Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Metastasis

Metastasis

Metastasis is the spread of cancer cells from the original site to distant locations in the body. Cancer cells can spread via blood vessels (hematogenous) as well as lymph vessels in the body.
Epithelial-to-Mesenchymal Transition
The epithelial-to-mesenchymal transition or EMT is a developmental process commonly observed in wound healing, embryogenesis, and cancer metastasis. EMT is induced by transforming growth factor-beta (TGF-β) or receptor tyrosine kinase (RTK) ligands, which further...

You might also read

Related Articles

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

Sort by

Same author

Improving preoperative risk stratification in colorectal liver metastases: a multi-institutional evaluation of multimodal prediction models.

Scientific reports·2026

Same author

3D and 4D Free-Breathing Abdominal T1-Weighted MRI in Clinical Practice Using Deep Learning Auto-Navigation and Reconstruction.

Magnetic resonance in medicine·2026

Same author

Molecular and Clinical Determinants of Targeted Therapy Treatment in Biliary Tract Cancer.

Clinical cancer research : an official journal of the American Association for Cancer Research·2026

Same author

Radiomic Carotid Plaque Features Integrated into Machine Learning Models for Cardiovascular Risk Prediction.

Ultrasound in medicine & biology·2026

Same author

Towards quality control and harmonization of deep learning CT radiomics: An in-silico feasibility study with virtual colorectal liver metastases.

Medical physics·2026

Same author

Pembrolizumab and olaparib in homologous-recombination-deficient metastatic pancreatic cancer: the phase 2 POLAR trial.

Nature medicine·2026

Search research articles

Related Experiment Video

Updated: Jul 12, 2025

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

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

Published on: August 16, 2020

Applying Natural Language Processing to Single-Report Prediction of Metastatic Disease Response Using the OR-RADS

Lydia Elbatarny¹, Richard K G Do², Natalie Gangai²

¹School of Computing, Queen's University, Kingston, ON K7L 2N8, Canada.

|October 28, 2023

Summary

This study shows that a Natural Language Processing (NLP) model using the standardized Oncologic Response-Radiology Reporting and Data System (OR-RADS) lexicon can accurately predict cancer treatment response from radiological reports, exceeding human performance.

Keywords:

computed tomography disease progression metastasis natural language processing radiology

More Related Videos

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

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

Published on: October 13, 2023

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

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

Published on: December 6, 2024

Related Experiment Videos

Last Updated: Jul 12, 2025

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

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

Published on: August 16, 2020

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

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

Published on: October 13, 2023

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

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

Published on: December 6, 2024

Area of Science:

Oncology
Radiology
Natural Language Processing
Artificial Intelligence

Background:

Standardized reporting of cancer treatment response in radiological reports is crucial for collecting Real-World Evidence (RWE).
Current lack of standardization hinders large-scale interpretation of disease response and personalized treatment development.

Purpose of the Study:

To evaluate the utility of Natural Language Processing (NLP) for large-scale interpretation of disease response using a standardized oncologic response lexicon (OR-RADS).
To assess the performance of a Bidirectional Encoder Representations from Transformers (BERT) model in classifying cancer treatment response based on radiological reports.

Main Methods:

Radiologists annotated 3503 radiological reports with one of seven OR-RADS categories.
A BERT model was trained on the annotated dataset for multiclass and single-class classification of disease response.
Human performance was compared against the BERT model's performance.

Main Results:

The BERT model achieved high accuracies (95-99%) across all classification tasks, outperforming human performance (74-93%).
The model demonstrated superior performance in single-class tasks compared to multiclass tasks.
Misclassifications by the model were minimal, primarily involving overprediction of equivocal and mixed response categories.

Conclusions:

The BERT NLP model is feasible for predicting cancer patient disease response from radiological reports, demonstrating performance superior to human readers.
Adoption of the standardized OR-RADS lexicon can enhance the accuracy of large-scale RWE collection for cancer treatment effectiveness.