Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Magnetic Resonance Imaging

Magnetic Resonance Imaging

Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...

Brain Imaging

Brain Imaging

Brain imaging technologies provide critical insights into both the structure and function of the human brain, enabling medical professionals and researchers to diagnose, study, and treat neurological disorders or psychiatric disorders more effectively.
These technologies include computerized axial tomography (CAT or CT scans), positron-emission tomography (PET scans), magnetic resonance imaging (MRI), functional magnetic resonance imaging (fMRI), and Transcranial Magnetic Stimulation (TMS).

You might also read

Related Articles

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

Sort by

Same author

Co-secretion of growth hormone and prolactin defines a high-risk acromegaly phenotype.

Pituitary·2026

Same author

Framework for subcellular localization of alpha-emitting radionuclides.

Physics in medicine and biology·2026

Same author

A proof-of-concept automated method for accurate skin dosimetry: correcting overestimated surface dose measurements.

Physics in medicine and biology·2026

Same author

Patterns of Failure in Synchronous Metastatic Non-Small Cell Lung Cancer Without Driver Alterations According to Metastatic Burden.

Cancers·2026

Same author

Deep Learning for Survival Prediction in Glioblastoma: Time-dependent Model Interpretability Using MRI, Clinical, and Molecular Data.

Radiology. Artificial intelligence·2026

Same author

Preliminary treatment planning strategy for blood dose reduction in head and neck radiotherapy.

Journal of applied clinical medical physics·2026

Search research articles

Related Experiment Video

Updated: Jun 3, 2026

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

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

Published on: January 7, 2019

Enhancing Brain Metastases Detection and Segmentation in Black-Blood MRI Using Deep Learning and Segment Anything

Sang Kyun Yoo^1,2, Tae Hyung Kim^1,3, Jin Sung Kim^1,2,4

¹Department of Radiation Oncology, Yonsei Cancer Center, Heavy Ion Therapy Research Institute, Yonsei University College of Medicine, Seoul, Korea.

Yonsei Medical Journal

|July 25, 2025

Summary

Deep learning models enhanced with generative adversarial networks (GANs) and Segment Anything Model (SAM) post-processing significantly improve brain metastases (BMs) detection and segmentation on black-blood MRI scans. This approach offers higher accuracy for identifying BMs in medical imaging.

Keywords:

Black-blood image Segment Anything Model auto-segmentation brain metastases deep learning

More Related Videos

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

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

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

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

Published on: November 30, 2022

Related Experiment Videos

Last Updated: Jun 3, 2026

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

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

Published on: January 7, 2019

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

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

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

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

Published on: November 30, 2022

Area of Science:

Medical Imaging
Artificial Intelligence
Oncology

Background:

Black-blood (BB) magnetic resonance images (MRI) provide superior contrast for detecting brain metastases (BMs).
Accurate segmentation of BMs is crucial for treatment planning and monitoring.
Deep learning (DL) offers potential for automated detection and segmentation of BMs.

Purpose of the Study:

To investigate the efficacy and accuracy of DL architectures combined with post-processing for BMs detection and segmentation using BB images.
To evaluate modified U-Net architectures, including integration with generative adversarial networks (GANs).
To assess the impact of Segment Anything Model (SAM) as a post-processing step.

Main Methods:

Utilized BB MRI scans from 50 patients for training (40) and testing (10) DL models.
Implemented piecewise linear histogram matching for intensity normalization and resampling.
Applied modified U-Net architectures, including a U-Net-GAN combination, for segmentation.
Used SAM for post-processing of DL-generated bounding boxes.
Quantitatively assessed models using lesion-wise sensitivity (LWS), patient-wise Dice Similarity Coefficient (DSC), and average false-positive rate (FPR).

Main Results:

The modified U-Net with GAN achieved the highest patient-wise DSC (0.853) and LWS (89.19%), outperforming standard U-Net and modified U-Net alone.
The U-Net-GAN combination reduced the average FPR to less than 1.
SAM post-processing did not significantly alter LWS or FPR but increased patient-wise DSC by 2%-3% for all U-Net-based models.

Conclusions:

Modifications to the U-Net architecture, particularly with GAN integration, significantly enhance BMs detection and segmentation in BB MRI.
SAM serves as an effective post-processing tool to further refine segmentation precision.
The combined DL approach shows promise for improving automated analysis of brain metastases.