文献速递肿瘤 PET/CT核素与放射性配体治疗

基于深度学习和影像组学框架对前列腺癌PSMA PET图像进行PSMA-RADS分类

Deep learning and radiomics framework for PSMA-RADS classification of prostate cancer on PSMA PET.
PubMed 文献 · EJNMMI Res · 2022-12-29

本研究为IRB批准、符合HIPAA的回顾性研究,对267例前列腺癌患者[18F]DCFPyL PET/CT的3794个病灶按PSMA-RADS分类并随机分为训练、验证和测试集,框架在测试集上病灶级和患者级PSMA-RADS分类的AUROC分别为0.87和0.90,病灶级和患者级前列腺癌分类的AUROC分别为0.92和0.85。

要点

  • 框架在测试集上病灶级与患者级PSMA-RADS分类AUROC分别为0.87和0.90。
  • 框架在测试集上病灶级与患者级前列腺癌分类AUROC分别为0.92和0.85。
  • 正确预测的平均置信度评分显著高于错误预测(P < 0.05)。

核心结论

  • 该框架可在PSMA PET图像上提供病灶级和患者级PSMA-RADS及前列腺癌分类。
  • 该框架具有可解释性,并提供置信度和概率评分,可能帮助医生做出更明智的临床决策。

研究设计与样本

  • 本研究为IRB批准、符合HIPAA的回顾性研究。
  • 267例前列腺癌患者的[18F]DCFPyL PET/CT扫描共3794个病灶被分配至PSMA-RADS类别,并随机分为训练集、验证集和测试集。

主要发现

  • 测试集上病灶级和患者级PSMA-RADS分类的AUROC分别为0.87和0.90。
  • 测试集上病灶级和患者级前列腺癌分类的AUROC分别为0.92和0.85。
  • t-SNE分析揭示了PSMA-RADS类别与疾病发现之间的学习关系。
  • 平均置信度评分反映了预期准确性,正确预测的置信度评分显著高于错误预测(P < 0.05)。
  • 测量的概率评分反映了与PSMA-RADS框架一致的前列腺癌可能性。

局限性

  • 原文未报告局限性。

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

BACKGROUND: Accurate classification of sites of interest on prostate-specific membrane antigen (PSMA) positron emission tomography (PET) images is an important diagnostic requirement for the differentiation of prostate cancer (PCa) from foci of physiologic uptake. We developed a deep learning and radiomics framework to perform lesion-level and patient-level classification on PSMA PET images of patients with PCa. METHODS: This was an IRB-approved, HIPAA-compliant, retrospective study. Lesions on [18F]DCFPyL PET/CT scans were assigned to PSMA reporting and data system (PSMA-RADS) categories and randomly partitioned into training, validation, and test sets. The framework extracted image features, radiomic features, and tissue type information from a cropped PET image slice containing a lesion and performed PSMA-RADS and PCa classification. Performance was evaluated by assessing the area under the receiver operating characteristic curve (AUROC). A t-distributed stochastic neighbor embedding (t-SNE) analysis was performed. Confidence and probability scores were measured. Statistical significance was determined using a two-tailed t test. RESULTS: PSMA PET scans from 267 men with PCa had 3794 lesions assigned to PSMA-RADS categories. The framework yielded AUROC values of 0.87 and 0.90 for lesion-level and patient-level PSMA-RADS classification, respectively, on the test set. The framework yielded AUROC values of 0.92 and 0.85 for lesion-level and patient-level PCa classification, respectively, on the test set. A t-SNE analysis revealed learned relationships between the PSMA-RADS categories and disease findings. Mean confidence scores reflected the expected accuracy and were significantly higher for correct predictions than for incorrect predictions (P < 0.05). Measured probability scores reflected the likelihood of PCa consistent with the PSMA-RADS framework. CONCLUSION: The framework provided lesion-level and patient-level PSMA-RADS and PCa classification on PSMA PET images. The framework was interpretable and provided confidence and probability scores that may assist physicians in making more informed clinical decisions.

来源:EJNMMI Res,查看原文。版权归原作者所有。

引用

  1. Leung KH, Rowe SP, Leal JP, et al. Deep learning and radiomics framework for PSMA-RADS classification of prostate cancer on PSMA PET. EJNMMI Res. 2022. PMID: 36580220. doi:10.1186/s13550-022-00948-1

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。