文献速递腹部泌尿生殖技术与安全CT

多期相CT纹理分析特征对实性肾脏肿块机器学习分类的期相增强重要性

Importance of phase enhancement for machine learning classification of solid renal masses using texture analysis features at multi-phasic CT.
PubMed 文献 · Abdom Radiol (NY) · 2020-07-05

本研究回顾性纳入177个实性肾脏肿块,提取平扫、皮髓质期和肾实质期CT的25个二维纹理分析特征,用XGBoost评估机器学习分类肾细胞癌与良性肿瘤、透明细胞肾细胞癌与其他肿瘤的效能。结果显示各期相AUC无显著差异,但用一期相训练、另一期相测试时模型性能下降,尤其平扫与增强CT之间。

要点

  • 纹理分析机器学习分类肾脏肿块的AUC不依赖CT期相,皮髓质期与肾实质期之间无显著差异。
  • 用一期相训练、另一期相测试时模型性能下降,平扫与增强CT之间尤为明显。
  • 该发现对使用不同CT协议研究肾脏肿块的大型注册研究有启示。

诊断标准与关键数值

  • 肾细胞癌 vs 良性肿瘤:皮髓质期增强CT的AUC为0.70(标准差0.19),敏感度96%、特异度32%;肾实质期增强CT的AUC为0.71(标准差0.14),敏感度83%、特异度58%。
  • 透明细胞肾细胞癌 vs 其他肿瘤:皮髓质期增强CT的AUC为0.77(标准差0.12),敏感度49%、特异度90%;肾实质期增强CT的AUC为0.71(标准差0.16),敏感度22%、特异度94%。
  • 增强CT与平扫CT的AUC比较无差异(p=0.058-0.54);联合三个期相数据较单期相评估无改善(p=0.39-0.68)。
  • 用一期相训练、另一期相测试时AUC下降:肾细胞癌 vs 良性肿瘤 p=0.045-0.106;透明细胞肾细胞癌 vs 其他肿瘤 p<0.001。

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)。

英文原文(摘要)· 点击展开

OBJECTIVE: To compare machine learning (ML) of texture analysis (TA) features for classification of solid renal masses on non-contrast-enhanced CT (NCCT), corticomedullary (CM) and nephrographic (NG) phase contrast-enhanced (CE) CT.

MATERIALS AND METHODS: With IRB approval, we retrospectively identified 177 consecutive solid renal masses (116 renal cell carcinoma [RCC]; 51 clear cell [cc], 40 papillary, 25 chromophobe and 61 benign tumors; 49 oncocytomas and 12 fat-poor angiomyolipomas) with renal protocol CT between 2012 and 2017. Tumors were independently segmented by two blinded radiologists. Twenty-five 2-dimensional TA features were extracted from each phase. Diagnostic accuracy for 1) RCC versus benign tumor and 2) cc-RCC versus other tumor was assessed using XGBoost.

RESULTS: ML of texture analysis features on different phases achieved mean area under the ROC curve (AUC [SD]), sensitivity/specificity for 1) RCC vs benign = 0.70(0.19), 96%/32% on CM-CECT and 0.71(0.14), 83%/58% on NG-CECT and; 2) cc-RCC vs other = 0.77(0.12), 49%/90% on CM-CECT and 0.71(0.16), 22%/94% on NG-CECT. There was no difference in AUC comparing CECT to NCCT (p = 0.058-0.54) and no improvement when combining data across all three phases compared single-phase assessment (p = 0.39-0.68) for either outcome. AUCs decreased when ML models were trained with one phase and tested on a different phase for both outcomes (RCC;p = 0.045-0.106, cc-RCC; < 0.001).

CONCLUSION: Accuracy of machine learning classification of renal masses using texture analysis features did not depend on phase; however, models trained using one phase performed worse when tested on another phase particularly when associating NCCT and CECT. These findings have implications for large registries which use varying CT protocols to study renal masses.

来源:Abdom Radiol (NY),查看原文。版权归原作者所有。

引用

  1. Schieda N, Nguyen K, Thornhill RE, et al. Importance of phase enhancement for machine learning classification of solid renal masses using texture analysis features at multi-phasic CT. Abdom Radiol (NY). 2020. PMID: 32627049. doi:10.1007/s00261-020-02632-1

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。