EUVIMEDEUVIMED entdecken
Open Access · CC0

Deep learning models built from PSMA PET of the primary tumor can predict synchronous and metachronous prostate cancer metastases

Jesus E Juarez Casillas iD, Maryam Nezafat, Cecil M Benitez, Kamil Rzechowski, Nathanael Kane, Karl Sjöstrand, Aseem Anand, Ida Sonni, Gholam R Berenji, Sai Duriseti, Matthew B Rettig iD, Nicholas G Nickols iD

PLOS One · 05.06.2026 · 21 (6) · e0349825

DOI: 10.1371/journal.pone.0349825 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, online erschienen am 05.06.2026. Verfasst von Jesus E Juarez Casillas und 11 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiation Oncology, David Geffen School of Medicine at UCLA, Los Angeles, California, United States of America. Hauptthemen laut MEDLINE: Prostatic Neoplasms, Deep Learning, Positron-Emission Tomography, Antigens, Surface. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC0). Gefördert von: This study was funded through a Cooperative Research and Development Agreement between VA Greater Los Angeles and Lantheus..

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

The objective was to develop prognostic models that included convolutional neural networks (CNN) derived from 18 F-DCFPyL (PSMA) PET imaging of the primary tumor uptake patterns to prognose early metastatic progression after curative intent treatment for localized prostate cancer.

Methods

Due to the lack of sufficient cases with adequate follow-up and metastatic events to derive this model directly, we derived models that predict the presence of synchronous metastases using only data obtained from the primary tumor. Because early metastatic progression events are consequent to occult metastases present at the time of initial therapy, we hypothesized that a model trained to predict synchronous metastases might also predict metachronous metastatic progression. A convolutional neural network (CNN) model was generated using whole-prostate PSMA PET images and auto-segmented intraprostatic lesions and combined with clinicopathologic data and imaging parameters to develop a multimodal model. Model performance was evaluated using the area under the receiver operating characteristic curve (AUC) for predicting synchronous metastases and metachronous metastatic progression.

Results

The multimodal model and CNN model had AUCs of 0.82 (95% CI 0.69–0.92, p < 0.005) and 0.72 (95% CI 0.55–0.84, p 0.0059), respectively, for prediction of synchronous metastases. Shapley additive explanation analysis showed the CNN had the largest contribution to the combined model performance. For metastatic progression, the multimodal model had an AUC of 0.839 (95% CI: 0.6763–1.000, p = 0.0064).

Conclusion

The multimodal model trained to predict synchronous metastases also predicted metachronous metastatic progression. This supports the potential of artificial intelligence applied to primary tumor PSMA PET images for enhanced prognostication. However, significant limitations include the modest sample size, single center source of data, and potential for overfitting, which may limit generalizability. Therefore, further validation in a larger cohort is indicated.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

Prostatic NeoplasmsDeep LearningPositron-Emission TomographyAntigens, SurfaceGlutamate Carboxypeptidase IIMaleHumansConvolutional Neural NetworksNeoplasm MetastasisPrognosisDisease ProgressionAgedMiddle Aged

Substanzen

Antigens, SurfaceGlutamate Carboxypeptidase IIFOLH1 protein, human

Autor:innen und Institutionen

  • Department of Radiation Oncology, David Geffen School of Medicine at UCLA, Los Angeles, California, United States of America.
  • Exini Diagnostics (subsidiary of Lantheus Holdings, Inc), Bedford, Massachusetts, United States of America.
  • Department of Radiation Oncology, VA Greater Los Angeles Healthcare System, Los Angeles, CA, United States of America.
  • Department of Radiology, David Geffen School of Medicine at UCLA, Los Angeles, California, United States of America.
  • Department of Medicine, VA Greater Los Angeles Healthcare System, Los Angeles, California, United States of America.
  • Department of Medicine, David Geffen School of Medicine at UCLA, Los Angeles, California, United States of America.

ORCID-Profile: Jesus E Juarez Casillas, Matthew B Rettig, Nicholas G Nickols

Förderung

  • This study was funded through a Cooperative Research and Development Agreement between VA Greater Los Angeles and Lantheus.

Zitieren

APA

Juarez Casillas, J. E., Nezafat, M., Benitez, C. M., Rzechowski, K., Kane, N., Sjöstrand, K., Anand, A., Sonni, I., Berenji, G. R., Duriseti, S., Rettig, M. B., & Nickols, N. G. (2026). Deep learning models built from PSMA PET of the primary tumor can predict synchronous and metachronous prostate cancer metastases. PLOS One, 21(6), e0349825. https://doi.org/10.1371/journal.pone.0349825

Vancouver

Juarez Casillas JE, Nezafat M, Benitez CM, Rzechowski K, Kane N, Sjöstrand K, et al. Deep learning models built from PSMA PET of the primary tumor can predict synchronous and metachronous prostate cancer metastases. PLOS One. 2026;21(6):e0349825. doi:10.1371/journal.pone.0349825

BibTeX
@article{JuarezCasillas2026,
  author = {Juarez Casillas, Jesus E and Nezafat, Maryam and Benitez, Cecil M and Rzechowski, Kamil and Kane, Nathanael and Sjöstrand, Karl and Anand, Aseem and Sonni, Ida and Berenji, Gholam R and Duriseti, Sai and Rettig, Matthew B and Nickols, Nicholas G},
  title = {Deep learning models built from PSMA PET of the primary tumor can predict synchronous and metachronous prostate cancer metastases},
  journal = {PLOS One},
  year = {2026},
  volume = {21},
  number = {6},
  pages = {e0349825},
  doi = {10.1371/journal.pone.0349825}
}
Kostenlos starten →