A5087240427- Fetal and Pediatric Neurological Disorders
- Neonatal Respiratory Health Research
- Congenital Diaphragmatic Hernia Studies
- Ultrasound in Clinical Applications
- Prenatal Screening and Diagnostics
- Preterm Birth and Chorioamnionitis
- Pregnancy and preeclampsia studies
- Pregnancy-related medical research
- AI in cancer detection
- Neonatal and fetal brain pathology
- Domain Adaptation and Few-Shot Learning
- Ectopic Pregnancy Diagnosis and Management
- Assisted Reproductive Technology and Twin Pregnancy
- Retinal Diseases and Treatments
- Cutaneous lymphoproliferative disorders research
- Nonmelanoma Skin Cancer Studies
- Cutaneous Melanoma Detection and Management
- Glaucoma and retinal disorders
- Digital Radiography and Breast Imaging
- Breast Lesions and Carcinomas
- Radiomics and Machine Learning in Medical Imaging
- Lung Cancer Diagnosis and Treatment
- Retinal Imaging and Analysis
- Medical Research and Treatments
- Lymphadenopathy Diagnosis and Analysis
SOM Biotech (Spain)
2023-2025
Hospital Sant Joan de Déu Barcelona
2019-2023
Universitat de Barcelona
2019-2023
Hospital Clínic de Barcelona
2019-2022
The goal of this study was to evaluate the maturity current Deep Learning classification techniques for their application in a real maternal-fetal clinical environment. A large dataset routinely acquired screening ultrasound images (which will be made publicly available) collected from two different hospitals by several operators and machines. All were manually labeled an expert maternal fetal clinician. Images divided into 6 classes: four most widely used anatomical planes (Abdomen, Brain,...
Abstract Introduction Prematurity is a major global health issue. Twin pregnancies are group at especially high risk of preterm birth. Sonographic mid‐trimester cervical length has limited accuracy in predicting This study aimed to evaluate the association between sonographic markers early remodeling and inflammatory biomarkers fetal fibronectin, alone or combination, as predictors birth before 34+0 weeks asymptomatic twin pregnancies. Material Methods Prospective cohort study, including...
Abstract The objective of this study was to evaluate the performance a new version quantusFLM®, software tool for prediction neonatal respiratory morbidity (NRM) by ultrasound, which incorporates fully automated fetal lung delineation based on Deep Learning techniques. A set 790 ultrasound images obtained at 24 + 0–38 6 weeks’ gestation evaluated. Perinatal outcomes and occurrence NRM were recorded. quantusFLM® 3.0 applied all automatically delineate predict risk. test compared with same...
The objective of this study was to evaluate a novel automated test based on ultrasound cervical texture analysis predict spontaneous Preterm Birth (sPTB) alone and in combination with Cervical Length (CL). General population singleton pregnancies between 18 + 0 24 6 weeks' gestation were assessed prospectively at two centers. images evaluated the occurrence sPTB before weeks 37 34 recorded. CL measured on-site. applied offline all images. Their performance separately 633 recruited patients....
The aim of this study was to develop a pipeline using state-of-the-art deep learning methods automatically delineate and measure several the most important brain structures in fetal ultrasound (US) images.The dataset composed 5,331 images acquired during routine mid-trimester US scan. Our proposed performs following three steps: plane classification (transventricular, transthalamic, or transcerebellar plane); delineation (9 different structures); automatic measurement (from structure...
The aim of this study is to assess the potential quantitative image analysis and machine learning techniques differentiate between malignant lymph nodes benign affected by reactive changes due COVID-19 vaccination.
ABSTRACT Objectives To evaluate a novel Artificial Intelligence (AI) method for the detection of malignant skin lesions from dermoscopic images. Methods 58,457 images available online International Skin Imaging Collaboration (ISIC) Archive were downloaded. These acquired different centers worldwide by recognized dermatologists and show varied clinical outcomes belonging to types benign malign lesions. A state-of-the-art AI lesion classifier based on Deep Learning was designed. The method,...
Abstract Objectives To design and evaluate a novel automated glaucoma classifier from retinal fundus images. Methods We designed Artificial Intelligence (AI) tool to detect then downloaded publicly available image datasets containing healthy patients images with verified labels. Two thirds of the were used train classifier. The remaining third was create several cross-validation evaluation sets realistic prevalence, classifier’s performance in screening scenario. Results 10,658 seven...
