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

lncRNA - Long Non-coding RNAs02:39

lncRNA - Long Non-coding RNAs

10.1K
In humans, more than 80% of the genome gets transcribed. However, only around 2% of the genome codes for proteins. The remaining part produces non-coding RNAs which includes ribosomal RNAs, transfer RNAs, telomerase RNAs, and regulatory RNAs, among other types. A large number of regulatory non-coding RNAs have been classified into two groups depending upon their length – small non-coding RNAs, such as microRNA, which are less than 200 nucleotides in length, and long non-coding RNA...
10.1K

You might also read

Related Articles

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

Sort by
Same journal

Fairness-aware deep learning for predicting visual field loss from optical coherence tomography.

Journal of medical imaging (Bellingham, Wash.)·2026
Same journal

Image class translation: visual inspection of class-specific hypotheticals and classification based on translation distance.

Journal of medical imaging (Bellingham, Wash.)·2026
Same journal

Comparison of chest X-ray radiography AI model to comorbidities for predicting intensive care unit admission for COVID-19.

Journal of medical imaging (Bellingham, Wash.)·2026
Same journal

Literature Reviews After AI.

Journal of medical imaging (Bellingham, Wash.)·2026
Same journal

Illustration of transfer learning from breast cancer detection to risk prediction: adaptation to local data and local objectives.

Journal of medical imaging (Bellingham, Wash.)·2026
Same journal

RadGazeGen: radiomics and gaze-guided chest X-ray generation using diffusion models.

Journal of medical imaging (Bellingham, Wash.)·2026

Related Experiment Video

Updated: Mar 9, 2026

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
10:26

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Published on: May 19, 2023

2.6K

Lung nodule malignancy classification using only radiologist-quantified image features as inputs to statistical

Matthew C Hancock1, Jerry F Magnan1

  • 1Florida State University , Department of Mathematics, 208 Love Building, 1017 Academic Way, Tallahassee, Florida 32306-4510, United States.

Journal of Medical Imaging (Bellingham, Wash.)
|December 20, 2016
PubMed
Summary

Quantifying diagnostic image features from lung CT scans aids in classifying nodule malignancy. This study shows quantified features, including diameter and volume, achieve high accuracy comparable to algorithmic methods.

Keywords:
Lung Image Database Consortium datasetcomputer-aided diagnosislogistic regressionlung nodule classificationmachine learningrandom forests

More Related Videos

Multifractal Spectrum Analysis for Assessing Pulmonary Nodule Malignancy
05:24

Multifractal Spectrum Analysis for Assessing Pulmonary Nodule Malignancy

Published on: January 10, 2025

971
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

Related Experiment Videos

Last Updated: Mar 9, 2026

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules
10:26

Author Spotlight: A 3D Digital Model for the Diagnosis and Treatment of Pulmonary Nodules

Published on: May 19, 2023

2.6K
Multifractal Spectrum Analysis for Assessing Pulmonary Nodule Malignancy
05:24

Multifractal Spectrum Analysis for Assessing Pulmonary Nodule Malignancy

Published on: January 10, 2025

971
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

Area of Science:

  • Radiology and Medical Imaging
  • Computational Pathology
  • Artificial Intelligence in Medicine

Background:

  • Lung nodule assessment in CT scans relies on diagnostically relevant image features.
  • Many features are qualitatively defined, posing challenges for direct quantification.
  • Quantification of these features is crucial for developing computer-aided diagnosis (CAD) systems.

Purpose of the Study:

  • To evaluate the predictive capability of quantified diagnostic image features for classifying lung nodule malignancy using statistical learning.
  • To determine the usefulness of these quantified features as inputs for a CAD system.

Main Methods:

  • Utilized the Lung Image Database Consortium dataset.
  • Employed radiologist-assigned diagnostic feature values and derived estimates of nodule diameter and volume.
  • Calculated theoretical upper bounds for classification accuracy and assessed performance of statistical learning models.

Main Results:

  • Achieved a classification accuracy of 85.74% using only radiologist-assigned features, close to the theoretical maximum of 90.17%.
  • Incorporating diameter and volume features improved accuracy to 88.08% with an Area Under the Curve (AUC) of 0.949.
  • Spiculation, lobulation, subtlety, and calcification were identified as the most predictive features.

Conclusions:

  • Quantified diagnostic image features alone are competitive for classifying lung nodule malignancy.
  • This approach supports the development of effective CAD systems for lung nodule diagnosis.
  • The findings highlight the importance of specific qualitative features when quantified.