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

Imaging Studies for Cardiovascular System V: CT01:28

Imaging Studies for Cardiovascular System V: CT

42
Cardiac computed tomography (CT) scanning is an advanced cardiac imaging technique that utilizes CT technology, with or without intravenous (IV) contrast, to produce accurate cross-sectional virtual slices of specific areas of the heart, coronary circulation, and major blood vessels such as the aorta, pulmonary veins, and arteries. The computer processes these slices to generate three-dimensional images. Multidetector CT (MDCT) is a rapid form of CT scanning that captures multiple slices...
42
Computed Tomography01:10

Computed Tomography

4.6K
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...
4.6K

You might also read

Related Articles

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

Sort by
Same author

Request and reporting models for computed tomography in the multidisciplinary management of cancer patients: consensus between the Italian Society of Medical and Interventional Radiology (SIRM) and the Italian Society of Medical Oncology (AIOM).

La Radiologia medica·2026
Same author

Tracking interstitial lung disease in systemic sclerosis: integrating lung magnetic resonance imaging into a clinically oriented multimodal follow-up strategy.

Clinical and experimental rheumatology·2026
Same author

MRI-Based Radiomics to Predict Response to Neoadjuvant Therapy in Locally Advanced Rectal Cancer: A Retrospective Study.

Journal of personalized medicine·2026
Same author

Lymphoid interstitial pneumonia in Sjögren disease: clinical course and comparison with other ILD patterns.

Rheumatology (Oxford, England)·2026
Same author

Radiogenomics in Lymphoma and Multiple Myeloma: A Systematic Review of Current Evidence and Future Directions.

Journal of clinical medicine·2026
Same author

Cardiac magnetic resonance in patients with acute myocardial infarction: The added clinical value.

Vascular pharmacology·2026

Related Experiment Video

Updated: Jul 19, 2025

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

Natural language processing to convert unstructured COVID-19 chest-CT reports into structured reports.

Salvatore Claudio Fanni1, Chiara Romei2, Giovanni Ferrando3

  • 1Department of Translational Research, Academic Radiology, University of Pisa, Pisa, Italy.

European Journal of Radiology Open
|August 14, 2023
PubMed
Summary

A deep learning model automatically converts unstructured COVID-19 CT reports into structured data, improving accuracy and enabling data mining. This overcomes limitations of traditional structured reporting for radiologists.

Keywords:
Artificial intelligenceCOVID-19Deep learningNatural language processingStructured reporting

More Related Videos

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
08:05

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

14.2K
A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports
07:35

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

Published on: October 13, 2023

1.7K

Related Experiment Videos

Last Updated: Jul 19, 2025

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
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
08:05

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

14.2K
A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports
07:35

A Knowledge Graph Approach to Elucidate the Role of Organellar Pathways in Disease via Biomedical Reports

Published on: October 13, 2023

1.7K

Area of Science:

  • Radiology
  • Artificial Intelligence
  • Natural Language Processing

Background:

  • Structured reporting enhances completeness and reduces errors in radiological reports, facilitating data mining.
  • Radiologists perceive structured reporting as restrictive, limiting expressive freedom.

Purpose of the Study:

  • To develop a deep learning-based natural language processing method for automatic conversion of unstructured COVID-19 chest CT reports into structured reports.
  • To overcome the limitations of traditional structured reporting.

Main Methods:

  • A convolutional neural network was trained on 202 COVID-19 chest CT reports, using radiologist-generated structured reports as ground truth.
  • The model extracted 62 categorical variables, with performance evaluated using mean accuracy and F1 score across two iterations (with and without fine-tuning).
  • Error analysis identified sources of incorrect model processing.

Main Results:

  • The model achieved 93.7% mean accuracy and 93.8% F1 score in the first iteration, with 46% of errors due to wrong inference.
  • After fine-tuning, performance improved to 95.8% for both metrics, and inference errors decreased to 26%.

Conclusions:

  • A convolutional neural network effectively automates the conversion of free-form radiological text into structured reports.
  • This approach overcomes structured reporting limitations and facilitates radiological data mining.