To evaluate the reproducibility of ultrasound cervical length (CL) measurement at second trimester.A set 565 images were collected 19 + 0-24 6 weeks' gestation. Two senior maternal-fetal specialists measured CL in each image on three occasions 2 weeks apart. In interval between first and following two measures, clinicians reviewed 20 together to agree criteria for measurement. Measurements analyzed intra- inter-observer disagreement. The robustness patient classification when measure was...
Abstract To evaluate the concordance of risk neonatal respiratory morbidity (NRM) assessed by quantitative ultrasound lung texture analysis (QuantusFLM) between twin fetuses same pregnancy. Prospective study conducted in pregnancies. Fetal images were obtained at 26.0–38.6 weeks gestation. Categorical (high or low) and continuous results NRM compared twins. from 131 pairs (262 images) twins included. The classified into three gestational age ranges: Group 1 (26.0–29.6 weeks, 78 images, 39...
The objective of this study was to evaluate the performance quantitative ultrasound fetal lung texture analysis in predicting neonatal respiratory morbidity (NRM) twin pregnancies. This an ambispective involving consecutive cases. Eligible cases included pregnancies between 27.0 and 38.6 weeks gestation, for which image thorax obtained within 48 h delivery. Images were analyzed using quantusFLM® version 3.0. primary outcome morbidity, defined as occurrence either transient tachypnea newborn...
Deep learning (DL) technology has been proposed as an available tool to improve clinical and research in fetal medicine. However, currently DL approaches are not easily affordable since they require massive amount of accurately classified and/or processed ultrasound images, which means time knowledge. Our objective was evaluate the performance a algorithm automatically classify images. Prospective study including 1784 patients that were evaluated our routine screening scan unit from 18 40...
To evaluate the performance of deep learning algorithms to automatically classify 3 standard axial planes fetal brain used as part ultrasound routine pregnancy screening during second trimester. We performed a prospective study 14 months including all singleton pregnant women attending trimester (19 25 weeks gestational ages). A total 5430 images were included from 1994 pregnancies. senior maternal-fetal specialist manually classified these in one different (transventricular, transthalamic...
To evaluate the risk of neonatal respiratory morbidity (NRM) assessed by QuantusFLM® in fetuses twin and singleton pregnancies. Prospective study pregnancies from 26.0 to 38.6 weeks gestation, for which ultrasound images an axial section fetal thorax were obtained. Images collected stored original DICOM format analysed with QuantusFLM®. We included 212 (98 114 singleton), 450 classified three groups gestational age (table a). group-1 (149 images); group-2 (161 images) group-3 (140 images)....
To evaluate the agreement on risk of neonatal respiratory morbidity (NRM) in fetuses twin pregnancies. Prospective study pregnancies from 26 to 37.6 weeks gestation, for which ultrasound images an axial section fetal thorax (figure 1) were obtained. Images collected and stored DICOM format analysed with QuantusFLM®. We included 98 (20 MC 78 DC). A total 306 classified three groups gestational ages (table 1). The mean age birthweight was 37.1 (1.4); 2,435 (345)g 1 2,363 (440)g 2. There is...
Abstract Objective: To evaluate the concordance of risk neonatal respiratory morbidity (NRM) assessed by quantitative ultrasound lung texture analysis (QuantusFLM®) in fetuses twin pregnancies. Methods : Prospective study conducted Fetal images were obtained at 26.0–38.6 weeks gestation. Categorical (high or low) and continuous results NRM compared between twins. Results from 131 pairs twins included. The classified into three gestational age ranges: Group 1: 26.0 to 29.6 (29.8%); 2: 30.0...
Abstract Objectives To propose a tool to detect and locate malignant nodules microcalcifications in mammography judge its potential as screening tool. Methods In this institutional review board approved retrospective study we presented new based on deep learning techniques predict lesions mammograms, called quantusMM. 3,114 mammograms from 976 patients were collected Onkologikoa (Instituto Oncológico de Kutxa) databases for purpose: 1,248 images with nodules, 736 1,131 without any suspicious...