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

Search research articles

Related Experiment Video

Updated: May 25, 2026

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

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

Published on: May 19, 2023

Probabilistic lung nodule classification with belief decision trees.

Dmitriy Zinovev¹, Jonathan Feigenbaum, Jacob Furst

¹DePaul University, Chicago, IL 60604, USA. dzinovev@cdm.depaul.edu

Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual International Conference

|January 19, 2012

Summary

This summary is machine-generated.

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

Comparing ME/CFS following mononucleosis with Long COVID.

Chronic illness·2026

Same author

Outcomes of ME/CFS following infectious mononucleosis: seven-year follow-up of a prospective study.

Frontiers in medicine·2026

Same author

Identifying post-exertional malaise subtypes: Differentiating physical and mental PEM manifestations.

Journal of health psychology·2026

Same author

Dmcie: Diffusion model with concatenation of inputs and errors for enhanced brain tumor segmentation in MRI images.

International journal of computer assisted radiology and surgery·2025

Same author

Harnessing Generative AI for Lung Nodule Spiculation Characterization.

Journal of imaging informatics in medicine·2025

Same author

The Implications and Predictability of Sleep Reversal for People with Myalgic Encephalomyelitis/Chronic Fatigue Syndrome: A Machine Learning Approach.

Healthcare (Basel, Switzerland)·2025

This study introduces a multiple-label classification method to predict radiologist opinions on lung nodules in CT scans. The approach achieved 69% performance, offering a valuable tool for Computer-Aided Diagnostic Characterization (CADc).

Area of Science:

Radiology
Medical Imaging
Artificial Intelligence in Medicine

Background:

Radiologists interpret complex semantic characteristics of lung nodules on Computed Tomography (CT) scans.
Computer-Aided Diagnostic Characterization (CADc) systems aim to assist radiologists by predicting these semantic features.
Accurate characterization of lung nodules is crucial for early cancer detection and patient management.

Purpose of the Study:

To propose and evaluate a multiple-label classification algorithm for predicting the distribution of radiologist opinions on lung nodules.
To assess the performance of belief decision trees in modeling inter-reader variability in lung nodule characterization.
To establish a computational method for Computer-Aided Diagnostic Characterization (CADc) that reflects expert consensus.

Main Methods:

More Related Videos

Three-Dimensional Reconstruction for the Whole Lung with Early Multiple Pulmonary Nodules

Three-Dimensional Reconstruction for the Whole Lung with Early Multiple Pulmonary Nodules

Published on: October 13, 2023

Use of Electromagnetic Navigational Transthoracic Needle Aspiration (E-TTNA) for Sampling of Lung Nodules

Use of Electromagnetic Navigational Transthoracic Needle Aspiration (E-TTNA) for Sampling of Lung Nodules

Published on: May 23, 2015

Related Experiment Videos

Last Updated: May 25, 2026

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

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

Published on: May 19, 2023

Three-Dimensional Reconstruction for the Whole Lung with Early Multiple Pulmonary Nodules

Three-Dimensional Reconstruction for the Whole Lung with Early Multiple Pulmonary Nodules

Published on: October 13, 2023

Use of Electromagnetic Navigational Transthoracic Needle Aspiration (E-TTNA) for Sampling of Lung Nodules

Use of Electromagnetic Navigational Transthoracic Needle Aspiration (E-TTNA) for Sampling of Lung Nodules

Published on: May 23, 2015

Utilized the National Cancer Institute (NCI) Lung Image Database Consortium (LIDC) dataset, containing semantic annotations from up to four radiologists for 914 lung nodules.
Developed a multiple-label classification algorithm based on belief decision trees to predict the distribution of semantic characteristics.
Evaluated the algorithm's performance using a novel distance-threshold curve technique, measuring the area under the curve (AUC).

Main Results:

The proposed multiple-label classification approach achieved 69% performance on the validation subset.
The belief decision tree model demonstrated effectiveness in predicting the distribution of radiologist opinions.
The distance-threshold curve technique provided a robust method for evaluating multi-label classification performance in this context.

Conclusions:

Multiple-label classification algorithms are suitable for representing the diagnostic consensus of multiple radiologists on lung CT scans.
This approach provides a valuable tool for Computer-Aided Diagnostic Characterization (CADc) when definitive ground truth is unavailable.
The findings support the integration of advanced machine learning techniques to enhance radiologist decision-making in lung nodule analysis.