文献速递肿瘤 PET/CT核素与放射性配体治疗

PET/CT影像中的人工智能病灶追踪:一种应用于PSMA PET/CT扫描的孪生CNN流程提案

AI lesion tracking in PET/CT imaging: a proposal for a Siamese-based CNN pipeline applied to PSMA PET/CT scans.
PubMed 文献 · Eur J Nucl Med Mol Imaging · 2025-07-08

本研究提出一种孪生卷积神经网络(CNN)流程,用于在基线和随访[68Ga]Ga-或[18F]F-PSMA PET/CT扫描之间追踪骨病灶,数据来自接受两周期[177Lu]Lu-PSMA治疗的转移性去势抵抗性前列腺癌患者。最佳配置下CNN分类病灶对应关系的准确率达83%、AUC为0.91,对应病灶的追踪准确率达89%。作者认为CNN可能有助于PSMA PET/CT中多病灶的追踪,未来需临床研究验证其能否改善治疗结局预测。

要点

  • 孪生CNN流程在PSMA PET/CT中追踪骨病灶,最佳配置分类准确率83%、AUC 0.91。
  • 对应病灶的追踪准确率达89%。
  • 作者认为CNN可能有助于多病灶追踪,未来需临床研究验证。

核心结论

  • 作者证明CNN可能有助于PSMA PET/CT扫描中多个病灶的追踪。
  • 未来需临床研究验证该流程能否改善治疗结局的预测。

研究设计与样本

  • 本研究在转移性去势抵抗性前列腺癌患者接受两周期[177Lu]Lu-PSMA治疗后的全身基线及随访[68Ga]Ga-或[18F]F-PSMA PET/CT扫描上,应用孪生CNN流程追踪大量骨病灶。
  • 数据准备包括病灶分割和仿射配准,算法提取合适病灶图像块并输入孪生CNN,训练其将病灶图像块对分类为对应或非对应病灶。
  • 实验采用不同输入图像块类型及2D和3D孪生网络进行。

主要发现

  • CNN模型成功学习分类病灶对应关系,最佳配置准确率达83%,AUC=0.91。
  • 对应病灶的流程追踪准确率达89%。

临床怎么用

  • 原文未据此给出临床推荐。

局限性

  • 未来需临床研究验证该流程能否改善治疗结局预测。

以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。

原文

PURPOSE: Assessing tumor response to systemic therapies is one of the main applications of PET/CT. Routinely, only a small subset of index lesions out of multiple lesions is analyzed. However, this operator dependent selection may bias the results due to possible significant inter-metastatic heterogeneity of response to therapy. Automated, AI-based approaches for lesion tracking hold promise in enabling the analysis of many more lesions and thus providing a better assessment of tumor response. This work introduces a Siamese CNN approach for lesion tracking between PET/CT scans. METHODS: Our approach is applied on the laborious task of tracking a high number of bone lesions in full-body baseline and follow-up [68Ga]Ga- or [18F]F-PSMA PET/CT scans after two cycles of [177Lu]Lu-PSMA therapy of metastatic castration resistant prostate cancer patients. Data preparation includes lesion segmentation and affine registration. Our algorithm extracts suitable lesion patches and forwards them into a Siamese CNN trained to classify the lesion patch pairs as corresponding or non-corresponding lesions. RESULTS: Experiments have been performed with different input patch types and a Siamese network in 2D and 3D. The CNN model successfully learned to classify lesion assignments, reaching an accuracy of 83 % in its best configuration with an AUC = 0.91. For corresponding lesions the pipeline accomplished lesion tracking accuracy of even 89 %. CONCLUSION: We proved that a CNN may facilitate the tracking of multiple lesions in PSMA PET/CT scans. Future clinical studies are necessary if this improves the prediction of the outcome of therapies.

来源:Eur J Nucl Med Mol Imaging,查看原文。版权归原作者所有。

引用

  1. Hein SP, Schultheiss M, Gafita A, et al. AI lesion tracking in PET/CT imaging: a proposal for a Siamese-based CNN pipeline applied to PSMA PET/CT scans. Eur J Nucl Med Mol Imaging. 2025. PMID: 40627160. doi:10.1007/s00259-025-07426-5

供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。