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

You might also read

Related Articles

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

Sort by
Same author

A New Severity Index for Placental Abruption Predicts Recurrence Risk in Future Pregnancies.

Journal of clinical medicine·2026
Same author

Investigating the anticancer activity of eravacycline in pancreatic cancer via target-based deep learning and experimental validation.

Briefings in bioinformatics·2026
Same author

Vitamin D Supplementation and Treatment-Free Survival in Early-Stage CLL: A Real-World Validation Study.

EJHaem·2026
Same author

Artificial Intelligence-Enabled Serial Electrocardiograms for Prediction of All-Cause Mortality in Secondary Care Settings.

JACC. Advances·2026
Same author

Learning Normal Representations for Blood Biomarkers.

ArXiv·2026
Same author

Effect of cumulative blood pressure exposure on long-term cardiovascular outcomes in the community, a nationwide cohort study.

The American journal of medicine·2026

Related Experiment Video

Updated: Jul 8, 2025

Human Brown Adipose Tissue Depots Automatically Segmented by Positron Emission Tomography/Computed Tomography and Registered Magnetic Resonance Images
09:21

Human Brown Adipose Tissue Depots Automatically Segmented by Positron Emission Tomography/Computed Tomography and Registered Magnetic Resonance Images

Published on: February 18, 2015

12.2K

Improving severity classification of Hebrew PET-CT pathology reports using test-time augmentation.

Seffi Cohen1, Edo Lior1, Moshe Bocher2

  • 1Department of Software and Information Systems Engineering, Ben Gurion University, Beer-Sheva, 8410501, Israel.

Journal of Biomedical Informatics
|December 15, 2023
PubMed
Summary

This study introduces Text Test Time Augmentation (TTTA) to improve cancer severity classification in Hebrew medical reports. TTTA enhances accuracy by augmenting text data, boosting performance by 15.18%.

Keywords:
NLPHPET-CTReports-classificationTTA

More Related Videos

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.8K
Analysis of 18FDG PET/CT Imaging as a Tool for Studying Mycobacterium tuberculosis Infection and Treatment in Non-human Primates
10:04

Analysis of 18FDG PET/CT Imaging as a Tool for Studying Mycobacterium tuberculosis Infection and Treatment in Non-human Primates

Published on: September 5, 2017

18.8K

Related Experiment Videos

Last Updated: Jul 8, 2025

Human Brown Adipose Tissue Depots Automatically Segmented by Positron Emission Tomography/Computed Tomography and Registered Magnetic Resonance Images
09:21

Human Brown Adipose Tissue Depots Automatically Segmented by Positron Emission Tomography/Computed Tomography and Registered Magnetic Resonance Images

Published on: February 18, 2015

12.2K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.8K
Analysis of 18FDG PET/CT Imaging as a Tool for Studying Mycobacterium tuberculosis Infection and Treatment in Non-human Primates
10:04

Analysis of 18FDG PET/CT Imaging as a Tool for Studying Mycobacterium tuberculosis Infection and Treatment in Non-human Primates

Published on: September 5, 2017

18.8K

Area of Science:

  • Medical Informatics
  • Natural Language Processing
  • Computational Linguistics

Background:

  • Classifying Hebrew medical reports is difficult due to linguistic complexity and ambiguity.
  • Accurate cancer severity classification from diagnostic reports is crucial for patient care.

Purpose of the Study:

  • To propose and evaluate Text Test Time Augmentation (TTTA) for improved classification of cancer severity levels in Hebrew PET-CT reports.
  • To enhance the robustness and semantic extraction capabilities of models analyzing morphologically rich medical text.

Main Methods:

  • Developed and applied Text Test Time Augmentation (TTTA) during both training and testing phases.
  • Generated and evaluated text augmentations to improve information retrieval and model understanding of Hebrew medical reports.
  • Utilized a large dataset of manually labeled Hebrew PET-CT reports from Ziv hospital.

Main Results:

  • The TTTA approach significantly outperformed baseline models without augmentation.
  • Achieved a 15.18% improvement in PR-AUC for cancer severity level classification.
  • Demonstrated enhanced extraction of medical concepts and improved classification accuracy.

Conclusions:

  • TTTA is an effective method for analyzing complex Hebrew medical texts, particularly for cancer severity classification.
  • The approach addresses limitations in automated analysis of morphologically rich medical language.
  • TTTA shows potential to aid physicians in cancer diagnosis and treatment planning.