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

Overall Survival with [<sup>177</sup>Lu]Lu-PSMA-617 Versus [<sup>177</sup>Lu]Lu-PSMA I&T: A Propensity Score-Matched Real-World Analysis.

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

Direct Androgen Receptor Antagonism Enhances Therapeutic PSMA Radioligand Uptake in Prostate Cancer Models.

Molecular imaging and biology·2026
Same author

CXCR4-targeted PET/CT in early systemic sclerosis-associated interstitial lung disease: a prospective proof-of-concept study of in vivo inflammatory activity.

European journal of nuclear medicine and molecular imaging·2026
Same author

Quantitative accuracy of <sup>177</sup>Lu SPECT/CT imaging using ring-shaped CZT versus dual-head NaI systems.

EJNMMI physics·2026
Same author

Factors Influencing Double-Strand Break Focus Biodosimetry for Detection of Internal Low-LET Irradiation in Human Blood Samples.

Radiation research·2026
Same author

Applications of artificial intelligence in nuclear medicine.

Zeitschrift fur medizinische Physik·2026

Related Experiment Video

Updated: Jul 17, 2025

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

2.8K

PSMA-PET improves deep learning-based automated CT kidney segmentation.

Julian Leube1, Matthias Horn1, Philipp E Hartrampf1

  • 1University Hospital Würzburg, Department of Nuclear Medicine, Oberdürrbacher Str. 6, 97080 Würzburg, Germany.

Zeitschrift Fur Medizinische Physik
|September 4, 2023
PubMed
Summary
This summary is machine-generated.

Incorporating PET-based pre-segmentation significantly improves deep learning-based kidney segmentation for radiopharmaceutical therapy dosimetry. This approach enhances accuracy, especially for complex kidney anatomies, reducing calculation time.

Keywords:
Artificial intelligenceAutomatic segmentationDeep-learning based CT segmentationKidney segmentationPET/CT imaging

More Related Videos

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
08:05

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

14.2K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

441

Related Experiment Videos

Last Updated: Jul 17, 2025

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

2.8K
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
08:05

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

14.2K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

441

Area of Science:

  • Medical Imaging
  • Radiopharmaceutical Therapy
  • Artificial Intelligence in Medicine

Background:

  • Accurate dosimetry in radiopharmaceutical therapies requires precise organ segmentation, with kidneys being critical organs-at-risk.
  • Manual kidney segmentation is time-consuming; deep learning methods using CT data have been developed for automated segmentation.
  • Previous automated methods relied solely on CT, prompting an investigation into the added value of incorporating PSMA-PET data.

Purpose of the Study:

  • To evaluate the impact of integrating PSMA-PET data into deep learning models for automated kidney segmentation.
  • To compare the performance of CT-only segmentation with methods incorporating PET-based information.

Main Methods:

  • Developed and tested five U-Net based deep learning approaches for automated kidney segmentation using CT and/or PET data from 108 PET/CT examinations.
  • Included methods using CT only, PET only, combined CT and PET, CT with a coarse PET mask, and CT pre-segmented with a PET mask.
  • Quantitative assessment involved Dice score, volume deviation, and Hausdorff distance on a 20-patient test set, with visual evaluation by a nuclear physician on 100 additional patients.

Main Results:

  • The best performance was achieved using CT images pre-segmented with a PET-based coarse mask.
  • This PET-enhanced method significantly outperformed CT-only segmentation, as confirmed by visual evaluation.
  • Nuclear physicians preferred segmentations utilizing PET-based pre-segmentation in 80% of cases.

Conclusions:

  • Integrating PET-based pre-segmentation substantially enhances deep learning-based kidney segmentation accuracy for dosimetry.
  • The method is particularly beneficial for kidneys with cysts or those adjacent to other organs, improving segmentation in challenging cases.
  • This advancement promises to reduce dosimetry calculation time and improve overall accuracy in radiopharmaceutical therapy.