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

Towards the construction of a virtual yeast.

Nature·2026

Same author

A Biomimetic Single-Atom Nanozyme With a Substrate Pocket for Accurate and Continuous Sweat Glucose Monitoring.

Advanced materials (Deerfield Beach, Fla.)·2026

Same author

Effect of Al on the Isothermal Oxidation Behavior of a Ti<sub>70</sub>Zr<sub>20</sub>Ta<sub>10</sub> Shape Memory Alloy at 900 °C.

Materials (Basel, Switzerland)·2026

Same author

Tryptamine from wake-active monoaminergic neurons regulates sleep homeostasis.

Nature neuroscience·2026

Same author

Quercetin regulates lipid metabolism and inflammatory microenvironment of microglia after spinal cord injury through activating the butyrate-FFAR2/AMPK/TFEB gut-brain axis signaling pathway.

International immunopharmacology·2026

Same author

Catalytic and regulatory basis of tRNA t<sup>6</sup>A modification by the KEOPS complex.

Nature communications·2026

Search research articles

Related Experiment Video

Updated: Jul 25, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

[A multimodal medical image contrastive learning algorithm with domain adaptive denormalization].

Han Wen^1,2, Ying Zhao³, Xiuding Cai^1,2

¹Chengdu Institute of Computer Applications, Chinese Academy of Sciences, Chengdu 610213, P. R. China.

Sheng Wu Yi Xue Gong Cheng Xue Za Zhi = Journal of Biomedical Engineering = Shengwu Yixue Gongchengxue Zazhi

|June 28, 2023

Summary

This summary is machine-generated.

This study introduces a novel contrastive learning method for multimodal medical images, improving diagnostic accuracy with limited data. The approach enhances learning from diverse image types, offering a new solution for medical AI pre-training.

Keywords:

Disease diagnosis Domain adaptive denormalization Multimodal medical image Self-supervised learning

More Related Videos

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Related Experiment Videos

Last Updated: Jul 25, 2025

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities

Published on: October 27, 2023

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Area of Science:

Artificial Intelligence
Medical Imaging
Machine Learning

Context:

Deep learning excels in medical imaging but requires extensive annotated data.
Annotating medical images is costly and time-consuming, posing a challenge for model training.
Existing methods like transfer learning and self-supervised learning are underexplored in multimodal medical imaging.

Purpose:

To propose a novel contrastive learning framework for multimodal medical images.
To leverage same-patient, multi-modality images as positive samples to enhance learning.
To introduce a domain adaptive denormalization method for effective multimodal data augmentation.

Summary:

The proposed contrastive learning method utilizes images from different modalities of the same patient as positive samples.
This strategy increases positive sample availability, enabling the model to learn lesion similarities and differences across modalities.
A domain adaptive denormalization technique is introduced to address augmentation challenges in multimodal data.

Impact:

Achieved 74.79% accuracy and 78.37% F1 score in microvascular infiltration recognition.
Demonstrated significant improvements in brain tumor pathology grading.
Provides a valuable pre-training solution for multimodal medical image analysis and diagnostic accuracy.