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

Generalizable spinal cord multiple sclerosis lesion segmentation across MRI contrasts, protocols, and centers.

Multiple sclerosis (Houndmills, Basingstoke, England)·2026

Same author

Making sense of TILs: recommendations for morphological assessment of tumour-infiltrating lymphocytes in gastro-oesophageal carcinoma: A report on behalf of the International Immuno-Oncology Biomarker Working Group.

Histopathology·2026

Same author

Deep Learning Models Connecting Images and Text: A Primer for Radiologists.

Radiographics : a review publication of the Radiological Society of North America, Inc·2025

Same author

Towards reliable WMH segmentation under domain shift: An application study using maximum entropy regularization to improve uncertainty estimation.

Computers in biology and medicine·2025

Same author

Prompt Learning With Bounding Box Constraints for Medical Image Segmentation.

IEEE transactions on bio-medical engineering·2025

Same author

Towards Foundation Models and Few-Shot Parameter-Efficient Fine-Tuning for Volumetric Organ Segmentation.

Medical image analysis·2025

Same journal

Generative morphodynamic forecasting enables robust zero-shot volumetric medical segmentation.

Medical image analysis·2026

Same journal

ContiMorph: An unsupervised learning framework for cardiac motion tracking with time-continuous diffeomorphism.

Medical image analysis·2026

Same journal

MedP-CLIP: Medical CLIP with region-aware prompt integration.

Medical image analysis·2026

Same journal

Multi-organ guided diagnosis of mild cognitive impairment via hierarchical alignment and knowledge distillation.

Medical image analysis·2026

Same journal

SUDA: Simultaneous unsupervised knowledge distillation and adaptation of foundation models for efficient pathological image analysis.

Medical image analysis·2026

Same journal

Beyond the LUMIR challenge: The pathway to foundational registration models.

Medical image analysis·2026

See all related articles

Search research articles

Related Experiment Video

Updated: Aug 25, 2025

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

Source-free domain adaptation for image segmentation.

Mathilde Bateson¹, Hoel Kervadec², Jose Dolz²

¹ÉTS Montréal, 1100 Notre-Dame St W, Montreal, Quebec H3C 1K3, Canada.

Medical Image Analysis

|October 13, 2022

Summary

This summary is machine-generated.

This study introduces source-free domain adaptation for image segmentation, enabling models to adapt to new data without source images, crucial for medical imaging privacy. The method uses prior knowledge to guide adaptation, achieving comparable results to existing techniques.

Keywords:

Deep networks Mutual information Prior knowledge Segmentation Shannon entropy Source-free domain adaptation

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

Related Experiment Videos

Last Updated: Aug 25, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

Area of Science:

Computer Vision
Medical Imaging
Machine Learning

Background:

Domain adaptation (DA) is vital for applying models across different data domains, but often requires access to source data.
Privacy concerns and data sharing limitations, especially in medical imaging, restrict the use of source images during adaptation.
Existing DA methods typically need concurrent access to both source and target domain images, limiting their applicability.

Purpose of the Study:

To develop a novel source-free domain adaptation (SFDA) method for image segmentation.
To address the challenge of adapting models to new domains without access to original source data, particularly in privacy-sensitive medical imaging applications.
To leverage anatomical priors and weak target labels for effective model adaptation.

Main Methods:

Introduced a source-free domain adaptation framework for image segmentation.
Formulated the adaptation using label-free entropy minimization on target data.
Integrated a class-ratio prior, derived from anatomical knowledge, via Kullback-Leibler divergence.
Explored the connection between the loss function and maximizing mutual information between target images and predictions.

Main Results:

Demonstrated effectiveness across diverse medical segmentation tasks (spine, prostate, cardiac) and modalities.
Achieved results comparable to state-of-the-art methods despite the absence of source images during adaptation.
Showcased a straightforward adaptation strategy using a single network, unlike complex adversarial techniques.
Validated the method's performance in challenging domain-adaptation scenarios.

Conclusions:

The proposed prior-aware entropy minimization is effective for source-free domain adaptation in image segmentation.
The method offers a practical solution for medical imaging segmentation where source data privacy is a concern.
The framework is versatile, applicable to various segmentation problems, and provides a valuable alternative to existing DA techniques.