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

You might also read

Related Articles

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

Sort by

Same author

Green emitting diatomite-derived Zn<sub>2</sub>SiO<sub>4</sub>:Mn as a dual functional sensor for the development of latent fingerprints.

Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy·2026

Same author

Development of a cholera toxin B subunit-adjuvanted Helicobacter pylori multi-epitope vaccine and evaluation of its immunization effect in mice.

Cytokine·2026

Same author

Propagating Cross-View Semantics for Multi-view Clustering: A Unified Anchor Refinement Paradigm.

IEEE transactions on pattern analysis and machine intelligence·2026

Same author

EyeRAG: graph retrieval-augmented generation for safe and accurate clinical dialogue in ophthalmology.

NPJ digital medicine·2026

Same author

Efficacy and safety of doravirine/lamivudine/tenofovir as initial treatment for people living with HIV in China.

Antimicrobial agents and chemotherapy·2026

Same author

Rational Dual-Site Doping of the Hematite Photoanode Unlocks Efficient Solar Water Splitting.

ACS applied materials & interfaces·2026

Search research articles

Related Experiment Video

Updated: Jun 11, 2025

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Published on: May 5, 2011

Unveiling Thymoma Typing Through Hyperspectral Imaging and Deep Learning.

Qize Lv¹, Ke Liang², ChongXuan Tian¹

¹Department of Biomedical Engineering Institute, School of Control Science and Engineering, Shandong University, Jinan, China.

Journal of Biophotonics

|October 3, 2024

Summary

This study introduces a new hyperspectral imaging and deep learning method for thymoma classification. The technique achieves 95% accuracy, improving automated diagnosis of this rare thymic epithelial tumor.

Keywords:

assisted diagnosis hyperspectral imaging residual neural network thymoma

More Related Videos

Terahertz Imaging and Characterization Protocol for Freshly Excised Breast Cancer Tumors

Terahertz Imaging and Characterization Protocol for Freshly Excised Breast Cancer Tumors

Published on: April 5, 2020

A Rapid Method for Multispectral Fluorescence Imaging of Frozen Tissue Sections

A Rapid Method for Multispectral Fluorescence Imaging of Frozen Tissue Sections

Published on: March 30, 2020

Related Experiment Videos

Last Updated: Jun 11, 2025

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Published on: May 5, 2011

Terahertz Imaging and Characterization Protocol for Freshly Excised Breast Cancer Tumors

Terahertz Imaging and Characterization Protocol for Freshly Excised Breast Cancer Tumors

Published on: April 5, 2020

A Rapid Method for Multispectral Fluorescence Imaging of Frozen Tissue Sections

A Rapid Method for Multispectral Fluorescence Imaging of Frozen Tissue Sections

Published on: March 30, 2020

Area of Science:

Oncology
Medical Imaging
Artificial Intelligence

Background:

Thymoma diagnosis is challenging due to subjective traditional methods, leading to inaccuracies.
Current methods for thymoma classification have high false-negative rates and are time-consuming.

Purpose of the Study:

To develop an automated thymoma classification technique using hyperspectral imaging and deep learning.
To improve the accuracy and efficiency of thymoma diagnosis.

Main Methods:

Hyperspectral imaging captured pathological thymoma slices.
Spectral data was processed, transformed into 2D images using the Gramian Angular Field (GAF) method.
A variant residual network was employed for feature extraction and classification.

Main Results:

The integrated hyperspectral imaging and deep learning model achieved an average classification accuracy of 95%.
The method demonstrated significant enhancements in classification accuracy and diagnostic efficiency.

Conclusions:

This novel technique offers a highly effective approach for automated thymoma diagnosis.
The method optimizes data utilization and feature representation learning for improved diagnostic outcomes.