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

Behavioral and functional characterization of early-stage Parkinson's disease models reveals attentional deficits and circuit-level connectivity alterations.

Experimental neurology·2026

Same author

Management of Hemodialyzed Patients Treated with Radioactive Iodine for Thyroid Cancer: How Could We Improve It? Tracks from the Lille Experience.

Journal of nuclear medicine : official publication, Society of Nuclear Medicine·2026

Same author

[<sup>18</sup>F]FDG PET/CT imaging in Polyarteritis Nodosa-spectrum vasculitis.

Seminars in nuclear medicine·2026

Same author

Does a patient who needs portal vein embolization (PVE) to proceed to major hepatectomy (MH) have the same hepatic functional reserve than a patient with no preoperative PVE?

Hepatobiliary surgery and nutrition·2026

Same author

[<sup>18</sup>F]FDG PET/CT value in the diagnostic evaluation of patients with polyarteritis nodosa.

European journal of nuclear medicine and molecular imaging·2026

Same author

Electroencephalography microstates detect early cognitive impairment in Parkinson's disease.

Parkinsonism & related disorders·2026

Search research articles

Related Experiment Video

Updated: Mar 30, 2026

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

Is STAPLE algorithm confident to assess segmentation methods in PET imaging?

Anne-Sophie Dewalle-Vignion¹, Nacim Betrouni, Clio Baillet

¹Université Lille, Inserm, CHU Lille, U1189-ONCO-THAI-Image Assisted Laser Therapy for Oncology, F-59000 Lille, France.

Physics in Medicine and Biology

|November 20, 2015

Summary

The Simultaneous Truth and Performance Level Estimation (STAPLE) algorithm improves tumor segmentation accuracy in [18F]-fluorodeoxyglucose positron emission tomography (PET) imaging. It provides a more reliable ground truth than manual delineations or automatic methods alone for radiation therapy planning.

More Related Videos

Human Brown Adipose Tissue Depots Automatically Segmented by Positron Emission Tomography/Computed Tomography and Registered Magnetic Resonance Images

Human Brown Adipose Tissue Depots Automatically Segmented by Positron Emission Tomography/Computed Tomography and Registered Magnetic Resonance Images

Published on: February 18, 2015

High-Resolution Cardiac Positron Emission Tomography/Computed Tomography for Small Animals

High-Resolution Cardiac Positron Emission Tomography/Computed Tomography for Small Animals

Published on: December 16, 2022

Related Experiment Videos

Last Updated: Mar 30, 2026

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

Human Brown Adipose Tissue Depots Automatically Segmented by Positron Emission Tomography/Computed Tomography and Registered Magnetic Resonance Images

Human Brown Adipose Tissue Depots Automatically Segmented by Positron Emission Tomography/Computed Tomography and Registered Magnetic Resonance Images

Published on: February 18, 2015

High-Resolution Cardiac Positron Emission Tomography/Computed Tomography for Small Animals

High-Resolution Cardiac Positron Emission Tomography/Computed Tomography for Small Animals

Published on: December 16, 2022

Area of Science:

Medical Imaging
Radiotherapy
Computational Radiology

Background:

Accurate tumor segmentation in [18F]-fluorodeoxyglucose positron emission tomography (PET) is vital for assessing treatment response and defining radiation therapy targets.
Evaluating segmentation methods often relies on manual physician delineations, which can introduce variability.
The Simultaneous Truth and Performance Level Estimation (STAPLE) algorithm offers a potential solution for managing multi-observer variability.

Purpose of the Study:

To evaluate the accuracy of the STAPLE algorithm in estimating the ground truth for tumor segmentation in PET imaging.
To compare the performance of STAPLE against manual delineations and automatic segmentation results.

Main Methods:

A complete evaluation study using various criteria was conducted on simulated PET data.
The STAPLE algorithm was applied to both manual and automatic tumor segmentation results.
A specific configuration of the STAPLE implementation from the Computational Radiology Laboratory was utilized.

Main Results:

The consensus segmentation generated by STAPLE from manual delineations showed higher accuracy (80% overlap) than individual manual delineations.
Applying STAPLE to automatic segmentation results also led to improved accuracy.
STAPLE demonstrated superior performance compared to manual delineations or automatic segmentations used in isolation.

Conclusions:

The STAPLE algorithm, with the tested configuration, is a more appropriate method for estimating ground truth in PET tumor segmentation.
It offers a more reliable basis for assessing the accuracy of segmentation methods in PET imaging.
STAPLE may be preferred over relying solely on manual or automatic segmentation results for clinical applications.