文献速递儿科影像骨肌DR

基于深度学习的计算机骨龄评估程序:准确性与效率评估

Computerized Bone Age Estimation Using Deep Learning Based Program: Evaluation of the Accuracy and Efficiency.
PubMed 文献 · AJR Am J Roentgenol · 2017-09-12

本研究评估了一种基于Greulich-Pyle法的深度学习自动骨龄评估软件。对200例3-17岁患者左手X线片,软件单独、软件辅助和Greulich-Pyle图谱辅助三种方式估算骨龄,参考标准由两名经验丰富放射科医师共识确定。软件单独骨龄与参考骨龄一致率69.5%,相关性r=0.992(p<0.001);软件辅助使 reviewer 1 一致率从63.0%升至72.5%,reviewer 2 从49.5%升至57.5%,阅片时间分别减少18.0%和40.0%。

要点

  • 软件单独骨龄与参考骨龄一致率69.5%,相关性r=0.992(p<0.001)。
  • 软件辅助使 reviewer 1 一致率从63.0%升至72.5%,reviewer 2 从49.5%升至57.5%。
  • 软件辅助使 reviewer 1 和 reviewer 2 阅片时间分别减少18.0%和40.0%。

核心结论

  • 自动软件系统能可靠准确估算骨龄,似乎能在不损害诊断准确性的情况下通过减少阅片时间提高效率。

研究设计与样本

  • 基于Greulich-Pyle法的深度学习技术开发自动骨龄测定软件;使用200例3-17岁患者左手X线片,比较软件单独(first-rank骨龄)、两名放射科医师软件辅助和两名放射科医师仅Greulich-Pyle图谱辅助的骨龄估算;参考骨龄由两名经验丰富放射科医师共识确定。

诊断标准与关键数值

  • 软件单独骨龄与参考骨龄一致率69.5%,相关性r=0.992(p<0.001)。
  • reviewer 1 一致率:Greulich-Pyle图谱辅助63.0% vs 软件辅助72.5%。
  • reviewer 2 一致率:Greulich-Pyle图谱辅助49.5% vs 软件辅助57.5%。
  • 阅片时间减少:reviewer 1 减少18.0%,reviewer 2 减少40.0%。

临床应用与阅片要点

  • 自动软件系统似乎可在不损害诊断准确性的情况下减少阅片时间、提高效率。

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: The purpose of this study is to evaluate the accuracy and efficiency of a new automatic software system for bone age assessment and to validate its feasibility in clinical practice.

MATERIALS AND METHODS: A Greulich-Pyle method-based deep-learning technique was used to develop the automatic software system for bone age determination. Using this software, bone age was estimated from left-hand radiographs of 200 patients (3-17 years old) using first-rank bone age (software only), computer-assisted bone age (two radiologists with software assistance), and Greulich-Pyle atlas-assisted bone age (two radiologists with Greulich-Pyle atlas assistance only). The reference bone age was determined by the consensus of two experienced radiologists.

RESULTS: First-rank bone ages determined by the automatic software system showed a 69.5% concordance rate and significant correlations with the reference bone age (r = 0.992; p < 0.001). Concordance rates increased with the use of the automatic software system for both reviewer 1 (63.0% for Greulich-Pyle atlas-assisted bone age vs 72.5% for computer-assisted bone age) and reviewer 2 (49.5% for Greulich-Pyle atlas-assisted bone age vs 57.5% for computer-assisted bone age). Reading times were reduced by 18.0% and 40.0% for reviewers 1 and 2, respectively.

CONCLUSION: Automatic software system showed reliably accurate bone age estimations and appeared to enhance efficiency by reducing reading times without compromising the diagnostic accuracy.

来源:AJR Am J Roentgenol,查看原文。版权归原作者所有。

引用

  1. Kim JR, Shim WH, Yoon HM, et al. Computerized Bone Age Estimation Using Deep Learning Based Program: Evaluation of the Accuracy and Efficiency. AJR Am J Roentgenol. 2017. PMID: 28898126. doi:10.2214/AJR.17.18224

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。