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 Experiment Video

Updated: Jun 11, 2026

Synchronous Triplanar Reconstruction Integrated with Color Doppler Mapping for Precise and Rapid Localization of Thyroid Lesions
05:41

Synchronous Triplanar Reconstruction Integrated with Color Doppler Mapping for Precise and Rapid Localization of Thyroid Lesions

Published on: February 9, 2024

From Slice to Sequence: Autoregressive Tracking Transformer for Consistent 3D Lymph Node Detection in CT Scans.

Qinji Yu, Yirui Wang, Ke Yan

    IEEE Transactions on Medical Imaging
    |June 9, 2026
    PubMed
    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

    Disruption of dynactin complex function in intellectual disability.

    Proceedings of the National Academy of Sciences of the United States of America·2026
    Same author

    Postoperative impact of pelvic organ prolapse and urinary incontinence surgeries on female sexual function measured by validated instruments: a systematic review and meta-analysis.

    Sexual medicine reviews·2026
    Same author

    Nrf2 deficiency converts the ESCC microenvironment into an immunologically active state via the GPX2-ICD-DC signaling path.

    Journal of translational medicine·2026
    Same author

    Zanthoxylum nitidum-derived active alkaloid nitidine chloride mitigates ulcerative colitis by remodeling gut microbiota and activating SIRT1 to restore intestinal barrier integrity.

    Phytomedicine : international journal of phytotherapy and phytopharmacology·2026
    Same author

    Efficacy of Nurse-Led WIKAP Intervention on Hypoglycemia Coping Confidence and Outcomes in Adolescents with Type 1 Diabetes Mellitus: A Quasi-Experimental Study in Zhijiang, China.

    Patient preference and adherence·2026
    Same author

    Clinical and economic burden of recurrence among older patients with locoregionally advanced head and neck squamous cell carcinoma in the United States.

    Journal of managed care & specialty pharmacy·2026

    This study introduces LN-Tracker, a novel transformer model for enhanced 3D lymph node (LN) detection in CT scans. LN-Tracker improves accuracy by tracking LNs slice-by-slice, outperforming existing 2D, 2.5D, and 3D methods.

    Area of Science:

    • Radiology and Medical Imaging
    • Artificial Intelligence in Healthcare
    • Computer Vision for Medical Diagnosis

    Background:

    • Lymph node (LN) assessment is crucial for cancer staging and treatment planning.
    • Detecting low-contrast, scattered LNs in 3D CT scans presents significant challenges for clinicians.
    • Existing 2.5D methods lack explicit inter-slice consistency modeling for 3D LN objects, necessitating complex post-processing.

    Purpose of the Study:

    • To develop a novel method for accurate and efficient 3D lymph node detection and instance association in CT scans.
    • To address the limitations of existing 2.5D and 3D detection approaches by modeling inter-slice consistency.
    • To propose LN-Tracker, a transformer-based model for joint end-to-end detection and 3D instance association.

    Main Methods:

    More Related Videos

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

    Published on: November 30, 2022

    Related Experiment Videos

    Last Updated: Jun 11, 2026

    Synchronous Triplanar Reconstruction Integrated with Color Doppler Mapping for Precise and Rapid Localization of Thyroid Lesions
    05:41

    Synchronous Triplanar Reconstruction Integrated with Color Doppler Mapping for Precise and Rapid Localization of Thyroid Lesions

    Published on: February 9, 2024

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
    04:48

    Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

    Published on: November 30, 2022

    • Formulated 3D LN detection as a slice-by-slice tracking task along the z-axis.
    • Proposed LN-Tracker, a novel tracking transformer built upon a DETR-based detector.
    • Implemented decoupled transformer queries (track and detection groups) with masked attention and a similarity loss for robust inter-slice association.

    Main Results:

    • LN-Tracker achieved superior performance on four LN datasets, demonstrating at least a 2.49% gain in average sensitivity compared to leading 3D/2.5D/tracking detectors.
    • The model showed robust performance in low-contrast scenarios due to its similarity loss mechanism.
    • Validated generalizability on public lung nodule and prostate tumor detection tasks, achieving top performance.

    Conclusions:

    • LN-Tracker offers a significant advancement in 3D lymph node detection by effectively integrating detection and 3D instance association.
    • The proposed tracking transformer approach enhances accuracy and robustness, particularly for challenging low-contrast and scattered lymph nodes.
    • LN-Tracker's generalizability across different medical imaging tasks highlights its potential for broad clinical application.