文献速递肿瘤 PET/CT

基于卷积神经网络的胸腺上皮肿瘤18F-FDG PET/CT全自动定量测量

Fully Automatic Quantitative Measurement of 18F-FDG PET/CT in Thymic Epithelial Tumors Using a Convolutional Neural Network.
PubMed 文献 · Clin Nucl Med · 2022-04-27

本研究回顾性纳入186例可切除胸腺上皮肿瘤患者(145例胸腺瘤、41例胸腺癌),开发准三维U-net深度学习分割算法自动测量18F-FDG PET/CT代谢参数并与手动测量比较。自动测量的SUVmax、MTV、TLG与手动测量一致性良好(CCC 0.92-0.96),对胸腺癌诊断和无复发生存的预后价值与手动测量无显著差异。

要点

  • 深度学习模型自动分割胸腺上皮肿瘤的平均Dice相似系数为0.83±0.34。
  • 自动与手动测量的SUVmax、MTV、TLG一致性良好,CCC分别为0.92、0.96、0.96。
  • 自动与手动测量的AUC和HR无显著差异。

核心结论

  • 基于深度学习的模型在胸腺上皮肿瘤中提供了与手动测量相当的分割性能和代谢参数值。

研究设计与样本

  • 回顾性纳入186例 consecutive 可切除胸腺上皮肿瘤患者(145例胸腺瘤、41例胸腺癌),均有术前18F-FDG PET/CT。
  • 训练准三维U-net架构以模拟 ground-truth 感兴趣体积,用Dice相似系数评估分割性能。

主要发现

  • 平均Dice相似系数为0.83±0.34。
  • 自动测量的SUVmax(斜率0.97;CCC 0.92)、MTV(斜率0.94;CCC 0.96)、TLG(斜率0.96;CCC 0.96)与手动测量一致性良好。
  • 放射组学参数的平均CCC和斜率分别为0.88±0.06和0.89±0.05。
  • 自动测量的SUVmax、MTV、TLG对胸腺癌诊断准确性良好(AUC:SUVmax 0.95;MTV 0.85;TLG 0.87),预后价值显著(HR:SUVmax 1.31 [95%CI 1.16-1.48];MTV 2.11 [1.09-4.06];TLG 1.90 [1.12-3.23])。
  • 自动与手动测量之间任何代谢参数的AUC或HR均无显著差异。

关键数值与推荐

  • 原文未报告诊断阈值或推荐条款。

临床怎么用

  • 原文未据此给出临床推荐。

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

OBJECTIVES: The aim of this study was to develop a deep learning (DL)-based segmentation algorithm for automatic measurement of metabolic parameters of 18F-FDG PET/CT in thymic epithelial tumors (TETs), comparable performance to manual volumes of interest. PATIENTS AND METHODS: A total of 186 consecutive patients with resectable TETs and preoperative 18F-FDG PET/CT were retrospectively enrolled (145 thymomas, 41 thymic carcinomas). A quasi-3D U-net architecture was trained to resemble ground-truth volumes of interest. Segmentation performance was assessed using the Dice similarity coefficient. Agreements between manual and DL-based automated extraction of SUVmax, metabolic tumor volume (MTV), total lesion glycolysis (TLG), and 63 radiomics features were evaluated via concordance correlation coefficients (CCCs) and linear regression slopes. Diagnostic and prognostic values were compared in terms of area under the receiver operating characteristics curve (AUC) for thymic carcinoma and hazards ratios (HRs) for freedom from recurrence. RESULTS: The mean Dice similarity coefficient was 0.83 ± 0.34. Automatically measured SUVmax (slope, 0.97; CCC, 0.92), MTV (slope, 0.94; CCC, 0.96), and TLG (slope, 0.96; CCC, 0.96) were in good agreement with manual measurements. The mean CCC and slopes were 0.88 ± 0.06 and 0.89 ± 0.05, respectively, for the radiomics parameters. Automatically measured SUVmax, MTV, and TLG showed good diagnostic accuracy for thymic carcinoma (AUCs: SUVmax, 0.95; MTV, 0.85; TLG, 0.87) and significant prognostic value (HRs: SUVmax, 1.31 [95% confidence interval, 1.16-1.48]; MTV, 2.11 [1.09-4.06]; TLG, 1.90 [1.12-3.23]). No significant differences in the AUCs or HRs were found between automatic and manual measurements for any of the metabolic parameters. CONCLUSIONS: Our DL-based model provides comparable segmentation performance and metabolic parameter values to manual measurements in TETs.

来源:Clin Nucl Med,查看原文。版权归原作者所有。

引用

  1. Han S, Oh JS, Kim YI, et al. Fully Automatic Quantitative Measurement of 18F-FDG PET/CT in Thymic Epithelial Tumors Using a Convolutional Neural Network. Clin Nucl Med. 2022. PMID: 35675135. doi:10.1097/RLU.0000000000004146

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。