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

Unleashing the potential of open-set noisy samples against label noise for medical image classification.

Medical image analysis·2025
Same author

Modeling annotator preference and stochastic annotation error for medical image segmentation.

Medical image analysis·2023
Same author

Deep-learning based quantification model for hip bone marrow edema and synovitis in patients with spondyloarthritis based on magnetic resonance images.

Frontiers in physiology·2023
Same author

Reproductive outcomes of women with moderate to severe intrauterine adhesions after transcervical resection of adhesion: A systematic review and meta-analysis.

Medicine·2023
Same author

A convolutional neural network with pixel-wise sparse graph reasoning for COVID-19 lesion segmentation in CT images.

Computers in biology and medicine·2023
Same author

Long noncoding RNAs regulate intrauterine adhesion and cervical cancer development and progression.

Seminars in cell & developmental biology·2023
Same journal

MUST: Multi-style virtual staining with incomplete pairs.

IEEE transactions on medical imaging·2026
Same journal

BrainCL: Transformer-Based Brain Network Contrastive Learning with Multi-Order Topology and Salience Masking.

IEEE transactions on medical imaging·2026
Same journal

LLM-enhanced Neuron Segmentation and Reconstruction in Complex Mouse Brain Images.

IEEE transactions on medical imaging·2026
Same journal

Matrixed-Spectrum Decomposition Accelerated Linear Boltzmann Transport Equation Solver for Fast Scatter Correction in Multi-Spectral CT.

IEEE transactions on medical imaging·2026
Same journal

The Ritz Adjoint Method for MRI Pulse Design.

IEEE transactions on medical imaging·2026
Same journal

Physiology-guided Self-supervised Learning for Simultaneous Dual-Tracer PET Separation.

IEEE transactions on medical imaging·2026
See all related articles

Related Experiment Video

Updated: Oct 4, 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

Learning From Ambiguous Labels for Lung Nodule Malignancy Prediction.

Zehui Liao, Yutong Xie, Shishuai Hu

    IEEE Transactions on Medical Imaging
    |February 7, 2022
    PubMed
    Summary
    This summary is machine-generated.

    This study introduces a novel multi-view "divide-and-rule" (MV-DAR) model to improve lung nodule malignancy prediction by effectively learning from ambiguous radiologist annotations on CT scans.

    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

    527

    Related Experiment Videos

    Last Updated: Oct 4, 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

    527

    Area of Science:

    • Medical imaging analysis
    • Artificial intelligence in healthcare
    • Radiology and oncology

    Background:

    • Accurate lung nodule malignancy prediction is crucial for early lung cancer diagnosis.
    • Ambiguous radiologist annotations and human biases pose significant challenges for deep learning models.
    • Existing models struggle to effectively learn from unreliable or inconsistent labels.

    Purpose of the Study:

    • To develop a novel deep learning model, the multi-view 'divide-and-rule' (MV-DAR) model, for lung nodule malignancy prediction.
    • To address the challenge of learning from both reliable and ambiguous annotations in chest CT scans.
    • To improve the robustness and accuracy of malignancy prediction by leveraging inconsistent and low-reliable labels.

    Main Methods:

    • A multi-view 'divide-and-rule' (MV-DAR) model was proposed, categorizing nodules into consistent/reliable (CR-Set), inconsistent (IC-Set), and low-reliable (LR-Set) based on annotation consistency.
    • The model employs a two-stage training procedure with three DAR models, each comprising prediction (Prd-Net), counterfactual (CF-Net), and low-reliable (LR-Net) networks.
    • Attention mechanisms (NA-Module, CA-Module) were utilized in the fine-tuning phase to transfer learned representations from CF-Net and LR-Net to Prd-Net.

    Main Results:

    • The MV-DAR model demonstrated effectiveness in learning from ambiguous and inconsistent lung nodule annotations.
    • Evaluations on LIDC-IDRI and LUNGx datasets showed the MV-DAR model's superiority over existing noisy label-learning methods.
    • The model successfully improved lung nodule malignancy prediction accuracy by utilizing diverse annotation qualities.

    Conclusions:

    • The MV-DAR model offers a robust solution for lung nodule malignancy prediction, adept at handling ambiguous annotations.
    • This approach effectively mitigates the impact of human bias and annotation variability in deep learning models.
    • The MV-DAR model represents a significant advancement in leveraging complex, real-world annotation data for improved diagnostic accuracy.