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

Radiological Investigation III: Pulmonary Angiogram and PET Scan01:13

Radiological Investigation III: Pulmonary Angiogram and PET Scan

178
Radiological investigations are paramount in the diagnosis and management of various pulmonary diseases. Two essential investigations are the Pulmonary Angiogram and the Positron Emission Tomography (PET) Scan.
Pulmonary Angiogram
A Pulmonary Angiogram is an invasive procedure involving injecting a contrast medium through a catheter threaded into the pulmonary artery or the right side of the heart to visualize the pulmonary vasculature. Computed Tomography (CT) scans have mainly replaced this...
178

You might also read

Related Articles

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

Sort by
Same author

A New Classification System for Postinterventional Cerebral Hyperdensity: The Influence on Hemorrhagic Transformation and Clinical Prognosis in Acute Stroke.

Neural plasticity·2021
See all related articles

Related Experiment Video

Updated: Sep 25, 2025

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

2.1K

Classification and Segmentation Algorithm in Benign and Malignant Pulmonary Nodules under Different CT

Zhiqian Lu1, Feixiang Long1, Xiaodong He2

  • 1Department of Radiology, The People's Hospital of Xuancheng City, Anhui 242000, China.

Computational and Mathematical Methods in Medicine
|May 2, 2022
PubMed
Summary

Deep neural networks and 3D convolutional neural networks effectively classify and segment pulmonary nodules across various CT reconstruction types. This approach shows high accuracy in distinguishing benign from malignant nodules, regardless of reconstruction method.

More Related Videos

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
07:53

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Published on: October 13, 2023

1.6K
Multifractal Spectrum Analysis for Assessing Pulmonary Nodule Malignancy
05:24

Multifractal Spectrum Analysis for Assessing Pulmonary Nodule Malignancy

Published on: January 10, 2025

518

Related Experiment Videos

Last Updated: Sep 25, 2025

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

2.1K
Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer
07:53

Author Spotlight: Advancing 3D Modeling for Enhanced Diagnosis and Treatment of Pulmonary Nodules in Early-Stage Lung Cancer

Published on: October 13, 2023

1.6K
Multifractal Spectrum Analysis for Assessing Pulmonary Nodule Malignancy
05:24

Multifractal Spectrum Analysis for Assessing Pulmonary Nodule Malignancy

Published on: January 10, 2025

518

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Radiology
  • Pulmonary Nodule Analysis

Background:

  • Accurate characterization of pulmonary nodules is crucial for diagnosing lung diseases.
  • Different computed tomography (CT) reconstruction algorithms can influence nodule appearance and detection.
  • Advanced computational methods are being explored to improve diagnostic accuracy in radiology.

Purpose of the Study:

  • To evaluate the efficacy of a deep neural network (DNN) combined with a 3D convolutional neural network (CNN) for classifying and segmenting pulmonary nodules.
  • To compare the performance of this AI model across three different CT reconstruction algorithms: lung window, mediastinum window, and bone window.
  • To determine if CT reconstruction methods significantly impact the diagnostic accuracy of the AI model in differentiating benign from malignant pulmonary nodules.

Main Methods:

  • Retrospective analysis of chest CT plain scan data from 55 patients.
  • Development and training of a classification and segmentation algorithm using DNN and 3D CNN.
  • Comparison of algorithm performance across lung, mediastinum, and bone window reconstructions using analysis of variance.
  • Pathological results served as the gold standard for nodule classification.

Main Results:

  • The DNN-CNN model achieved high classification accuracy for pulmonary nodule density types (98.2%, 96.4%, 94.5%) and diagnostic accuracy for benign/malignant nodules (98.2%, 96.4%, 94.5%) across the three reconstruction methods.
  • Nodule segmentation performance, measured by Dice coefficients, was consistent across algorithms (80.32% ± 5.91%, 79.83% ± 6.12%, 80.17% ± 5.89%).
  • No statistically significant differences (P > 0.05) were observed in classification accuracy, Dice coefficients, or diagnostic accuracy among the different CT reconstruction algorithms.

Conclusions:

  • The DNN combined with 3D CNN demonstrates robust efficiency in identifying and segmenting pulmonary nodules.
  • The AI model's performance in classifying and segmenting nodules is not significantly affected by the choice of CT reconstruction algorithm.
  • This AI approach offers a reliable tool for distinguishing benign from malignant pulmonary nodules, irrespective of CT reconstruction parameters.