PSMA‐Hornet: Fully‐automated, multi‐target segmentation of healthy organs in PSMA PET/CT images
Medical Physics · 2024-02 · 51 (2) · 1203-1216
DOI: 10.1002/mp.16658 ↗Kurz gefasst
Fachartikel in der Zeitschrift Medical Physics, online erschienen am 06.08.2023. Verfasst von Ivan S Klyuzhin und 6 weiteren Autor:innen. Beteiligte Einrichtung: Department of Integrative Oncology, BC Cancer Research Institute, Vancouver, BC, Canada. Hauptthemen laut MEDLINE: Prostatic Neoplasms, Antigens, Surface, Glutamate Carboxypeptidase II. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 24 Literaturangaben. Gefördert von: Canadian Institutes of Health Research Project, National Institutes of Health / Canadian Institutes of Health Research QIN.
Abstract (Originalsprache)
Background
Prostate‐specific membrane antigen (PSMA) PET imaging represents a valuable source of information reflecting disease stage, response rate, and treatment optimization options, particularly with PSMA radioligand therapy. Quantification of radiopharmaceutical uptake in healthy organs from PSMA images has the potential to minimize toxicity by extrapolation of the radiation dose delivery towards personalization of therapy. However, segmentation and quantification of uptake in organs requires labor‐intensive organ delineations that are often not feasible in the clinic nor scalable for large clinical trials.
Purpose
In this work we develop and test the PSMA Healthy organ segmentation network (PSMA‐Hornet), a fully‐automated deep neural net for simultaneous segmentation of 14 healthy organs representing the normal biodistribution of [ 18 F]DCFPyL on PET/CT images. We also propose a modified U‐net architecture, a self‐supervised pre‐training method for PET/CT images, a multi‐target Dice loss, and multi‐target batch balancing to effectively train PSMA‐Hornet and similar networks.
Methods
The study used manually‐segmented [ 18 F]DCFPyL PET/CT images from 100 subjects, and 526 similar images without segmentations. The unsegmented images were used for self‐supervised model pretraining. For supervised training, Monte‐Carlo cross‐validation was used to evaluate the network performance, with 85 subjects in each trial reserved for model training, 5 for validation, and 10 for testing. Image segmentation and quantification metrics were evaluated on the test folds with respect to manual segmentations by a nuclear medicine physician, and compared to inter‐rater agreement. The model's segmentation performance was also evaluated on a separate set of 19 images with high tumor load.
Results
With our best model, the lowest mean Dice coefficient on the test set was 0.826 for the sublingual gland, and the highest was 0.964 for liver. The highest mean error in tracer uptake quantification was 13.9% in the sublingual gland. Self‐supervised pretraining improved training convergence, train‐to‐test generalization, and segmentation quality. In addition, we found that a multi‐target network produced significantly higher segmentation accuracy than single‐organ networks.
Conclusions
The developed network can be used to automatically obtain high‐quality organ segmentations for PSMA image analysis tasks. It can be used to reproducibly extract imaging data, and holds promise for clinical applications such as personalized radiation dosimetry and improved radioligand therapy.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Substanzen
Autor:innen und Institutionen
- Department of Integrative Oncology, BC Cancer Research Institute, Vancouver, BC, Canada.
- AI for Health, Microsoft, Redmond, Washington, USA.
- Deparment of Radiology, University of British Columbia, Vancouver, BC, Canada.
- Department of Functional Imaging, BC Cancer, Vancouver, BC, Canada.
- Deparment of Physics and Astronomy, University of British Columbia, Vancouver, BC, Canada.
Förderung
- Canadian Institutes of Health Research Project
- National Institutes of Health / Canadian Institutes of Health Research QIN
Zitieren
APA
Klyuzhin, I. S., Chaussé, G., Bloise, I., Harsini, S., Ferres, J. L., Uribe, C., & Rahmim, A. (2024). PSMA‐Hornet: Fully‐automated, multi‐target segmentation of healthy organs in PSMA PET/CT images. Medical Physics, 51(2), 1203-1216. https://doi.org/10.1002/mp.16658
Vancouver
Klyuzhin IS, Chaussé G, Bloise I, Harsini S, Ferres JL, Uribe C, et al. PSMA‐Hornet: Fully‐automated, multi‐target segmentation of healthy organs in PSMA PET/CT images. Medical Physics. 2024;51(2):1203-1216. doi:10.1002/mp.16658
BibTeX
@article{Klyuzhin2024,
author = {Klyuzhin, Ivan S and Chaussé, Guillaume and Bloise, Ingrid and Harsini, Sara and Ferres, Juan Lavista and Uribe, Carlos and Rahmim, Arman},
title = {PSMA‐Hornet: Fully‐automated, multi‐target segmentation of healthy organs in PSMA PET/CT images},
journal = {Medical Physics},
year = {2024},
volume = {51},
number = {2},
pages = {1203--1216},
doi = {10.1002/mp.16658}
}
EUVIMED