Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Transformers01:26

Transformers

1.1K
A device that transforms voltages from one value to another using induction is called a transformer. A transformer consists of two separate coils, or windings, wrapped around the same soft iron core. However, they are electrically insulated from each other.
The iron core has a substantial relative permeability. Therefore, the magnetic field lines generated due to the current in one winding are almost entirely confined within the core, such that the same magnetic flux permeates each turn of both...
1.1K
Improving Translational Accuracy02:07

Improving Translational Accuracy

9.9K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
9.9K
Positron Emission Tomography01:29

Positron Emission Tomography

4.1K
Positron emission tomography (PET) is a medical imaging technique involving radiopharmaceuticals — substances that emit short-lived radiation. Although the first PET scanner was introduced in 1961, it took 15 more years before radiopharmaceuticals were combined with the technique and revolutionized its potential.
One of the main requirements of a PET scan is a positron-emitting radioisotope, which is produced in a cyclotron and then attached to a substance used by the part of the body...
4.1K
Introduction to Nuclear Reprogramming01:14

Introduction to Nuclear Reprogramming

1.9K
Nuclear reprogramming is the process of switching gene expression of one cell type to that of another cell type, usually from a differentiated cell state to an undifferentiated cell state. Differentiation occurs during processes such as development and morphogenesis, tissue regeneration, and malignancy. Cells can also be artificially induced to reprogram their gene expression by techniques such as nuclear transfer, induced pluripotency, and cell fusion. Such techniques have many applications in...
1.9K
Computed Tomography01:10

Computed Tomography

4.4K
Tomography refers to imaging by sections. Computed tomography (CT) is a non-invasive imaging technique that uses computers to analyze several cross-sectional X-rays to reveal minute details about structures in the body.
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...
4.4K
Reporter Genes02:11

Reporter Genes

11.3K
Reporter genes are a type of protein-coding gene that are often tagged to a gene of interest. Once inside a target cell, reporter genes usually produce visually identifiable characteristics like fluorescence and luminescence when expressed along with the gene of interest. Thus, reporter genes “report” the presence or absence of genes of interest in an organism, determine the gene expression pattern, or track the physical location of a DNA segment or protein in the cell.
11.3K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Vasculopathy as a mechanical barrier to cancer spread: Clinical evidence and a rheology-based model in lung cancer and other solid tumors.

Translational oncology·2026
Same author

A multimodal EHR-based phenotyping framework integrating consensus clustering and transformer-based clinical NLP: application to autoimmune gastritis.

International journal of medical informatics·2026
Same author

ViTMARE - A Vision Transformer Pipeline for Anomaly Detection in 3D Brain MRI.

Studies in health technology and informatics·2026
Same author

Extraction of Endoscopic Markers from Clinical Notes in Italian Patients with Autoimmune Atrophic Gastritis Using Small Language Models.

Studies in health technology and informatics·2026
Same author

Ontology-Enriched Guidelines Retrieval for Complex Rheumatological Cases.

Studies in health technology and informatics·2026
Same author

Redesigning Python Programming Course in the Generative AI Era: An Italian Case Study.

Studies in health technology and informatics·2026

Related Experiment Video

Updated: Jun 22, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

543

Reshaping free-text radiology notes into structured reports with generative question answering transformers.

Laura Bergomi1, Tommaso M Buonocore1, Paolo Antonazzo2

  • 1Department of Electrical, Computer and Biomedical Engineering, University of Pavia, Pavia, Italy.

Artificial Intelligence in Medicine
|July 4, 2024
PubMed
Summary

This study introduces an AI pipeline using IT5 to automatically fill structured radiology reporting registries from Italian free-text reports. The system effectively extracts diverse data types, matching human expert performance for free-text information.

Keywords:
Biomedical information extractionClinical textGenerative artificial intelligenceLymphomaNatural language processingRadiology

More Related Videos

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts
07:50

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

Published on: September 20, 2018

15.9K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.2K

Related Experiment Videos

Last Updated: Jun 22, 2025

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

543
A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts
07:50

A Metadata Extraction Approach for Clinical Case Reports to Enable Advanced Understanding of Biomedical Concepts

Published on: September 20, 2018

15.9K
Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma
04:09

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

8.2K

Area of Science:

  • Artificial Intelligence
  • Natural Language Processing
  • Medical Informatics

Background:

  • Free-text radiology reports hinder clinical data extraction and utilization.
  • Structured reporting (SR) is recommended for standardization, completeness, and improved information retrieval.
  • Developing automated methods for SR registry completion is crucial for efficient clinical workflows.

Purpose of the Study:

  • To propose and evaluate an AI pipeline for extracting information from Italian free-text radiology reports.
  • To automatically populate a structured reporting registry for CT staging of lymphoma patients.
  • To leverage Natural Language Processing (NLP) and Transformer-based models for this task.

Main Methods:

  • Utilized the Italian-specific T5 model (IT5) for a rule-free generative Question Answering approach.
  • Processed 174 Italian radiology reports, focusing on categorical, free-text, and numerical data extraction.
  • Implemented batch-truncation and ex-post combination strategies to handle model context length limitations.
  • Evaluated performance using accuracy, F1 score, format accuracy, and human expert feedback for free-text answers.

Main Results:

  • The IT5 ex-post combination model achieved notable results in information extraction, performing comparably to GPT-3.5.
  • Human assessment of free-text answers showed a high correlation with AI performance metrics (F1 score).
  • GPT-3.5 generated more human-like statements but sometimes provided answers inappropriately.

Conclusions:

  • A fine-tuned Transformer model (IT5) with moderate parameters is effective for clinical information extraction in automated SR registry filling.
  • The system accurately extracts and formats data, approximating human expert performance for free-text items.
  • The model demonstrates the ability to discern when information is relevant or not, enhancing its clinical utility.