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: Jun 10, 2026

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

Label fusion in atlas-based segmentation using a selective and iterative method for performance level estimation

Thomas Robin Langerak¹, Uulke A van der Heide, Alexis N T J Kotte

¹Image Sciences Institute, University Medical Center Utrecht, 3508 GA Utrecht, The Netherlands. robin@isi.uu.nl

IEEE Transactions on Medical Imaging

|July 30, 2010

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

AI-based histopathology analysis predicts checkpoint inhibitor response in advanced melanoma and identifies patterns associated with response.

European journal of cancer (Oxford, England : 1990)·2026

Same author

DeepMultiConnectome: Deep multi-task prediction of structural connectomes directly from diffusion MRI tractography.

NeuroImage·2026

Same author

Deep learning motion correction of quantitative stress perfusion cardiovascular magnetic resonance.

Journal of cardiovascular magnetic resonance : official journal of the Society for Cardiovascular Magnetic Resonance·2026

Same author

Dosimetric comparison between brachytherapy and MR-Linac as a boost modality for locally advanced cervical cancer.

Clinical and translational radiation oncology·2026

Same author

Beyond accuracy: Quantifying the reliability of multiple instance learning for whole slide image classification.

PloS one·2025

Same author

Scaling up self-supervised learning for improved surgical foundation models.

Medical image analysis·2025

This study introduces a new method for combining medical image segmentations, improving accuracy in prostate cancer MRIs. The selective and iterative procedure for performance level estimation (SIMPLE) outperforms existing techniques.

Area of Science:

Medical image analysis
Computational anatomy
Radiology

Background:

Multi-atlas based segmentation requires effective label fusion of propagated segmentations.
Current methods either select atlases before/after registration or use performance estimation for weighting.

Purpose of the Study:

To propose a novel selective and iterative method for performance level estimation (SIMPLE).
To combine atlas selection and performance estimation for improved label fusion in medical image segmentation.

Main Methods:

SIMPLE iteratively refines estimated segmentation performance and the selected atlas set.
The method was evaluated on a dataset of 100 prostate cancer patient MR images.

Main Results:

More Related Videos

Enhancing Electrode Location Assessment in Cochlear Implantation via Computed Tomography Image Fusion

Enhancing Electrode Location Assessment in Cochlear Implantation via Computed Tomography Image Fusion

Published on: January 17, 2025

Related Experiment Videos

Last Updated: Jun 10, 2026

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

Enhancing Electrode Location Assessment in Cochlear Implantation via Computed Tomography Image Fusion

Enhancing Electrode Location Assessment in Cochlear Implantation via Computed Tomography Image Fusion

Published on: January 17, 2025

SIMPLE demonstrated significantly better segmentation results compared to existing methods.
Performance improvements were noted against STAPLE and weighted majority voting variants.

Conclusions:

The proposed SIMPLE method offers a superior approach to label fusion in multi-atlas segmentation.
This iterative strategy enhances segmentation accuracy for prostate cancer MR imaging.