Jove
Visualize
Contáctanos
JoVE
x logofacebook logolinkedin logoyoutube logo
ACERCA DE JoVE
Visión GeneralLiderazgoBlogCentro de Ayuda JoVE
AUTORES
Proceso de PublicaciónConsejo EditorialAlcance y PolíticasRevisión por ParesPreguntas FrecuentesEnviar
BIBLIOTECARIOS
TestimoniosSuscripcionesAccesoRecursosConsejo Asesor de BibliotecasPreguntas Frecuentes
INVESTIGACIÓN
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchivo
EDUCACIÓN
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualCentro de Recursos para ProfesoresSitio de Profesores
Términos y Condiciones de Uso
Política de Privacidad
Políticas

Videos de Conceptos Relacionados

Data Reporting and Recording01:24

Data Reporting and Recording

5.4K
Reporting and recording are crucial in data documentation. The timely, thorough, and accurate documentation of facts is essential when recording patient data. Failure to record findings during an assessment or interpretation of a problem will result in loss of information and make the patient document unreliable. The reader is left with general impressions if the information is not specific. A recording is documenting data of the individual's health information in a traceable, secure, and...
5.4K
Bacterial Transformation01:33

Bacterial Transformation

59.5K
In 1928, bacteriologist Frederick Griffith worked on a vaccine for pneumonia, which is caused by Streptococcus pneumoniae bacteria. Griffith studied two pneumonia strains in mice: one pathogenic and one non-pathogenic. Only the pathogenic strain killed host mice.
Griffith made an unexpected discovery when he killed the pathogenic strain and mixed its remains with the live, non-pathogenic strain. Not only did the mixture kill host mice, but it also contained living pathogenic bacteria that...
59.5K
Model Approaches for Pharmacokinetic Data: Physiological Models01:15

Model Approaches for Pharmacokinetic Data: Physiological Models

259
Physiological models in pharmacokinetics are instrumental in understanding the distribution and elimination of drugs within the body. These models describe the drug concentration within target organs, influenced by factors such as drug uptake, tissue volume, and blood flow. Drug uptake is governed by the partition coefficient, which signifies the drug concentration ratio in tissue to that in the blood. The blood flow rate to a specific tissue is expressed as Qt, and the rate of change in tissue...
259
Model Approaches for Pharmacokinetic Data: Compartment Models01:14

Model Approaches for Pharmacokinetic Data: Compartment Models

545
Compartmental analysis is a widely adopted approach to characterizing drug pharmacokinetics. It uses compartment models that conceptualize the body as a collection of reversibly communicating compartments, each representing a group of tissues exhibiting similar drug distribution characteristics. The movement rate of the drug between these compartments is typically described by first-order kinetics.
Two primary types of compartment models are recognized: mammillary and catenary. The more...
545
Model Approaches for Pharmacokinetic Data: Distributed Parameter Models01:06

Model Approaches for Pharmacokinetic Data: Distributed Parameter Models

247
Pharmacokinetic models are mathematical constructs that represent and predict the time course of drug concentrations in the body, providing meaningful pharmacokinetic parameters. These models are categorized into compartment, physiological, and distributed parameter models.
The distributed parameter models are specifically designed to account for variations and differences in some drug classes. This model is particularly useful for assessing regional concentrations of anticancer or...
247
Transformation01:26

Transformation

808
Microbial communities are dynamic environments where cell lysis releases free DNA into the surroundings. Other cells can take up this extracellular DNA through a process known as transformation.When a cell incorporates this foreign DNA into its genome, resulting in genetic modification, the process is known as transformation. Cells capable of this process are termed competent. Competence can be natural, as observed in certain bacteria and archaea, or artificially induced in the...
808

También podría leer

Artículos Relacionados

Artículos vinculados a este trabajo por autores compartidos, revista y gráfico de citas.

Ordenar por
Same author

Tree ring segmentation performance in highly disturbed trees using deep learning.

PloS one·2026
Same author

Comparison of different criteria for rheumatic heart disease screening: an empirical study in Sierra Leone.

BMC cardiovascular disorders·2026
Same author

Artificial intelligence-predicted ECG age gap as a biomarker: bias-adjusted correlation with mortality and cardiovascular risk factors.

European heart journal. Digital health·2026
Same author

Why Do Radiologists Disown Breast Thermography? A Critical Review of Recent Studies and Recommendations.

Cancers·2025
Same author

Breast thermography: a systematic review and meta-analysis.

