文献速递胸部骨肌CT

全自动肋骨骨折检测系统在胸部CT图像上的应用及其对放射科医生诊断表现的影响

A fully automated rib fracture detection system on chest CT images and its impact on radiologist performance.
PubMed 文献 · Skeletal Radiol · 2021-02-18

研究从多家医院收集8529幅胸部CT图像训练深度学习模型,在单台CT扫描仪采集的300幅胸部CT图像(861处肋骨骨折)上外部测试。使用深度学习模型后,放射科医生骨折检测的精确率、召回率和F1-score分别达0.943、0.978和0.960,阅片时间从158.3±35.7秒降至42.3±6.8秒。结论认为放射科医生在深度学习模型辅助下诊断和分类肋骨骨折表现最佳。

要点

  • 深度学习模型辅助下放射科医生骨折检测精确率0.943、召回率0.978、F1-score 0.960。
  • 使用模型后阅片时间从158.3±35.7秒降至42.3±6.8秒。
  • 模型辅助使检测召回和分类准确率(0.922和0.863)高于医生单独判读(0.812和0.850)。

关键影像表现/征象

  • 肋骨骨折在骨窗上逐层标记,金标准共含861处肋骨骨折。
  • 模型辅助使检测召回和分类准确率分别为0.922和0.863,医生单独判读分别为0.812和0.850。
  • 模型辅助下放射科医生骨折检测精确率0.943、召回率0.978、F1-score 0.960。
  • 使用模型后放射科医生阅片时间从158.3±35.7秒降至42.3±6.8秒。

诊断标准与关键数值

  • 模型辅助下肋骨骨折检测精确率0.943、召回率0.978、F1-score 0.960。
  • 模型检测召回0.922、分类准确率0.863;医生单独判读检测召回0.812、分类准确率0.850。

临床应用与阅片要点

  • 两名低年资放射科医生在深度学习模型辅助下肋骨骨折检测精确率、召回率和F1-score均提高。
  • 使用深度学习模型后放射科医生阅片时间从158.3±35.7秒降至42.3±6.8秒。

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 rib fracture detection and classification by radiologists using CT images with and without a deep learning model.

MATERIALS AND METHODS: A total of 8529 chest CT images were collected from multiple hospitals for training the deep learning model. The test dataset included 300 chest CT images acquired using a single CT scanner. The rib fractures were marked in the bone window on each CT slice by experienced radiologists, and the ground truth included 861 rib fractures. We proposed a heterogeneous neural network for rib fracture detection and classification consisting of a cascaded feature pyramid network and a classification network. The deep learning-based model was evaluated based on the external testing data. The precision rate, recall rate, F1-score, and diagnostic time of two junior radiologists with and without the deep learning model were computed, and the Chi-square, one-way analysis of variance, and least significant difference tests were used to analyze the results.

RESULTS: The use of the deep learning model increased detection recall and classification accuracy (0.922 and 0.863) compared with the radiologists alone (0.812 vs. 0.850). The radiologists achieved a higher precision rate, recall rate, and F1-score for fracture detection when using the deep learning model, at 0.943, 0.978, and 0.960, respectively. When using the deep learning model, the radiologist's reading time was decreased from 158.3 ± 35.7 s to 42.3 ± 6.8 s.

CONCLUSION: Radiologists achieved the highest performance in diagnosing and classifying rib fractures on CT images when assisted by the deep learning model.

来源:Skeletal Radiol,查看原文。版权归原作者所有。

引用

  1. Meng XH, Wu DJ, Wang Z, et al. A fully automated rib fracture detection system on chest CT images and its impact on radiologist performance. Skeletal Radiol. 2021. PMID: 33599801. doi:10.1007/s00256-021-03709-8

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。