文献速递腹部CT

深度学习图像重建在胰腺癌可切除性预测中的效果:诊断性能与阅片者信心

Effect of deep learning image reconstruction in the prediction of resectability of pancreatic cancer: Diagnostic performance and reader confidence.
PubMed 文献 · Eur J Radiol · 2021-06-11

回顾性分析47例经病理证实的胰腺癌患者的基线多期增强CT,比较FBP、ASiR-V 60%与DLIR低、中、高强度重建。DLIR-H预测R0切除的平均AUC为0.91,显著高于FBP的0.75和ASiR-V的0.81;DLIR较FBP和ASiR-V 60%显著提高阅片者信心,且DLIR-H的阅片者间一致性最高。

要点

  • DLIR-H预测R0切除的平均AUC为0.91,高于FBP的0.75和ASiR-V的0.81。
  • DLIR较FBP和ASiR-V 60%显著提高阅片者信心,且信心随DLIR强度等级线性增加。
  • DLIR-H在可切除性分类中阅片者间一致性最高,阅片者信心主观变异最低。

核心结论

  • DLIR-H算法可能改善CT对胰腺癌局部可切除性评估的诊断性能和阅片者信心,同时降低阅片者间变异。

研究设计与样本

  • 回顾性研究纳入47例经病理证实的胰腺癌患者,均接受基线多期增强CT;图像采用FBP、ASiR-V 60%及DLIR TrueFidelity低、中、高强度重建,由4名委员会认证的腹部放射科医生阅片。

诊断标准与关键数值

  • 以R0切除为参考标准,DLIR-H预测R0切除的平均AUC为0.91(95%CI 0.79, 0.98),FBP为0.75(95%CI 0.60, 0.86),ASiR-V为0.81(95%CI 0.67, 0.91);DLIR-H与FBP比较P=0.030,与ASiR-V比较P=0.023。

临床应用与阅片要点

  • 阅片时将胰腺癌分为可切除、交界可切除或不可切除;DLIR-H较FBP和ASiR-V 60%提高阅片者信心(所有P<0.001),且信心随DLIR强度等级增加线性升高;DLIR-H的阅片者间一致性最高。

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 assess the diagnostic performance and reader confidence in determining the resectability of pancreatic cancer at computed tomography (CT) using a new deep learning image reconstruction (DLIR) algorithm.

METHODS: A retrospective review was conduct of on forty-seven patients with pathologically confirmed pancreatic cancers who underwent baseline multiphasic contrast-enhanced CT scan. Image data sets were reconstructed using filtered back projection (FBP), hybrid model-based adaptive statistical iterative reconstruction (ASiR-V) 60 %, and DLIR "TrueFidelity" at low(L), medium(M), and high strength levels(H). Four board-certified abdominal radiologists reviewed the CT images and classified cancers as resectable, borderline resectable, or unresectable. Diagnostic performance and reader confidence for categorizing the resectability of pancreatic cancer were evaluated based on the reference standards, and the interreader agreement was assessed using Fleiss k statistics.

RESULTS: For prediction of margin-negative resections(ie, R0), the average area under the receiver operating characteristic curve was significantly higher with DLIR-H (0.91; 95 % confidence interval [CI]: 0.79, 0.98) than FBP (0.75; 95 % CI:0.60, 0.86) and ASiR-V (0.81; 95 % CI:0.67, 0.91) (p = 0.030 and 0.023 respectively). Reader confidence scores were significantly better using DLIR compared to FBP and ASiR-V 60 % and increased linearly with the increase of DLIR strength level (all p < 0.001). Among the image reconstructions, DLIR-H showed the highest interreader agreement in the resectability classification and lowest subject variability in the reader confidence.

CONCLUSIONS: The DLIR-H algorithm may improve the diagnostic performance and reader confidence in the CT assignment of the local resectability of pancreatic cancer while reducing the interreader variability.

来源:Eur J Radiol,查看原文。版权归原作者所有。

引用

  1. Lyu P, Neely B, Solomon J, et al. Effect of deep learning image reconstruction in the prediction of resectability of pancreatic cancer: Diagnostic performance and reader confidence. Eur J Radiol. 2021. PMID: 34144309. doi:10.1016/j.ejrad.2021.109825

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。