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

AI for Radiology: A Primer Part II. Interacting with AI Results.

Radiology·2026
Same author

Bridging Parallel Disciplines: An Integrated Workshop for Clinical and Imaging Informatics Training.

Journal of imaging informatics in medicine·2026
Same author

Non-interruptive decision support to increase appropriate screening for primary hyperparathyroidism.

American journal of surgery·2026
Same author

From detection to diagnosis: Early outcomes of a specialized adrenal nodule clinic.

Surgery·2026
Same author

ACR's Assess-AI: A Registry for Real-World Performance Monitoring of Clinical Imaging Artificial Intelligence.

Journal of the American College of Radiology : JACR·2026
Same author

Climate Change and Globally Sustainable Cardiovascular Magnetic Resonance.

Magnetic resonance imaging clinics of North America·2026

Related Experiment Video

Updated: Feb 19, 2026

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

8.9K

Integrating Natural Language Processing and Machine Learning Algorithms to Categorize Oncologic Response in Radiology

Po-Hao Chen1,2, Hanna Zafar3, Maya Galperin-Aizenberg3

  • 1Department of Radiology, Perelman School of Medicine, Hospital of the University of Pennsylvania, 3400 Spruce Street, Philadelphia, PA, 19104, USA. po-hao.chen@uphs.upenn.edu.

Journal of Digital Imaging
|October 29, 2017
PubMed
Summary

This study explored natural language processing (NLP) and machine learning (ML) for extracting cancer insights from radiology reports. Combining TF-IDF with support vector machines (SVM) achieved the highest accuracy, demonstrating the power of optimized NLP and ML integration.

Keywords:
InformaticsMachine learningNatural language processingStructured reporting

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

7.6K
Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:33

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

1.2K

Related Experiment Videos

Last Updated: Feb 19, 2026

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

8.9K
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

7.6K
Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System
05:33

Introduction of an Integrated Pathology Image Management, Artificial Intelligence, and Reporting System

Published on: July 11, 2025

1.2K

Area of Science:

  • Medical informatics
  • Computational linguistics
  • Radiology

Background:

  • A large amount of medical data is unstructured, limiting its utility.
  • Natural language processing (NLP) and machine learning (ML) can extract insights from unstructured radiology reports.
  • The combined impact of NLP and ML techniques in this domain requires further investigation.

Purpose of the Study:

  • To investigate the codependent effects of various NLP and ML techniques on extracting cancer information from radiology reports.
  • To compare the performance of different NLP and ML algorithm combinations for predicting cancer status (Progression, Stable Disease, Improvement, No Cancer).

Main Methods:

  • Utilized a dataset of 9418 cross-sectional abdomen/pelvis CT and MR examinations from April 2015 to November 2016.
  • Employed three NLP techniques: term frequency-inverse document frequency (TF-IDF), term frequency weighting (TF), and 16-bit feature hashing.
  • Combined NLP techniques with five ML algorithms: logistic regression (LR), random decision forest (RDF), support vector machine (SVM), Bayes point machine (BPM), and fully connected neural network (NN).

Main Results:

  • The best-performing NLP model used tokenized unigrams and bigrams with TF-IDF.
  • Increasing N-gram length provided minimal benefit for most ML algorithms.
  • The support vector machine (SVM) algorithm achieved the highest performance, with 90.6% average accuracy and an F-score of 0.813 on the test dataset.

Conclusions:

  • The interplay between NLP and ML algorithms significantly impacts interpretation accuracy in analyzing radiology reports.
  • Concurrent optimization of both NLP and ML algorithms is crucial for achieving optimal predictive accuracy.
  • This study highlights the potential of integrated NLP and ML approaches for structured data extraction in radiology.