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

Computerized Segmentation Method for Nonmasses on Breast DCE-MRI Images Using ResUNet++ with Slice Sequence Learning and Cross-Phase Convolution.

Journal of imaging informatics in medicine·2024
Same author

Computer-Aided Diagnosis Scheme for Distinguishing Between Benign and Malignant Masses on Breast DCE-MRI Images Using Deep Convolutional Neural Network with Bayesian Optimization.

Journal of digital imaging·2020
Same journal

How is Bias Learned in Medical Image Analysis Models? An Exploration of the Encoding of Demographic Information in Deep Learning Models Trained to Detect Abnormalities on Chest X-Rays.

Journal of imaging informatics in medicine·2026
Same journal

AI-Based Opportunistic CT Risk Assessment Using TotalSegmentator in Osteoporotic Vertebral Fractures.

Journal of imaging informatics in medicine·2026
Same journal

A Computationally Efficient and Improved Brain Tumor Recognition System by MRI-Segmentation Integrated Classification Network.

Journal of imaging informatics in medicine·2026
Same journal

Ultrasound Domain Adaptation for Robust Kidney Segmentation via Spectral-Similarity-Guided Translation.

Journal of imaging informatics in medicine·2026
Same journal

Dynamic Fuzzy-Gaussian Modeling (DynFGM): A Kurtosis-Adaptive Unsupervised Framework for Automated Adipose Tissue Segmentation in Abdominal MRI.

Journal of imaging informatics in medicine·2026
Same journal

MammoDenseSegNet: A Context-Aware Deep Learning Model for Dense Tissue Segmentation in Digital Mammograms.

Journal of imaging informatics in medicine·2026
See all related articles
  1. Home
  3. Computerized Classification Method For Glioma Molecular Subtypes On Brain Mr Images Using Sam-med3d With Low-rank Adaptation.
  1. Home
  3. Computerized Classification Method For Glioma Molecular Subtypes On Brain Mr Images Using Sam-med3d With Low-rank Adaptation.

Related Experiment Video

Optimization of High Grade Glioma Cell Culture from Surgical Specimens for Use in Clinically Relevant Animal Models and 3D Immunochemistry
12:25

Optimization of High Grade Glioma Cell Culture from Surgical Specimens for Use in Clinically Relevant Animal Models and 3D Immunochemistry

Published on: January 7, 2014

Computerized Classification Method for Glioma Molecular Subtypes on Brain MR Images Using SAM-Med3D with Low-Rank

Akiyoshi Hizukuri1

  • 1Yokohama City University, 22-2 Seto, Kanazawa-Ku, Yokohama, Kanagawa, Japan. hizukuri.aki.jx@yokohama-cu.ac.jp.

Journal of Imaging Informatics in Medicine
|June 22, 2026

View abstract on PubMed

Summary
This summary is machine-generated.

This study introduces a novel AI method using brain MRI scans to classify glioma molecular subtypes, avoiding invasive tumor biopsies. The approach demonstrates high accuracy, offering a less burdensome alternative for patient management.

Keywords:
Brain MR imageGlioma molecular subtypesLow-rank adaptationSAM-Med3DTransfer learning

More Related Videos

Laser Capture Microdissection of Glioma Subregions for Spatial and Molecular Characterization of Intratumoral Heterogeneity, Oncostreams, and Invasion
09:09

Laser Capture Microdissection of Glioma Subregions for Spatial and Molecular Characterization of Intratumoral Heterogeneity, Oncostreams, and Invasion

Published on: April 12, 2020

Reproducible 3D Glioblastoma Migration Assay with Magnetic Nanoparticle Mediated Spheroid Localization Under Hypoxic Conditions
07:55

Reproducible 3D Glioblastoma Migration Assay with Magnetic Nanoparticle Mediated Spheroid Localization Under Hypoxic Conditions

Published on: May 12, 2026

Related Experiment Videos

Optimization of High Grade Glioma Cell Culture from Surgical Specimens for Use in Clinically Relevant Animal Models and 3D Immunochemistry
12:25

Optimization of High Grade Glioma Cell Culture from Surgical Specimens for Use in Clinically Relevant Animal Models and 3D Immunochemistry

Published on: January 7, 2014

Laser Capture Microdissection of Glioma Subregions for Spatial and Molecular Characterization of Intratumoral Heterogeneity, Oncostreams, and Invasion
09:09

Laser Capture Microdissection of Glioma Subregions for Spatial and Molecular Characterization of Intratumoral Heterogeneity, Oncostreams, and Invasion

Published on: April 12, 2020

Reproducible 3D Glioblastoma Migration Assay with Magnetic Nanoparticle Mediated Spheroid Localization Under Hypoxic Conditions
07:55

Reproducible 3D Glioblastoma Migration Assay with Magnetic Nanoparticle Mediated Spheroid Localization Under Hypoxic Conditions

Published on: May 12, 2026

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Oncology

Background:

  • Identifying glioma molecular subtypes is crucial for patient treatment.
  • Current genetic testing requires tumor tissue, posing a significant burden.
  • Non-invasive methods for molecular subtype classification are needed.

Purpose of the Study:

  • To develop and evaluate a computerized method for classifying glioma molecular subtypes using multi-modal brain MRI.
  • To leverage a pretrained 3D foundation model (SAM-Med3D) for this classification task.

Main Methods:

  • A multi-modal network incorporating four modality-specific 3D image encoders (T1w, T2w, FLAIR, T1ce) was developed.
  • Low-rank adaptation was used to efficiently adapt encoders.
  • A classification head was integrated for molecular subtype prediction using extracted image and prompt embeddings.

Main Results:

  • The proposed SAM-Med3D-based network achieved an area under the curve (AUC) of 0.931.
  • This performance surpassed conventional networks like SGPNet (0.827), MA-MTLN (0.902), and MTTU-Net (0.910).

Conclusions:

  • The SAM-Med3D-based network effectively classifies glioma molecular subtypes from multi-modal brain MRI.
  • This AI-driven approach offers a promising, non-invasive alternative to traditional genetic testing.