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: Mar 8, 2026

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

Unsupervised Transfer Learning via Multi-Scale Convolutional Sparse Coding for Biomedical Applications.

Hang Chang, Ju Han, Cheng Zhong

IEEE Transactions on Pattern Analysis and Machine Intelligence

|January 28, 2017

Summary

This summary is machine-generated.

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

Identifying predictive hematological biomarkers for radiation exposure by machine learning in mouse models.

Communications medicine·2026

Same author

A quantitative proteomics dataset for assessment and prediction of low dose X-ray radiation exposure in mice.

bioRxiv : the preprint server for biology·2026

Same author

Multiple types of exogenous microparticles coexist in the early human decidua and placental villi.

Environment international·2026

Same author

Genetic variations and their interaction with thirdhand smoke exposure on anxiety and memory in Collaborative Cross mice.

Environment international·2026

Same author

Is Protein Quantification and Physical Normalization Always Necessary in Proteomics?

bioRxiv : the preprint server for biology·2026

Same author

Agnostic capture of pathogens for the detection and diagnostics of emerging threats.

iScience·2026

Same journal

TraGraph-GS: Trajectory Graph-based Gaussian Splatting for Arbitrary Large-Scale Scene Rendering.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

SWIFT: A Small-World Interaction Framework for Flow-Aware Trajectory Prediction in Autonomous Driving.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

HardFlow: Hard-Constrained Sampling for Flow-Matching Models Via Trajectory Optimization.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

Industrial Brain: Self-Evolving Neuro-Symbolic Autonomy with Causal Resilience for Cyber-Physical Systems.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

Adaptive Hardness-Driven Dictionary Distillation for Incomplete Streaming View Clustering.

IEEE transactions on pattern analysis and machine intelligence·2026

Same journal

Mixture of Global and Local Experts with Diffusion Transformer for Controllable Face Generation.

IEEE transactions on pattern analysis and machine intelligence·2026

See all related articles

This study introduces a novel unsupervised transfer learning method for biomedical tasks with limited data. The multi-scale convolutional sparse coding (MSCSC) approach effectively learns and adapts knowledge across domains, improving performance in data-scarce scenarios.

Area of Science:

Biomedical informatics
Machine learning
Computer vision

Background:

Transfer learning is crucial for knowledge generalization across domains.
Supervised deep learning excels but requires large labeled datasets, often unavailable in biomedicine.
Unsupervised transfer learning is urgently needed for data-scarce biomedical applications.

Purpose of the Study:

To develop a novel unsupervised transfer learning method for biomedical tasks.
To enable learning transferable knowledge and fine-tuning it for small-scale target tasks.
To address limitations of supervised methods in low-data biomedical scenarios.

Main Methods:

Proposed a multi-scale convolutional sparse coding (MSCSC) method.
MSCSC automatically learns filter banks at different scales with enforced scale-specificity.

Related Experiment Videos

Last Updated: Mar 8, 2026

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

Provides an unsupervised framework for base knowledge learning and fine-tuning.

Main Results:

MSCSC demonstrated effectiveness in both regular and transfer learning tasks.
Evaluated across various biomedical domains.
Validated the method's capability in learning transferable base knowledge and fine-tuning.

Conclusions:

The proposed MSCSC method offers an effective unsupervised transfer learning solution for biomedical data.
MSCSC successfully learns and adapts knowledge across domains, even with limited data.
The approach shows promise for improving machine learning performance in diverse biomedical applications.