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 Experiment Video

Updated: Jun 12, 2026

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

Clinical application of AI for lung lobe segmentation and functional quantification with SPECT/CT: open-source versus

Elaheh Amini1,2,3, Maria Goemans4, Daniel Kyrollos5

  • 1Department of Nuclear Medicine and Molecular Imaging, The Ottawa Hospital, Ottawa, ON, Canada. eamini@ohri.ca.

Scientific Reports
|June 10, 2026
PubMed
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

Visual versus quantitative tau-PET Braak staging in Alzheimer's disease using [<sup>18</sup>F]MK6240.

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

Analytical Models to Optimize Tacrolimus Dosing in Solid Organ Transplantation: A Systematic Review.

Pharmaceutics·2026
Same author

Choroidal-ventricular system abnormalities are linked to amyloid-β aggregation in Alzheimer's disease.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2026
Same author

Isolated Occipital Lobe Hypometabolism on [<sup>18</sup>F]FDG PET.

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

Comparison of Planar and 3-Dimensional Methods for Quantification of Differential Renal Function Using <sup>99m</sup>Tc-DMSA and <sup>99m</sup>Tc-Glucoheptonate Renal Scintigraphy.

Journal of nuclear medicine technology·2025
Same author

Association of tumor markers CA 15-3, CEA, and CA 125 with [<sup>18</sup>F]NaF PET findings in breast cancer patients.

Frontiers in oncology·2025

This study shows that an in-house AI model significantly improves lung lobe quantification accuracy on SPECT/CT scans, especially in complex cases. Open-source models struggled with difficult scans, highlighting the need for robust AI in nuclear medicine.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Nuclear Medicine

Background:

  • Accurate lung lobe quantification using SPECT/CT is crucial for treatment planning but limited by current tools.
  • AI shows promise for improving SPECT/CT lobar quantification, but clinical validation is needed.

Purpose of the Study:

  • To compare the clinical accuracy of SPECT/CT-based lobar quantification using open-source and in-house developed AI segmentation models.
  • To evaluate the impact of an anatomy-aware modification on AI model performance, particularly in cases with missing lobes.

Main Methods:

  • A dataset of 200 diverse CT and SPECT scans with expert lobar annotations was curated and graded by difficulty.
  • An in-house AI model was trained and enhanced with an anatomy-aware softmax modification.
Keywords:
AI clinical integrationAI-based image segmentationLung lobe quantificationSPECT/CT quantification

More Related Videos

Unilateral Lung Volume Analysis Using Micro-CT for Enhanced Assessment of Pulmonary Fibrosis in Preclinical Models
03:38

Unilateral Lung Volume Analysis Using Micro-CT for Enhanced Assessment of Pulmonary Fibrosis in Preclinical Models

Published on: June 20, 2025

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging
10:44

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging

Published on: June 21, 2024

Related Experiment Videos

Last Updated: Jun 12, 2026

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

Unilateral Lung Volume Analysis Using Micro-CT for Enhanced Assessment of Pulmonary Fibrosis in Preclinical Models
03:38

Unilateral Lung Volume Analysis Using Micro-CT for Enhanced Assessment of Pulmonary Fibrosis in Preclinical Models

Published on: June 20, 2025

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging
10:44

Three-Dimensional Phase Resolved Functional Lung Magnetic Resonance Imaging

Published on: June 21, 2024

  • Lobar function error was computed after automated SPECT/CT coregistration and compared across local, open-source, and commercial models.

    • Main Results:

    • Open-source models showed significantly increased error standard-deviation with case complexity, especially in missing-lobe cases (0.57% to 5.79%).
    • The in-house local model and a commercial tool maintained high accuracy across all difficulties (0.51% to 1.4%).
    • The anatomy-aware modification eliminated false-positive lobe predictions, improving quantification accuracy.

    Conclusions:

    • AI-based tools can streamline routine lobar quantification with minimal physician oversight.
    • SPECT/CT lobar quantification benefits from robustness achieved through representative data training and anatomy-awareness.
    • While open-source models struggled with complex cases, they offered clinically acceptable results for typical anatomy and mild diseases.