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

Search research articles

Related Experiment Video

Updated: May 12, 2026

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands

Published on: July 26, 2014

Cross-Architecture Knowledge Distillation for Histopathological Image Analysis.

Seddik Boudissa¹, Hiroharu Kawanaka¹, Bruce Aronow^2,3,4

¹Graduate School of Engineering, Mie University, Mie 514-8507, Japan.

IEEE Access : Practical Innovations, Open Solutions

|May 11, 2026

Summary

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

Editor's Note: Myc-Transformed Epithelial Cells Down-Regulate Clusterin, Which Inhibits Their Growth in Vitro and Carcinogenesis in Vivo.

Cancer research·2026

Same author

Automated Eosinophil Quantification Using Deep Learning to Predict Therapy Escalation in Pediatric Ulcerative Colitis.

Clinical and translational gastroenterology·2026

Same author

End-to-End Multimodal Multiple Instance Learning for Cancer Histopathology Classification with Dual-Attention Fusion.

Journal of medical systems·2026

Same author

Pathology Public Datasets for Artificial Intelligence: A Systematic Review.

Journal of imaging informatics in medicine·2026

Same author

Investigating the oncogenic role of aberrant EZH2 in hepatoblastoma.

Scientific reports·2026

Same author

KAT5 regulates neurodevelopmental states associated with G0-like populations in glioblastoma.

Nature communications·2025

Same journal

Validating Single-Camera Pose Estimation Against Multi-Camera Motion Capture for Accessible Biomechanical Assessment.

IEEE access : practical innovations, open solutions·2026

Same journal

Learning to Diagnose Privately: DP-Powered LLMs for Radiology Report Classification.

IEEE access : practical innovations, open solutions·2026

Same journal

Radio-Frequency Toroid Susceptometry of Magnetic Nanoparticles: What Goes Around Comes Around.

IEEE access : practical innovations, open solutions·2026

Same journal

Mislabel Identification Using Transfer Learning-Based Ensemble Method.

IEEE access : practical innovations, open solutions·2026

Same journal

Deep Learning for Path Loss Prediction at 7 GHz in Urban Environment.

IEEE access : practical innovations, open solutions·2026

Same journal

A Translational Platform for Polyimide Neural Interfaces: Polyimide Synthesis and in Vivo Evaluation in Epileptic Mice.

IEEE access : practical innovations, open solutions·2026

See all related articles

This summary is machine-generated.

This study introduces a novel knowledge distillation framework to improve vision transformer (ViT) performance in histopathological image analysis. The method effectively transfers spatial and semantic knowledge from CNN teachers to ViT students, enhancing diagnostic accuracy for subtle cancer subtypes.

Area of Science:

Computational pathology
Medical image analysis
Deep learning architectures

Background:

Histopathological image analysis faces challenges with subtle variations and complex structures.
Convolutional Neural Networks (CNNs) excel at local patterns, while Vision Transformers (ViTs) capture long-range dependencies.
ViTs struggle with fine-grained spatial details in histopathology, especially with limited data.

Purpose of the Study:

To develop a knowledge distillation (KD) framework for transferring knowledge from CNNs to ViTs in histopathology.
To address representation and spatial misalignment between heterogeneous CNN and ViT architectures.
To improve ViT performance in analyzing complex histopathological images.

Main Methods:

Proposed a KD framework with a CNN teacher and ViT student.

Keywords:

Histopathology centered kernel alignment image classification kernel canonical correlation analysis knowledge distillation vision transformers

More Related Videos

Generating and Analyzing High-Parameter Histology Images with Histoflow Cytometry

Generating and Analyzing High-Parameter Histology Images with Histoflow Cytometry

Published on: June 21, 2024

High-Throughput, Multi-Image Cryohistology of Mineralized Tissues

High-Throughput, Multi-Image Cryohistology of Mineralized Tissues

Published on: September 14, 2016

Related Experiment Videos

Last Updated: May 12, 2026

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands

Reconstruction of 3-Dimensional Histology Volume and its Application to Study Mouse Mammary Glands

Published on: July 26, 2014

Generating and Analyzing High-Parameter Histology Images with Histoflow Cytometry

Generating and Analyzing High-Parameter Histology Images with Histoflow Cytometry

Published on: June 21, 2024

High-Throughput, Multi-Image Cryohistology of Mineralized Tissues

High-Throughput, Multi-Image Cryohistology of Mineralized Tissues

Published on: September 14, 2016

Introduced principled layer alignment using Centered Kernel Alignment (CKA) and Kernel Canonical Correlation Analysis (KCCA).

Implemented stage-level representation alignment to preserve semantic consistency across architectures.

Main Results:

Achieved 96.87% accuracy (patient-wise) and 98.82% (image-wise) on the BreakHis dataset.
Outperformed state-of-the-art KD methods by 4%.
Demonstrated significant performance improvements, especially for fine-grained subtypes.

Conclusions:

The proposed cross-architecture KD framework effectively enhances ViT performance in computational pathology.
Principled layer alignment strategies are crucial for successful knowledge transfer between CNNs and ViTs.
This approach shows promise for improving automated analysis of histopathological images.