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

Critical Review of Cataractogenesis and Lens Contouring in Radiation Oncology.

Advances in radiation oncology·2026
Same author

Multi-plane vision transformer for hemorrhage classification using axial and sagittal MRI data.

Scientific reports·2026
Same author

Deep learning based 3D brain metastasis synthesis with configurable parameters for 3D data augmentation.

Scientific reports·2026
Same author

Single shot full plan deep learning dose computation for radiation therapy using spherical harmonics.

Medical physics·2026
Same author

Towards a cardiovascular magnetic resonance foundation model for multi-task cardiac image analysis.

Journal of cardiovascular magnetic resonance : official journal of the Society for Cardiovascular Magnetic Resonance·2025
Same author

Deep learning-based identification of patients at increased risk of cancer using routine laboratory markers.

Scientific reports·2025

Related Experiment Video

Updated: Jun 19, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.8K

Extended nnU-Net for Brain Metastasis Detection and Segmentation in Contrast-Enhanced Magnetic Resonance Imaging With

Youngjin Yoo1, Eli Gibson1, Gengyan Zhao1

  • 1Siemens Healthineers, Digital Technology and Innovation, Princeton, New Jersey.

International Journal of Radiation Oncology, Biology, Physics
|July 26, 2024
PubMed
Summary

An enhanced nnU-Net framework improved brain metastasis detection and segmentation on MRI, significantly boosting small lesion sensitivity while controlling false positives for better early diagnosis and treatment planning.

More Related Videos

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
09:53

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Published on: August 16, 2020

7.2K
Modeling Brain Metastases Through Intracranial Injection and Magnetic Resonance Imaging
06:44

Modeling Brain Metastases Through Intracranial Injection and Magnetic Resonance Imaging

Published on: June 7, 2020

7.3K

Related Experiment Videos

Last Updated: Jun 19, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

6.8K
Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography
09:53

Quantifying the Brain Metastatic Tumor Micro-Environment using an Organ-On-A Chip 3D Model, Machine Learning, and Confocal Tomography

Published on: August 16, 2020

7.2K
Modeling Brain Metastases Through Intracranial Injection and Magnetic Resonance Imaging
06:44

Modeling Brain Metastases Through Intracranial Injection and Magnetic Resonance Imaging

Published on: June 7, 2020

7.3K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence in Medicine
  • Neuro-oncology

Background:

  • Brain metastases (BM) detection and segmentation on MRI are crucial for diagnosis and treatment planning.
  • Existing deep learning frameworks require optimization for improved performance, especially for smaller lesions.

Purpose of the Study:

  • To investigate an extended self-adapting nnU-Net framework for enhanced detection and segmentation of brain metastases (BM) on MRI.
  • To evaluate the framework's performance across various BM sizes and compare different adaptive strategies.

Main Methods:

  • Trained and tested six nnU-Net systems with adaptive data sampling or adaptive Dice loss on 3D post-Gd T1-weighted MRI from 2092 patients.
  • Utilized retrospective clinical data and augmented training sets with synthetic BMs.
  • Evaluated detection using sensitivity and false-positive (FP) rates; segmentation using Dice similarity coefficient and Hausdorff distances.

Main Results:

  • The nnU-Net with adaptive Dice loss demonstrated superior performance in BM detection and segmentation.
  • Achieved an overall sensitivity of 0.904 for all BM sizes at an FP rate of 0.65 ± 1.17.
  • Showcased high sensitivity for larger lesions (0.966 for BM ≥0.1 cm³) and improved sensitivity for smaller lesions (0.824 for BM <0.1 cm³).

Conclusions:

  • The extended self-configuring nnU-Net framework significantly enhances the detection sensitivity of small brain metastases.
  • Maintained a controlled false-positive rate, indicating improved accuracy and reliability.
  • The model shows potential for clinical utility in early BM detection and stereotactic radiosurgery planning.