Abstract: A method is disclosed for obtaining an image biomarker that quantifies the quality of the trabecular structure of bones. The method includes: retrieving high-resolution CT (Computed Tomography) and/or MRI (Magnetic Resonance Imaging) trabecular images from an image database; pre-processing and post-processing the high-resolution CT and/or MRI trabecular images and obtaining the unique image biomarker “QTS”. Pre-processing may include: calculating the region of interest “ROI”; calculating the bone fraction map; eliminating the partial volume effect; and, binarizing. Post-processing may include: skeletonisation and extraction of morphological and structural characteristics. Lastly, the unique image biomarker “QTS” is defined as: QTS=0.7137*Comp1+0.2863*Comp2.
Type:
Grant
Filed:
January 17, 2020
Date of Patent:
February 27, 2024
Assignees:
Fundación para la Investigación del Hospital Universitario La Fe de la Comunidad Valenciana, QUIBIM, S.L., UNIVERSIDAD DE ZARAGOZA
Inventors:
Angel Alberich Bayarri, Fabio García Castro, Amadeo Ten Esteve, Luis Martí Bonmatí, María Ángeles Pérez Ansón
Abstract: The present invention relates to a method and a system for identifying an anomaly in a chest X-ray image in posteroanterior orientation based on neural networks, which comprises: receiving the image in a classification module with a plurality of convolutional neural networks, each trained to identify at least one specific graphic pattern associated with a pathology; obtaining, for each of the convolutional neural networks, a probability of detecting the specific graphic pattern; receiving in a fully connected neural network all the probabilities obtained; and determining whether the chest X-ray image contains an anomaly, based on the detection probabilities provided.
Type:
Application
Filed:
January 30, 2020
Publication date:
November 17, 2022
Applicant:
QUIBIM, S.L.
Inventors:
Rafael LÓPEZ GONZÁLEZ, Belén FOS GUARINOS, Fabio GARCIA CASTRO, Ana Maria JIMÉNEZ PASTOR, Angel ALBERICH BAYARRI, LLuis MARIT BONMATI
Abstract: The present invention relates to a method and a system for the segmentation of white matter hyperintensities (WMHs) present in magnetic resonance brain images, comprising: providing an array of trained convolutional neural networks (CNNs) with a magnetic resonance brain image; determining, for each of the CNNs and for each voxel, the probability that the given voxel corresponds to a pathological hyperintensity; calculating the average of all the probabilities determined for each voxel; comparing the averaged probabilities for each voxel with a threshold; generating an image mask with the voxels that exceed the threshold.
Type:
Application
Filed:
January 30, 2020
Publication date:
October 27, 2022
Applicant:
QUIBIM, S.L.
Inventors:
Ana María JIMÉNEZ PASTOR, Eduardo CAMACHO RAMOS, Fabio GARCÍA CASTRO, Ángel ALBERICH BAYARRI, Josep PUIG ALCÁNTARA, Carles BIARNES DURÁN, Luis MARTÍ BONMATÍ, Salvador PEDRAZA GUTIÉRREZ