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 Concept Videos

Positron Emission Tomography01:29

Positron Emission Tomography

8.0K
Positron emission tomography (PET) is a medical imaging technique involving radiopharmaceuticals — substances that emit short-lived radiation. Although the first PET scanner was introduced in 1961, it took 15 more years before radiopharmaceuticals were combined with the technique and revolutionized its potential.
One of the main requirements of a PET scan is a positron-emitting radioisotope, which is produced in a cyclotron and then attached to a substance used by the part of the body...
8.0K
Imaging Studies II: Positron Emission Tomography and Scintigraphy01:25

Imaging Studies II: Positron Emission Tomography and Scintigraphy

724
Positron Emission Tomography (PET) is a medical imaging technique that provides crucial insights into the body's physiological functions at a molecular level. It is an indispensable resource for diagnosing, staging, and monitoring various illnesses, notably cancer, neurological disorders, and cardiovascular conditions.
Fundamental Principles of PET
724

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

A Novel Swarm Intelligence-Driven Feature Selection for Interpretable Machine Learning in Multiparametric MRI-Based GBM Overall Survival Analysis.

Cancers·2026
Same author

Classification of Biliary Strictures Using Real-Time Cholangioscopy Artificial Intelligence: The SMART-AI Trial.

Clinical gastroenterology and hepatology : the official clinical practice journal of the American Gastroenterological Association·2026
Same author

HPV-Associated Oropharyngeal Squamous Cell Carcinoma - Key Updates to the AJCC/UICC TNM9 Staging System.

Annals of surgical oncology·2026
Same author

Prostate cancer tissue mapping and stratification using DRAQ5 and Eosin fluorescent labels integrated with AI classification and segmentation algorithms.

PloS one·2026
Same author

Transostomy endoscopic vacuum therapy of anastomotic dehiscence after a low anterior resection.

VideoGIE : an official video journal of the American Society for Gastrointestinal Endoscopy·2026
Same author

An international multi-centre study to develop and validate federated learning-based prognostic models for anal cancer.

Nature communications·2026

Related Experiment Video

Updated: Mar 19, 2026

Human Brown Adipose Tissue Depots Automatically Segmented by Positron Emission Tomography/Computed Tomography and Registered Magnetic Resonance Images
09:21

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

Published on: February 18, 2015

12.7K

ATLAAS: an automatic decision tree-based learning algorithm for advanced image segmentation in positron emission

Beatrice Berthon1, Christopher Marshall, Mererid Evans

  • 1Wales Research & Diagnostic PET Imaging Centre, Cardiff University, CF14 4XN, Cardiff, UK.

Physics in Medicine and Biology
|June 9, 2016
PubMed
Summary
This summary is machine-generated.

A new decision tree algorithm, ATLAAS, automatically selects the best positron emission tomography (PET) automatic segmentation (PET-AS) method for radiotherapy planning. ATLAAS accurately predicts optimal segmentation, improving tumor delineation when the true contour is unknown.

More Related Videos

Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

11.2K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.7K

Related Experiment Videos

Last Updated: Mar 19, 2026

Human Brown Adipose Tissue Depots Automatically Segmented by Positron Emission Tomography/Computed Tomography and Registered Magnetic Resonance Images
09:21

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

Published on: February 18, 2015

12.7K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

11.2K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.7K

Area of Science:

  • Medical Imaging
  • Radiotherapy
  • Artificial Intelligence

Background:

  • Accurate tumor delineation on PET scans is essential for effective radiotherapy.
  • Current PET automatic segmentation (PET-AS) methods lack a consensus for optimal use across diverse tumor types.
  • Variability in manual segmentation introduces intra- and interobserver errors.

Purpose of the Study:

  • To develop a predictive segmentation model (ATLAAS) that automatically selects the best PET-AS method based on tumor characteristics.
  • To improve the accuracy and reliability of tumor delineation in radiotherapy planning.
  • To reduce variability in PET-AS by automating method selection.

Main Methods:

  • Developed ATLAAS, a supervised machine learning algorithm using decision trees.
  • Trained ATLAAS on 100 PET scans with known contours, incorporating nine PET-AS methods.
  • Decision trees predicted PET-AS accuracy (Dice Similarity Coefficient) based on tumor volume, SUV ratio, and texture metrics.
  • Evaluated ATLAAS performance on 85 PET scans from phantom studies.

Main Results:

  • ATLAAS demonstrated excellent accuracy across various phantom data.
  • The algorithm correctly predicted the optimal or near-optimal segmentation method in 93% of cases.
  • ATLAAS outperformed individual PET-AS methods, achieving a DSC of 0.881 on fillable phantom data and 0.819 on H&N phantom data.
  • All cases achieved DSCs above 0.650.

Conclusions:

  • ATLAAS is a robust automatic image segmentation algorithm utilizing decision tree predictive modeling.
  • The model can be trained on images with known contours to predict the best PET-AS method for unknown contours.
  • ATLAAS offers accurate and reliable image segmentation with significant potential for radiation oncology applications.