Refining deep learning segmentation in gallium-68-prostate-specific membrane antigen-11 positron emission tomography: evaluation of small lesion filtering and intersection-over-union thresholds
- 29 January 2026
- journal article
- Published by Wolters Kluwer Health in Nuclear Medicine Communications
- Vol. 47 (5) , 552-562
Abstract
Purpose: Evaluate how small lesion filtering and different intersection-over-union (IoU) thresholds influence deep learning segmentation of Ga-68-PSMA-11 PET images in prostate cancer. Methods: A 3D U-Net was trained on 115 patient scans with manual contours as ground truth. Performance was assessed at voxel, lesion and patient levels. Lesions less than 8 voxels (195 mm 3 ) or less than 27 voxels (658 mm 3 ) were optionally discarded, and lesion-level metrics were computed across 10–50% IoU thresholds. Results: Excluding lesions less than 27 voxels increased voxel-level Dice from 0.7975 to 0.8173 and improved precision. Lesion-level metrics were stable across IoU thresholds of 20–40% after 27-voxel filtering, while sensitivity declined at higher overlap thresholds. Patient-level sensitivity and positive predictive value reached 96.6 and 94.5%, respectively. Conclusion: Implementing small lesion filtering criteria improves the reliability of automated segmentation outputs, particularly for quantitative evaluation. For lesion-level metrics, defining true positives within the range of 20–40% IoU thresholds is optimal. Further validation through multicenter studies and larger datasets is essential to ensure the generalizability of these findings.Keywords
This publication has 23 references indexed in Scilit:
- A convolutional neural network–based system for fully automatic segmentation of whole-body [68Ga]Ga-PSMA PET images in prostate cancerEuropean Journal of Nuclear Medicine and Molecular Imaging, 2023
- A convolutional neural network with self-attention for fully automated metabolic tumor volume delineation of head and neck cancer in $[^{18}$F]FDG PET/CTEuropean Journal of Nuclear Medicine and Molecular Imaging, 2023
- Role of [68Ga]Ga-PSMA-11 PET radiomics to predict post-surgical ISUP grade in primary prostate cancerEuropean Journal of Nuclear Medicine and Molecular Imaging, 2023
- PSMA and FDG-PET as predictive and prognostic biomarkers in patients given [177Lu]Lu-PSMA-617 versus cabazitaxel for metastatic castration-resistant prostate cancer (TheraP): a biomarker analysis from a randomised, open-label, phase 2 trialThe Lancet Oncology, 2022
- Fully automatic prognostic biomarker extraction from metastatic prostate lesion segmentations in whole-body [68Ga]Ga-PSMA-11 PET/CT imagesEuropean Journal of Nuclear Medicine and Molecular Imaging, 2022
- Lutetium-177–PSMA-617 for Metastatic Castration-Resistant Prostate CancerNew England Journal of Medicine, 2021
- E-PSMA: the EANM standardized reporting guidelines v1.0 for PSMA-PETEuropean Journal of Nuclear Medicine and Molecular Imaging, 2021
- nnU-Net: a self-configuring method for deep learning-based biomedical image segmentationNature Methods, 2020
- Prostate-specific membrane antigen PET-CT in patients with high-risk prostate cancer before curative-intent surgery or radiotherapy (proPSMA): a prospective, randomised, multicentre studyThe Lancet, 2020
- The use of molecular volumetric parameters for the evaluation of Lu-177 PSMA I&T therapy response and survivalAnnals of Nuclear Medicine, 2019