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

You might also read

Related Articles

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

Sort by
Same author

Evaluation of deep learning-based reconstruction models on non-TOF BGO PET/CT: impact of acquisition times and BSREM penalization factors on lesion detectability and SNR.

EJNMMI physics·2026
Same author

The impact of PSMA-PET/CT on clinical decision-making in primary staging of prostate cancer.

EJNMMI research·2026
Same author

Evaluating <sup>18</sup>F-FDG PET-CT for Regional Lymph Node Assessment in Advanced Upper Tract Urothelial Carcinoma.

European urology open science·2026
Same author

The Swedish national guidelines on prostate cancer: recurrent, metastatic and castration resistant disease.

Scandinavian journal of urology·2026
Same author

Phase I trial of locoregional administration of autologous tumor-infiltrating lymphocytes in patients with uveal melanoma and liver metastases (the HAITILS trial).

Journal for immunotherapy of cancer·2026
Same author

Prognostic value of tumour volume based on [<sup>18</sup>F]PSMA-1007 PET/CT in prostate cancer.

EJNMMI reports·2026

Related Experiment Video

Updated: Mar 7, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.6K

Validation of an AI Method for Automated Lymphoma Metabolic Tumor Volume Segmentation Using a Public Benchmark PET/CT

May Sadik1, Måns Larsson2, Olof Enqvist2,3

  • 1Department of Molecular and Clinical Medicine, Sahlgrenska University Hospital, Sahlgrenska Academy at University of Gothenburg, Gothenburg, Sweden.

Journal of Nuclear Medicine : Official Publication, Society of Nuclear Medicine
|March 5, 2026
PubMed
Summary

An artificial intelligence (AI) method accurately segmented total metabolic tumor volume (TMTV) in lymphoma PET/CT scans, matching expert performance on a benchmark dataset. This AI tool shows promise for reducing workload and variability in lymphoma imaging.

Keywords:
artificial intelligencebenchmark datasetdeep learninglymphomatotal metabolic tumor volume

More Related Videos

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
Utilizing 18F-FDG PET/CT Imaging and Quantitative Histology to Measure Dynamic Changes in the Glucose Metabolism in Mouse Models of Lung Cancer
06:51

Utilizing 18F-FDG PET/CT Imaging and Quantitative Histology to Measure Dynamic Changes in the Glucose Metabolism in Mouse Models of Lung Cancer

Published on: July 21, 2018

18.8K

Related Experiment Videos

Last Updated: Mar 7, 2026

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.6K
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
Utilizing 18F-FDG PET/CT Imaging and Quantitative Histology to Measure Dynamic Changes in the Glucose Metabolism in Mouse Models of Lung Cancer
06:51

Utilizing 18F-FDG PET/CT Imaging and Quantitative Histology to Measure Dynamic Changes in the Glucose Metabolism in Mouse Models of Lung Cancer

Published on: July 21, 2018

18.8K

Area of Science:

  • Oncology
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Accurate segmentation of total metabolic tumor volume (TMTV) is crucial for lymphoma staging and treatment assessment.
  • Manual segmentation of 18F-FDG PET/CT scans is time-consuming and prone to interreader variability.

Purpose of the Study:

  • To evaluate an AI-based method for automated TMTV segmentation in lymphoma patients.
  • To compare AI performance against expert readers using a benchmark dataset.

Main Methods:

  • A 3D U-Net AI model was trained on 1,500 18F-FDG PET/CT scans.
  • The model was tested on 60 benchmark scans (follicular lymphoma, Hodgkin lymphoma, diffuse large B-cell lymphoma) segmented by nuclear medicine physicians.
  • Agreement was assessed using Bland-Altman analysis with a 10% or 10 cm3 deviation threshold.

Main Results:

  • The AI method achieved TMTV segmentation within 10% or 10 cm3 of the benchmark reference in 83% of cases.
  • In 4 additional cases, AI results showed partial concordance with at least one expert reader.
  • The AI model demonstrated high concordance with expert-derived TMTV in a standardized benchmark setting.

Conclusions:

  • The AI-based method performs comparably to human experts in segmenting TMTV in lymphoma.
  • Automated segmentation can reduce manual workload and interreader variability in clinical practice.
  • Human supervision remains necessary for optimal accuracy and error minimization.