Systematic reviews·2024
Same author

Deep Learning for Describing Breast Ultrasound Images with BI-RADS Terms.

Journal of imaging informatics in medicine·2024

Video Experimental Relacionado

Updated: Jan 27, 2026

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.3K

Extracción de datos estructurados de informes de imágenes mamarias no estructurados con modelos basados en

Mikel Carrilero-Mardones1, Jorge Pérez-Martín1, Francisco Javier Díez1

  • 1Department of Artificial Intelligence, Universidad Nacional de Educacion a Distancia (UNED), Madrid, Spain.

Frontiers in digital health
|January 26, 2026
PubMed
Resumen
Este resumen es generado por máquina.

Los modelos de lenguaje generativos, como BioGPT, destacan en la conversión de informes de imágenes mamarias no estructurados en datos estructurados. Esta automatización mejora la curación de datos clínicos y la integración de la investigación.

Palabras clave:
modelos BERTBI-RADScáncer de mamaimágenes mamariasclasificaciónrespuesta a preguntas extractivasmodelos generativosinformes estructurados

Más Videos Relacionados

Studying Triple Negative Breast Cancer Using Orthotopic Breast Cancer Model
09:29

Studying Triple Negative Breast Cancer Using Orthotopic Breast Cancer Model

Published on: March 20, 2020

18.8K
Neutron Crystallography Data Collection and Processing for Modelling Hydrogen Atoms in Protein Structures
10:10

Neutron Crystallography Data Collection and Processing for Modelling Hydrogen Atoms in Protein Structures

Published on: December 1, 2020

5.6K

Videos de Experimentos Relacionados

Last Updated: Jan 27, 2026

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images
04:23

A Swin Transformer-Based Model for Thyroid Nodule Detection in Ultrasound Images

Published on: April 21, 2023

2.3K
Studying Triple Negative Breast Cancer Using Orthotopic Breast Cancer Model
09:29

Studying Triple Negative Breast Cancer Using Orthotopic Breast Cancer Model

Published on: March 20, 2020

18.8K
Neutron Crystallography Data Collection and Processing for Modelling Hydrogen Atoms in Protein Structures
10:10

Neutron Crystallography Data Collection and Processing for Modelling Hydrogen Atoms in Protein Structures

Published on: December 1, 2020

5.6K

Área de la Ciencia:

  • Procesamiento del Lenguaje Natural
  • Informática Médica
  • Inteligencia Artificial

Sus antecedentes:

  • Los datos clínicos a menudo son texto libre no estructurado, lo que dificulta la investigación y la toma de decisiones.
  • Los datos clínicos estructurados son cruciales para la investigación y la toma de decisiones informadas.
  • Este estudio aborda el desafío de convertir informes de imágenes mamarias no estructurados en datos estructurados.

Objetivo del estudio:

  • Comparar el rendimiento de los modelos de lenguaje generativos y basados en BERT en la estructuración de informes de imágenes mamarias.
  • Evaluar modelos para la conversión de texto no estructurado en datos tabulares para uso clínico y de investigación.
  • Evaluar la eficacia del procesamiento del lenguaje natural en la extracción de datos médicos.

Principales métodos:

  • Se evaluaron cinco modelos basados en transformadores (BlueBERT, BioBERT, BioMedBERT, BioGPT, ClinicalT5) en 286 informes de imágenes mamarias en español traducidos al inglés.
  • Se empleó la clasificación para 19 variables categóricas y la respuesta a preguntas extractivas para 4 entidades.
  • Se probaron varias estrategias de ajuste fino y configuraciones de entrada, utilizando la precisión y las puntuaciones F1 macro para la evaluación.

Principales resultados:

  • BioGPT logró el más alto rendimiento en clasificación (96,10% de precisión, 90,30% de puntuación F1), superando a los modelos basados en BERT.
  • BioGPT mostró un sólido rendimiento en la respuesta a preguntas extractivas (93,24% de precisión), comparable a otros modelos de primer nivel.
  • BioGPT ofreció de forma exclusiva capacidades simultáneas de clasificación y respuesta a preguntas.

Conclusiones:

  • Los modelos generativos, especialmente BioGPT, proporcionan una solución escalable para automatizar la extracción de información estructurada de los informes de imágenes mamarias.
  • El rendimiento superior y la capacidad multitarea de BioGPT pueden reducir significativamente los esfuerzos manuales de curación de datos.
  • Los hallazgos respaldan la integración eficiente de datos de imágenes en flujos de trabajo de investigación y clínicos utilizando PNL avanzada.