Prostate-Specific Membrane Antigen PET/CT Segmentation Guided by Vision Language Models Embedding Clinical Report Semantics
Journal of Nuclear Medicine · 12.11.2026 · jnumed.126.272702
DOI: 10.2967/jnumed.126.272702 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Nuclear Medicine, online erschienen am 12.11.2026. Verfasst von Mahan Pouromidi und 9 weiteren Autor:innen. Beteiligte Einrichtung: Department of Basic and Translational Research, BC Cancer Research Institute, Vancouver, British Columbia, Canada. Die Arbeit nennt 31 Literaturangaben.
Abstract (Originalsprache)
Whole-body prostate-specific membrane antigen (PSMA) PET/CT segmentation remains challenging: manual contouring is unsustainable, and image-only artificial intelligence models often misclassify physiologic uptake as malignant, causing high false-positive rates. These limitations underscore the need for segmentation strategies that incorporate the nuclear medicine expertise encoded in PET/CT reports but not used by current models. We investigated whether routine PET/CT reports improve automated lesion segmentation for prostate cancer.
Methods
We developed a language-guided 3-dimensional SegResNet fusing report text with 68Ga-PSMA-11 PET/CT image features, encoding report semantics via 4 strategies (BiomedVLP, RadGraph, GPT-raw, GPT-engineered) compared with an image-only model (baseline). Of 320 patients who underwent 68Ga-PSMA-11 PET/CT, 297 studies were available; 13 were excluded for missing reports or incomplete image-mask pairs, leaving 284 for analysis, split at the patient level into 243 development cases and a fixed 41-case held-out test set. Metrics included Dice, intersection over union (IoU), precision, recall, average symmetric surface distance, 95th percentile Hausdorff distance, surface Dice similarity at 5 mm, and lesion-level false positives, using 3 matching criteria (any overlap; 1-to-1 maximum IoU matching, IoU ≥ 0.5; and correct localization of the SUVmax voxel). Significance was assessed using paired 1-sided Wilcoxon tests with Holm adjustment.
Results
Report guidance consistently reduced false positives and improved whole-mask boundary agreement. False-positive lesions were reduced by nearly 4 per patient with BiomedVLP and by approximately 3 per patient with RadGraph and GPT-raw. Average symmetric surface distance decreased from 105.4 ± 62.5 mm (image only) to 23.4 ± 18.2 mm with BiomedVLP, 36.9 ± 22.4 mm with RadGraph, and 36.3 ± 26.4 mm with GPT-raw; 95th percentile Hausdorff distance improved from 455.0 ± 169.3 mm to 123.8 ± 80.3 mm with BiomedVLP, and surface Dice similarity at 5 mm increased from 0.638 ± 0.172 to 0.705 ± 0.181. However, when these surface metrics were recomputed on matched true-positive lesions only using the same 3 criteria, no language-guided model differed significantly from the image-only model for any surface metric (all Holm-adjusted P = 1.0), indicating that the whole-mask improvements were attributable to false-positive suppression rather than genuine gains in contour accuracy on correctly detected lesions. Precision increased for BiomedVLP (0.099) and RadGraph (0.060), with a modest decrease in voxel-level recall (-0.051, BiomedVLP), reflecting a precision-recall trade-off from suppression of spurious uptake. Dice improved by 0.032 but was borderline significant; IoU increased for BiomedVLP (0.036). Lesion-level sensitivity changed by no more than 0.04 for all models and did not reach significance. Total lesion PSMA remained highly correlated with manual measurements (r ≥ 0.85), whereas PSMA tumor volume correlations were more variable across models (r = 0.37-0.70).
Conclusion
The integration of PET/CT report semantics into automated PSMA PET/CT segmentation substantially reduced false-positive lesions and preserved total lesion PSMA agreement with manual measurements; a matched true-positive-only reanalysis indicated that the accompanying whole-mask boundary-agreement gains reflected false-positive suppression rather than improved contour accuracy on correctly detected lesions. This approach may reduce manual cleanup and support more reliable quantitative workflows, although precision gains should be weighed against a modest recall reduction. External validation, extension of the true-positive-only analysis to independent cohorts, and PSMA-specific language pretraining are warranted.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Basic and Translational Research, BC Cancer Research Institute, Vancouver, British Columbia, Canada.
- Department of Radiology, University of British Columbia, Vancouver, British Columbia, Canada.
- Department of Medical Radiation Engineering, Shahid Beheshti University, Tehran, Iran.
- Shahid Beheshti University of Medical Sciences, Tehran, Iran.
- Nuclear Medicine Centre, Jam Hospital, Tehran, Iran.
- Khatam PET/CT Centre, Tehran, Iran.
Zitieren
APA
Pouromidi, M., Bayasi, N., Samimi, R., Hosseinzadeh, E., Divband, G., Nickkholgh, B., Adinehpour, Z., Shafiee Dastgerdi, S., Rahmim, A., & Yousefirizi, F. (2026). Prostate-Specific Membrane Antigen PET/CT Segmentation Guided by Vision Language Models Embedding Clinical Report Semantics. Journal of Nuclear Medicine, jnumed.126.272702. https://doi.org/10.2967/jnumed.126.272702
Vancouver
Pouromidi M, Bayasi N, Samimi R, Hosseinzadeh E, Divband G, Nickkholgh B, et al. Prostate-Specific Membrane Antigen PET/CT Segmentation Guided by Vision Language Models Embedding Clinical Report Semantics. Journal of Nuclear Medicine. 2026:jnumed.126.272702. doi:10.2967/jnumed.126.272702
BibTeX
@article{Pouromidi2026,
author = {Pouromidi, Mahan and Bayasi, Nourhan and Samimi, Rezvan and Hosseinzadeh, Elinaz and Divband, Ghasemali and Nickkholgh, Babak and Adinehpour, Zohreh and Shafiee Dastgerdi, Shaghayegh and Rahmim, Arman and Yousefirizi, Fereshteh},
title = {Prostate-Specific Membrane Antigen PET/CT Segmentation Guided by Vision Language Models Embedding Clinical Report Semantics},
journal = {Journal of Nuclear Medicine},
year = {2026},
pages = {jnumed.126.272702},
doi = {10.2967/jnumed.126.272702}
}
EUVIMED