用AI自动分割前列腺癌PSMA PET/CT肿瘤，预测生存期。
Fine-UNETR for PSMA PET/CT Lesion Segmentation: Automated Tumor Quantification and Overall Survival Stratification in Prostate Cancer
- 基于视觉变压器的Fine-UNETR模型，结合滑动窗口训练提升小病灶检测。
- 在内部数据上病灶分割Dice达66.63%，外部数据上检测率仍达87.18%。
- 自动量化肿瘤体积等指标可显著区分患者生存期，适合放疗前预后评估。
本研究回顾性分析了373例前列腺癌患者的PSMA PET/CT扫描（平均年龄71±8岁），开发并评估了基于视觉变压器的Fine-UNETR模型，用于全身影像中PSMA高摄取病灶的自动分割。该模型采用8×8×8体素分块嵌入和轴向滑动窗口训练，在299例数据上训练，74例验证。在独立队列67例放疗前患者中，通过Kaplan-Meier与log-rank检验评估总生存率分层。外部验证使用AutoPET IV PSMA PET/CT数据集中的192例。结果表明，Fine-UNETR在内部数据上达到66.63%的Dice相似系数、70.27%敏感度、67.77%精确度及79.53%病灶检出率（SUVmax≥5者达96.05%）。外部验证中Dice为44.11%，病灶检出率达87.18%，显示尽管存在域偏移，检测性能仍保持良好。AI衍生生物标志物与真实值高度一致（总肿瘤体积：r=0.984；总病灶摄取：r=0.989；病灶数量：r=0.960）。在临床队列中，总肿瘤体积（p=0.0019）、SUVmax（p=0.014）和SUVmean（p=0.016）均显著分层总体生存率。结论：Fine-UNETR能准确实现全身影像中PSMA病灶分割与肿瘤负荷量化，其生成的生物标志物具有显著预后价值。
原文摘要 · Abstract (English)
Introduction: To develop and evaluate Fine-UNETR, a Vision Transformer-based architecture for automated segmentation of PSMA-avid lesions on whole-body PET/CT, and to assess clinical utility of AI-derived tumor burden biomarkers for overall survival stratification in radioligand therapy. Methods: In this retrospective study, 373 PSMA PET/CT scans (mean age, 71+-8 years) from patients with prostate cancer were analyzed. Fine-UNETR, a modified UNETR with 8x8x8 voxel patch embedding and axial sliding window training, was trained on 299 scans and validated on 74 scans. Overall survival stratification was assessed in an independent cohort of 67 pre-radioligand therapy patients using Kaplan-Meier analysis and log-rank testing. External validation was performed on 192 cases from the AutoPET IV PSMA PET/CT dataset. Results: Fine-UNETR achieved a Dice similarity coefficient (DSC) of 66.63%, sensitivity of 70.27%, precision of 67.77%, and a lesion detection rate of 79.53% (96.05% for lesions with SUVmax >= 5). On the external validation dataset, the model achieved a DSC of 44.11% and a lesion detection rate of 87.18%, indicating that lesion detection performance was preserved despite reduced voxel-level overlap. AI-derived biomarkers showed excellent agreement with ground truth (total tumor volume: r=0.984; total lesion uptake: r=0.989; lesion count: r=0.960). In the clinical cohort, total tumor volume (p=0.0019), SUVmax (p=0.014), and SUVmean (p=0.016) significantly stratified overall survival. Conclusion: Fine-UNETR enables accurate automated whole-body PSMA lesion segmentation and tumor burden quantification. Performance on an external dataset demonstrates robustness despite evidence of domain shift. AI-derived biomarkers significantly stratified overall survival in a pre-radioligand therapy cohort, supporting the clinical utility of automated PSMA PET/CT quantification for prognostication.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。