cs.CVOct 29, 2026

Spatial Atlas-Informed Loss Ensembles for Whole-Body PSMA PET/CT Metastasis Segmentation

Authors: Grant N. Chau, Bashirul A. Biswas, Biratal Wagle, Matthew E. Maeder, Michael S. Leapman, James B. Yu, Indrani Bhattacharya

Organizations: Department of Computer Science, Dartmouth College, Hanover, NH, USA · Department of Biomedical Data Science, Geisel School of Medicine at Dartmouth, Hanover, NH, USA · Radiology, Dartmouth Hitchcock Medical Center, Lebanon, NH, USA · Department of Urology, Yale School of Medicine, New Haven, CT, USA · 

Abstract

Existing whole-body PSMA PET/CT prostate metastasis segmentation methods generally rely on images alone, without explicitly incorporating where metastases tend to occur. We investigate whether a population metastasis atlas can improve lesion detection when integrated into model training. We constructed voxel-wise mean and standard deviation maps from 375 expert-annotated training scans and used them to weight the cross-entropy loss of an nnU-Net. The additional penalties for missed lesions and false positives depend on spatial atlas statistics and diminish as predictions become confidently correct. Seven configurations were compared on validation data; three were combined by majority voting into SAILS (Spatial Atlas-Informed Loss enSemble). We compared SAILS with a baseline nnU-Net and inference-time atlas fusion on AutoPETIII (110 disease-positive cases) and Deep-PSMA (100 external cases). No atlas or registration is needed at inference. Results: On AutoPETIII, SAILS improved whole-body Dice (0.531 vs. 0.520; p=0.006), reduced missed-lesion volume (9.5 vs. 12.1 cc/case; p<0.01), and increased pooled lesion sensitivity (0.857 vs. 0.843; p=0.004). On Deep-PSMA, SAILS detected 126 additional reference lesions (sensitivity 0.769 vs. 0.751; p<0.001), without a significant whole-body Dice change (-0.009; p=0.36). High-risk bone Dice improved in both cohorts (0.576 vs. 0.552 and 0.667 vs. 0.653; both p<0.01). False-positive volume increased by 2.3 and 18.2 cc/case, respectively (p<0.001). Atlas-weighted training improves lesion detection, especially in high-risk bone, without test-time atlas registration, but increases false positives.

Figures & tables

Explore similar work

CardsList
  1. Improving PET/CT-Based Whole-Body Lesion Segmentation Using Prediction Uncertainty-Augmented Models

    Jun 8, 2026Bashirul Azam Biswas, Biratal Raj Wagle, Zhihan Yang +4Ensemble LearningPET/CT Imaging

  2. Anatomy-Aware Promptable Segmentation with Online Interactive Training for AUTOPET V

    Aug 28, 2026Pablo Lozano-Jimenez, Sergio Romero-Tapiador, Ruben TolosanaAnatomy-Guided Medical Image SegmentationMedical Image Segmentation

  3. MUST-PET: MUltimodal Self-supervised learning across Tracers for whole-body PET/CT-based lesion segmentation

    Aug 20, 2026Bashirul Azam Biswas, Amartya Bhattacharya, Biratal Raj Wagle +3Multimodal SSLPET/CT Tumor Segmentation