage
- Machine Learning and Data Classification
- Big Data and Business Intelligence
- Anomaly Detection Techniques and Applications
- Face and Expression Recognition
- Recommender Systems and Techniques
- Helicobacter pylori-related gastroenterology studies
- Complex Network Analysis Techniques
- Remote-Sensing Image Classification
- AI in cancer detection
- Robotics and Sensor-Based Localization
- Time Series Analysis and Forecasting
- Infant Health and Development
- COVID-19 diagnosis using AI
- Algorithms and Data Compression
- Machine Learning and Algorithms
- Sentiment Analysis and Opinion Mining
- Bayesian Modeling and Causal Inference
Universitat de Barcelona
2015-2024
Artificial Intelligence Research Institute
2022
Computer Vision Center
2008-2016
Barcelona Supercomputing Center
2012-2016
Centre de Recerca Matemàtica
2008-2015
Universitat Autònoma de Barcelona
2007-2013
The emergence of deep learning has considerably advanced the state-of-the-art in cardiac magnetic resonance (CMR) segmentation. Many techniques have been proposed over last few years, bringing accuracy automated segmentation close to human performance. However, these models all too often trained and validated using imaging samples from single clinical centres or homogeneous protocols. This prevented development validation that are generalizable across different centres, conditions scanner...
Forty hepatic abscesses were examined with dynamic computed tomography (CT). A "double target sign," consisting of a hypodense central area surrounded by first hyperdense ring and then zone, seems to be highly suggestive abscess formation. In 12 cases, the parenchyma surrounding lesion demonstrated transient hyperdensity after contrast injection, possibly due localized venous obstruction secondary acute inflammation. This is similar appearance an arterioportal fistula.
Learning to count is a learning strategy that has been recently proposed in the literature for dealing with problems where estimating number of object instances scene final objective. In this framework, task detect and localize individual seen as harder can be evaded by casting problem computing regression value from hand-crafted image features. paper we explore features are learned when training counting convolutional neural network order understand their underlying representation. To end...
Wireless capsule endoscopy (WCE) is a device that allows the direct visualization of gastrointestinal tract with minimal discomfort for patient, but at price large amount time screening. In order to reduce this time, several works have proposed automatically remove all frames showing intestinal content. These methods label as {intestinal content- clear} without discriminating between types content (with different physiological meaning) or portion image covered. addition, since presence has...
We have previously developed an original method to evaluate small bowel motor function based on computer vision analysis of endoluminal images obtained by capsule endoscopy. Our aim was demonstrate intestinal abnormalities in patients with functional disorders analysis. Patients (n = 205) and healthy subjects 136) ingested the endoscopic (Pillcam-SB2, Given-Imaging) after overnight fast 45 min gastric exit a liquid meal (300 ml, 1 kcal/ml) administered. Endoluminal image performed machine...
Abstract Background The precise relation of intestinal gas to symptoms, particularly abdominal bloating and distension remains incompletely elucidated. Our aim was define the normal values volume distribution identify abnormalities in functional‐type symptoms. Methods Abdominal computed tomography scans were evaluated healthy subjects ( n = 37) patients three conditions: basal (when they feeling well; 88), during an episode 82) after a challenge diet 24). Intestinal content measured by...
Abstract Background Cystic fibrosis (CF) is a multisystem disease caused by mutations in the cystic transmembrane conductance regulator (CFTR) protein. extensively expressed intestine and has an important role regulation of viscosity pH gut secretions. Several studies have reported delay small bowel colonic transit times patients with CF which been attributed to secretory dysfunction. Our aim was determine whether intestinal contractility affected these patients. Methods Consecutive referred...
Abstract Radiomics is an emerging technique for the quantification of imaging data that has recently shown great promise deeper phenotyping cardiovascular disease. Thus far, been mostly applied in single-centre studies. However, one main difficulties multi-centre studies inherent variability image characteristics due to centre differences. In this paper, a comprehensive analysis radiomics under several image- and feature-based normalisation techniques was conducted using magnetic resonance...
In today’s digital landscape, recommender systems have gained ubiquity as a means of directing users toward personalized products, services, and content. However, despite their widespread adoption long track research, these are not immune to shortcomings. A significant challenge faced by is the presence biases, which produces various undesirable effects, prominently popularity bias. This bias hampers diversity recommended items, thus restricting users’ exposure less popular or niche...
Abstract Background This study aimed to determine the proportion of cases with abnormal intestinal motility among patients functional bowel disorders. To this end, we applied an original method, previously developed in our laboratory, for analysis endoluminal images obtained by capsule endoscopy. novel technology is based on computer vision and machine learning techniques. Methods The endoscopic (Pillcam SB1; Given Imaging, Yokneam, Israel) was administered 80 disorders 70 healthy subjects....
State-of-the-art machine learning models, and especially deep ones, are significantly data-hungry; they require vast amounts of manually labeled samples to function correctly. However, in most medical imaging fields, obtaining said data can be challenging. Not only the volume is a problem, but also imbalances within its classes; it common have many more images healthy patients than those with pathology. Computer-aided diagnostic systems suffer from these issues, usually over-designing their...
Colon Capsule Endoscopy (CCE) is a minimally invasive procedure which increasingly being used as an alternative to conventional colonoscopy. Videos recorded by the capsule cameras are long and require one or more experts' time review identify polyps other potential intestinal problems that can lead major health issues. We developed tested multi-platform web application, AI-Tool, embeds Convolution Neural Network (CNN) help CCE reviewers. With of artificial intelligence, AI-Tool able detect...