Search research articles

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

Ki-67 and overall survival in patients with glioblastoma: A systematic prognostic review and meta-analysis.

Neuro-oncology advances·2026

Same author

Assessing Impact of Data Quality in Early Post-Operative Glioblastoma Segmentation.

Journal of imaging·2026

Same author

Dose-enhanced versus standard TTFields for first recurrence of glioblastoma: A randomized phase 2 clinical trial.

Neuro-oncology advances·2025

Same author

JAK inhibitors remove innate immune barriers facilitating viral propagation.

NAR molecular medicine·2025

Same author

Unravelling differences and hallmarks in suspected diffuse low-grade gliomas: a multicentre database study.

Brain communications·2025

Same author

Is tumor shape associated with molecular diagnosis, extent of resection, or postoperative focal deficits in diffuse low-grade gliomas?

Neuro-oncology advances·2025

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

Search research articles

Related Experiment Video

Updated: Jan 13, 2026

Modeling Brain Metastases Through Intracranial Injection and Magnetic Resonance Imaging

Modeling Brain Metastases Through Intracranial Injection and Magnetic Resonance Imaging

Published on: June 7, 2020

Automatic Brain Tumor Segmentation in 2D Intra-Operative Ultrasound Images Using Magnetic Resonance Imaging Tumor

Mathilde Gajda Faanes^1,2, Ragnhild Holden Helland^1,3, Ole Solheim^4,5

¹Department of Health Research, SINTEF Digital, 7465 Trondheim, Norway.

Journal of Imaging

|October 28, 2025

Summary

Magnetic resonance imaging (MRI) tumor annotations can train deep learning models for intra-operative ultrasound (iUS) brain tumor segmentation. This approach overcomes limited iUS data, achieving comparable performance to models trained with iUS data.

Keywords:

brain tumors deep learning intra-operative segmentation ultrasound

More Related Videos

Patient-Specific Polyvinyl Alcohol Phantom Fabrication with Ultrasound and X-Ray Contrast for Brain Tumor Surgery Planning

Patient-Specific Polyvinyl Alcohol Phantom Fabrication with Ultrasound and X-Ray Contrast for Brain Tumor Surgery Planning

Published on: July 14, 2020

Author Spotlight: Integrating High-Resolution Intravital Imaging and MRI to Enhance Stereotactic Body Radiation Therapy Planning

Author Spotlight: Integrating High-Resolution Intravital Imaging and MRI to Enhance Stereotactic Body Radiation Therapy Planning

Published on: April 12, 2024

Related Experiment Videos

Last Updated: Jan 13, 2026

Modeling Brain Metastases Through Intracranial Injection and Magnetic Resonance Imaging

Modeling Brain Metastases Through Intracranial Injection and Magnetic Resonance Imaging

Published on: June 7, 2020

Patient-Specific Polyvinyl Alcohol Phantom Fabrication with Ultrasound and X-Ray Contrast for Brain Tumor Surgery Planning

Patient-Specific Polyvinyl Alcohol Phantom Fabrication with Ultrasound and X-Ray Contrast for Brain Tumor Surgery Planning

Published on: July 14, 2020

Author Spotlight: Integrating High-Resolution Intravital Imaging and MRI to Enhance Stereotactic Body Radiation Therapy Planning

Author Spotlight: Integrating High-Resolution Intravital Imaging and MRI to Enhance Stereotactic Body Radiation Therapy Planning

Published on: April 12, 2024

Area of Science:

Neurosurgery
Medical Imaging
Artificial Intelligence

Background:

Accurate brain tumor segmentation during surgery is crucial for effective resection.
Current deep learning models for intra-operative ultrasound (iUS) segmentation are limited by small annotated datasets.
Magnetic resonance imaging (MRI) offers more accessible annotated data for tumor localization.

Purpose of the Study:

To investigate the efficacy of using MRI-derived tumor annotations for training deep learning models for iUS brain tumor segmentation.
To evaluate if MRI annotations can serve as a viable substitute for limited iUS annotations.
To assess the performance of models trained with different data origins against expert annotations.

Main Methods:

Utilized 180 annotated MRI scans and 29 annotated iUS images.
Performed image registration to transfer MRI annotations to corresponding iUS images.
Trained nnU-Net models with various combinations of MRI and iUS annotated data.
Compared model performance against expert neurosurgeon segmentations.

Main Results:

Models trained with MRI annotations showed performance comparable to those trained with iUS annotations or both.
The best model achieved a Dice score of 0.62 ± 0.31, close to the expert neurosurgeon's 0.67 ± 0.25.
Model performance was similar for larger tumors but lower for smaller tumors compared to experts.
Excluding smaller tumors from training datasets improved segmentation results.

Conclusions:

MRI tumor annotations are a feasible substitute for iUS annotations in training deep learning models for iUS brain tumor segmentation.
This approach can help overcome data scarcity issues in iUS image analysis.
Further refinement, potentially by addressing smaller tumor segmentation, is needed for optimal clinical application.