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

Composite CT scoring system for Diffuse Idiopathic Skeletal Hyperostosis (DISH): a validated and reproducible framework for diagnosis and severity assessment.

Proceedings of SPIE--the International Society for Optical Engineering·2026
Same author

Multimodal deep learning using pre-transplant CT images predicts cardiovascular events after liver transplantation.

Liver transplantation : official publication of the American Association for the Study of Liver Diseases and the International Liver Transplantation Society·2026
Same author

Automated Segmentation of Brainstem and Subcortical White Matter: Mapping the Deep Tegmental Core with BundleParc.

bioRxiv : the preprint server for biology·2026
Same author

MT-SAM: A Mamba-Transformer Enhanced SAM With Prior-Guided Prompting for Multi-Modal Prostate Cancer Delineation.

IEEE transactions on medical imaging·2026
Same author

Sex-related Variability of White-Matter Tracts is Robust to Tractography Methodology.

Research square·2026
Same author

Association of MRI-Visible Perivascular Spaces With Longitudinal Cognitive Decline Over a Decade.

Neurology·2026

Related Experiment Video

Updated: Nov 19, 2025

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

43.1K

Multi-Site Infant Brain Segmentation Algorithms: The iSeg-2019 Challenge.

Yue Sun, Kun Gao, Zhengwang Wu

    IEEE Transactions on Medical Imaging
    |January 28, 2021
    PubMed
    Summary

    Accurately segmenting infant brain MR images is crucial for understanding development. Deep learning models struggle with multi-site data, indicating that improving consistency across different imaging sites remains a significant challenge.

    More Related Videos

    Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
    04:25

    Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

    Published on: December 15, 2023

    3.3K
    Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
    06:48

    Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

    Published on: January 7, 2019

    9.2K

    Related Experiment Videos

    Last Updated: Nov 19, 2025

    Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
    14:08

    Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

    Published on: April 13, 2013

    43.1K
    Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
    04:25

    Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

    Published on: December 15, 2023

    3.3K
    Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
    06:48

    Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

    Published on: January 7, 2019

    9.2K

    Area of Science:

    • Medical Imaging
    • Neuroscience
    • Artificial Intelligence

    Background:

    • Accurate segmentation of infant brain magnetic resonance (MR) images into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) is essential for studying early brain development and disorders.
    • Deep learning methods show high performance but often fail when applied to data from different imaging sites due to variations in protocols and scanners (the multi-site issue).

    Purpose of the Study:

    • To evaluate the performance of state-of-the-art deep learning methods for infant brain MR image segmentation on a multi-site dataset.
    • To identify limitations and propose future directions for addressing the multi-site issue in infant brain image segmentation.

    Main Methods:

    • The study reviewed 8 top-ranked automatic segmentation methods from the iSeg-2019 challenge.
    • Performance was evaluated across multiple sites (UNC, UMN, Stanford, Emory) using a dataset with varying imaging protocols/scanners.
    • Analyses included whole brain, regions of interest, and gyral landmark curves.

    Main Results:

    • Deep learning methods achieved state-of-the-art performance on individual sites but showed significant performance degradation on data from different sites.
    • Multi-site consistency remains a critical and unresolved challenge for current automated infant brain segmentation techniques.
    • The iSeg-2019 dataset and challenge highlighted the difficulties associated with generalizability across diverse imaging environments.

    Conclusions:

    • Current deep learning models for infant brain segmentation are not robust to multi-site variations.
    • Further research is needed to develop methods that can generalize effectively across different scanners and imaging protocols.
    • Addressing the multi-site issue is crucial for the reliable application of automated segmentation in clinical and research settings.