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

Cerebral Edema ll: Pathophysiology

Cerebral Edema ll: Pathophysiology

Vasogenic edema is a major form of cerebral edema characterized by abnormal accumulation of fluid in the brain’s extracellular space due to disruption of the blood–brain barrier (BBB). The BBB is a specialized structure composed of endothelial cells connected by tight junctions, supported by astrocytic endfeet and a basement membrane. Under normal conditions, it tightly regulates the movement of ions, proteins, and solutes between the bloodstream and brain parenchyma. When this barrier loses...

You might also read

Related Articles

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

Sort by

Same author

Surgical Video Understanding with Alignment-Preserving Temporal Adaptation and Action Triplet Text Alignment.

Bioengineering (Basel, Switzerland)·2026

Same author

Rapid immunohistochemistry for intraoperative differentiation between high-grade gliomas and primary central nervous system lymphomas: a multicenter prospective study.

Brain tumor pathology·2026

Same author

Author Correction: Attenuated fusogenicity and pathogenicity of SARS-CoV-2 Omicron variant.

Nature·2026

Same author

Therapeutic Courses of Presumed Intracranial Immature Teratoma Diagnosed Based on Increased Alpha-Fetoprotein.

Journal of child neurology·2026

Same author

Virological characteristics of SARS-CoV-2-related coronaviruses dynamically circulating in Southeast Asia.

Cell·2026

Same author

Extraskeletal Myxoid Chondrosarcoma Mimicking Myoepithelial Tumor.

Case reports in pathology·2026

Same journal

Glomerular Capillary Microaneurysms in Membranoproliferative Glomerulonephritis: A Clinicopathological Study Highlighting the Involvement of IgG3.

Pathology international·2026

Same journal

A Homology-Based Application to Diagnose Colorectal Adenoma and Early-Stage Cancer.

Pathology international·2026

Same journal

Comprehensive Profiling Reveals Sialyl-Tn Upregulation and Prognostic Value in Prostate Cancer.

Pathology international·2026

Same journal

Undifferentiated Carcinoma of the Endometrium: Morphology, Immunophenotype, and Differential Diagnoses to Avoid Diagnostic Pitfalls.

Pathology international·2026

Same journal

Significance of Positive Cerebrospinal Fluid Cytology (Leptomeningeal Metastasis) in Central Nervous System Metastasis - A Multicentre Clinicopathological Review.

Pathology international·2026

Same journal

Role of Upregulated Mucin 21 in Detached Lung Cancer Cells.

Pathology international·2026

See all related articles

Search research articles

Home
Transfer Learning Strategies For Pathological Foundation Models: A Systematic Evaluation In Brain Tumor Classification.

Home
Transfer Learning Strategies For Pathological Foundation Models: A Systematic Evaluation In Brain Tumor Classification.

Related Experiment Video

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

Transfer Learning Strategies for Pathological Foundation Models: A Systematic Evaluation in Brain Tumor

Ken Enda¹, Yoshitaka Oda¹, Zen-Ichi Tanei²

¹Department of Cancer Pathology, Faculty of Medicine, Hokkaido University, Sapporo, Japan.

Pathology International

|February 18, 2026

View abstract on PubMed

Summary

This summary is machine-generated.

For brain tumor classification AI, linear probing (LP) with foundation models outperforms fine-tuning (FT) on external data. This approach enhances AI generalization, overcoming limitations of limited hospital case data.

More Related Videos

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

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

Related Experiment Videos

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

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

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

Area of Science:

Artificial Intelligence in Pathology
Computational Pathology
Machine Learning for Medical Imaging

Background:

Deploying pathology AI in hospitals is challenged by limited case data and adapting pre-trained models.
Brain tumor classification presents a specific challenge due to diverse categories and few institutional cases.
Optimal transfer learning strategies for foundation models in this context are unclear.

Purpose of the Study:

To evaluate fine-tuning (FT) versus linear probing (LP) for brain tumor classification using foundation and conventional AI models.
To determine the most effective transfer learning strategy for adapting AI models to local and external datasets.
To assess the impact of different transfer learning methods on AI model generalization capabilities.

Main Methods:

Compared FT and LP strategies on foundation models (UNI, Prov-GigaPath) and conventional models (ViT-L, CTransPath).
Trained models on an institutional dataset (254 cases) and validated on the EBRAINS dataset (698 cases).
Evaluated performance based on classification accuracy and generalization across datasets.

Main Results:

Conventional models showed FT ≥ LP performance on both datasets.
Foundation models exhibited a reversal: FT marginally outperformed LP on institutional data, while LP significantly outperformed FT on external data (p < 0.01).
UNI with LP (10 patches/case) surpassed fine-tuned conventional models (500 patches/case) on external validation (p < 0.001).

Conclusions:

Fine-tuning foundation models on limited institutional data may lead to overfitting and compromise generalization.
Linear probing preserves pre-trained representations, enabling more efficient AI implementation with superior generalization for brain tumor classification.
Linear probing emerges as a more robust strategy for deploying foundation models in pathology AI with limited local data.