Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: Mar 10, 2026

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities
07:13

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

Published on: October 27, 2023

1.7K

Adaptive multi-teacher knowledge distillation framework with foundation models for medical image analysis.

Dudu Liu1, Yuan Gao2, Ningyi Zhang1

  • 1Intelligent Medical Computing Laboratory, Faculty of Applied Sciences, Macao Polytechnic University, Rua de Luís Gonzaga Gomes, 999078, Macao Special Administrative Region of China.

Computerized Medical Imaging and Graphics : the Official Journal of the Computerized Medical Imaging Society
|March 9, 2026
PubMed
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

Efficacy of Jishi Shuanghua Granules in preventing radiation-induced esophagitis in non-small cell lung cancer patients undergoing concurrent chemoradiotherapy: protocol for a multicenter, randomized, double-blind, placebo-controlled trial.

Frontiers in medicine·2026
Same author

Modified sini powder for the management of postoperative depression in non-small cell lung cancer patients: a multicenter, randomized, double-blind, placebo-controlled trial protocol.

Frontiers in pharmacology·2026
Same author

Characteristics of dermal fibroblasts and their biotherapeutic value in musculoskeletal system diseases.

Frontiers in bioengineering and biotechnology·2026
Same author

Brain and knee joint degeneration following anterior cruciate ligament injury in a mouse model of Alzheimer's disease.

JBMR plus·2026
Same author

Soil Fungal Communities' Characteristics of the <i>Lamiophlomis rotata</i> Root-Zone to Altitude and Their Relationship with Environmental Factors.

Microorganisms·2026
Same author

CTransFuse: A Hybrid Transformer-CNN Framework for Precise Meniscus Segmentation and Lesion Identification.

IEEE journal of biomedical and health informatics·2026
This summary is machine-generated.

Foundation models (FMs) for medical imaging can now be distilled into a single, lightweight student model using MultiMedDistill. This framework enables efficient deployment on edge devices, overcoming computational limitations.

Area of Science:

  • Artificial Intelligence
  • Medical Imaging
  • Machine Learning

Background:

  • Foundation models (FMs) in medical imaging face deployment challenges on resource-limited edge devices due to high computational demands and large parameter sizes.
  • Retraining FMs requires scarce data and significant resources, while knowledge transfer often leads to information loss.

Purpose of the Study:

  • To introduce MultiMedDistill, an adaptive multi-teacher distillation framework for integrating heterogeneous FMs into a lightweight student model.
  • To enable efficient model coordination, capability migration, knowledge preservation, and practical edge deployment of medical imaging FMs.

Main Methods:

  • Developed MultiMedDistill, an adaptive multi-teacher distillation framework.
  • Integrated multiple heterogeneous FMs into a single lightweight student model.
Keywords:
Adaptive gating mechanismDeep learningFoundation modelsMedical image analysisModel compressionMulti-teacher knowledge distillation

Related Experiment Videos

Last Updated: Mar 10, 2026

Author Spotlight: An Efficient and Robust Software for Automated Fusion of Multiple Preclinical Imaging Modalities
07:13

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

Published on: October 27, 2023

1.7K
  • Implemented a dual-level gating mechanism for dynamic teacher coordination and a return decoder for semantic fidelity preservation.

    • Main Results:

    • Achieved 94.77% Dice on BUSI and 97.06% Dice on Kvasir-SEG across six benchmark datasets (ultrasound, endoscopy, fundus imaging, CT, MRI).
    • Demonstrated significant improvements of 25.76% and 13.04% over baselines.
    • Compressed the student model to 8.8M parameters (18× reduction), with adaptive gating and reconstruction-based knowledge preservation contributing notable gains.

    Conclusions:

    • MultiMedDistill effectively transfers FM capabilities with minimal computational cost.
    • The framework enables practical deployment of powerful medical imaging models on clinical edge devices.
    • This approach overcomes limitations of retraining and cross-model knowledge transfer for edge AI in healthcare.