EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Repeatability of Semi-Quantitative and Volumetric Features from Artificial-Intelligence-Guided Lesion Segmentation on 18F-DCFPyL PSMA-PET/CT Images: Results from a Test-Retest Cohort

Md Zobaer Islam iD, Timothy G Perk iD, Amy Weisman iD, Mark C Markowski iD, Kenneth J Pienta iD, Young E Whang iD, Matthew I Milowsky iD, Martin G Pomper iD, Nicholas Wisniewski, Ralph A Bundschuh, Rudolf A Werner iD, Michael A Gorin iD und 1 weitere

Tomography · 11.03.2026 · 12 (3) · 38

DOI: 10.3390/tomography12030038 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Tomography, online erschienen am 11.03.2026. Verfasst von Md Zobaer Islam und 12 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, University of Texas Southwestern Medical Center, Dallas, TX 75390, USA. Hauptthemen laut MEDLINE: Positron Emission Tomography Computed Tomography, Urea, Prostatic Neoplasms, Artificial Intelligence. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIBIB NIH HHS, prostate cancer foundation, Prostate Cancer Foundation Young Investigator Award.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objectives

This study evaluated the test–retest repeatability of semi-quantitative and volumetric features derived from artificial intelligence (AI)-assisted lesion segmentation on 18F-DCFPyL Prostate Specific Membrane Antigen (PSMA)-PET/CT imaging of patients with prostate cancer (PCa). Specifically, we assessed the reliability of maximum, minimum and total standardized uptake values (SUVmax, SUVmean, SUVtotal) and lesion volume measurements across varying lesion sizes and explored the implications of variability for clinical decision-making.

Methods

We analyzed 18F-DCFPyL PSMA-PET/CT images from 22 patients with metastatic PCa. Lesion segmentation was performed using the AI-guided TRAQinform IQ technology, followed by a manual review to eliminate potential false-positive sites of uptake. Lesion-level test–retest repeatability was evaluated using 95% limits of agreement (LOA), intra-class correlation coefficient (ICC), within-subject coefficient of variation (wCOV) and Bland–Altman analysis for SUV and volumetric parameters. Lesions were stratified by size (>1 cm3 and >1.5 cm3) to assess the impact of lesion volume cut-offs on measurement variability.

Results

A total of 297 lesions were analyzed, including 191 lesions > 1 cm3 and 161 lesions > 1.5 cm3. Test–retest variability was higher in smaller lesions, with narrower LOA and lower wCOV for larger lesions. SUVmax and SUVmean exhibited lower variability than SUVtotal and lesion volume. The 95% LOA for SUVmax ranged from −33.81% to +38.02% for all lesions, improving to −31.82% to +31.01% for lesions > 1.5 cm3. Similar trends were observed for SUVmean, SUVtotal, and volume. Bland–Altman plots confirmed reduced variability in larger lesions, with no significant systematic bias.

Conclusions

The test–retest repeatability of AI-assisted PSMA-PET/CT features varies by feature type, with semi-quantitative features demonstrating improved repeatability relative to volumetric features. Additionally, repeatability is influenced by lesion size, with larger lesions exhibiting greater reliability. These findings highlight the importance of lesion size-dependent thresholds in response assessment and variability-aware feature selection in prognostic models. Current algorithms may be better optimized for larger lesions and higher volumes of disease, with limitations remaining in the robust detection and segmentation of smaller/more subtle lesions.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Positron Emission Tomography Computed TomographyUreaProstatic NeoplasmsArtificial IntelligenceHumansMaleReproducibility of ResultsMiddle AgedAgedLysineRadiopharmaceuticalsGlutamate Carboxypeptidase IIGlutaratesPyridines

Stichwörter der Autor:innen

PET featuresPSMA-PET/CTartificial intelligencetest–retest

Substanzen

UreapiflufolastatLysineRadiopharmaceuticalsGlutamate Carboxypeptidase IIGlutaratesPyridines

Autor:innen und Institutionen

  • Department of Radiology, University of Texas Southwestern Medical Center, Dallas, TX 75390, USA.
  • AIQ Solutions, Madison, WI 53717, USA.
  • Sidney Kimmel Comprehensive Cancer Center, Johns Hopkins University School of Medicine, Baltimore, MD 21287, USA.
  • Division of Oncology, Department of Medicine, University of North Carolina, Chapel Hill, NC 27599, USA.
  • Department of Radiology, University of North Carolina, Chapel Hill, NC 27599, USA.
  • Department of Nuclear Medicine, Universitätsklinikum Carl Gustav Carus at the TU Dresden, 01307 Dresden, Germany.

ORCID-Profile: Md Zobaer Islam, Timothy G Perk, Amy Weisman, Mark C Markowski, Kenneth J Pienta, Young E Whang, Matthew I Milowsky, Martin G Pomper, Rudolf A Werner, Michael A Gorin

Förderung

  • NIBIB NIH HHS
  • prostate cancer foundation
  • Prostate Cancer Foundation Young Investigator Award

Zitieren

APA

Islam, M. Z., Perk, T. G., Weisman, A., Markowski, M. C., Pienta, K. J., Whang, Y. E., Milowsky, M. I., Pomper, M. G., Wisniewski, N., Bundschuh, R. A., Werner, R. A., Gorin, M. A., & Rowe, S. P. (2026). Repeatability of Semi-Quantitative and Volumetric Features from Artificial-Intelligence-Guided Lesion Segmentation on 18F-DCFPyL PSMA-PET/CT Images: Results from a Test-Retest Cohort. Tomography, 12(3), 38. https://doi.org/10.3390/tomography12030038

Vancouver

Islam MZ, Perk TG, Weisman A, Markowski MC, Pienta KJ, Whang YE, et al. Repeatability of Semi-Quantitative and Volumetric Features from Artificial-Intelligence-Guided Lesion Segmentation on 18F-DCFPyL PSMA-PET/CT Images: Results from a Test-Retest Cohort. Tomography. 2026;12(3):38. doi:10.3390/tomography12030038

BibTeX
@article{Islam2026,
  author = {Islam, Md Zobaer and Perk, Timothy G and Weisman, Amy and Markowski, Mark C and Pienta, Kenneth J and Whang, Young E and Milowsky, Matthew I and Pomper, Martin G and Wisniewski, Nicholas and Bundschuh, Ralph A and Werner, Rudolf A and Gorin, Michael A and Rowe, Steven P},
  title = {Repeatability of Semi-Quantitative and Volumetric Features from Artificial-Intelligence-Guided Lesion Segmentation on 18F-DCFPyL PSMA-PET/CT Images: Results from a Test-Retest Cohort},
  journal = {Tomography},
  year = {2026},
  volume = {12},
  number = {3},
  pages = {38},
  doi = {10.3390/tomography12030038}
}
Kostenlos starten →