文献速递乳腺胸部CT

深度学习对放射科医师和住院医师在CT上检测乳腺癌的影响:一项跨厂商测试研究

Impact of deep learning on radiologists and radiology residents in detecting breast cancer on CT: a cross-vendor test study.
PubMed 文献 · Clin Radiol · 2023-10-13

本回顾性研究纳入2010年1月至2020年12月接受增强胸部CT的患者,使用两家厂商设备图像训练和验证深度学习模型,并在测试组中评估模型辅助前后放射科医师和住院医师的诊断表现。模型在验证集和测试集的AUC分别为0.976和0.967,参考模型结果后5名阅片者的FOM显著提高(p=0.038)。结论认为深度学习可帮助放射科医师和住院医师在CT上检测乳腺癌。

要点

  • 深度学习模型在测试集检测乳腺癌的AUC为0.967。
  • 参考模型结果后5名阅片者FOM从0.933/0.962/0.883/0.944/0.867提高至0.958/0.968/0.917/0.947/0.900(p=0.038)。
  • 深度学习可帮助放射科医师和住院医师在CT上检测乳腺癌。

核心结论

  • 深度学习可帮助放射科医师和放射科住院医师在CT上检测乳腺癌。

研究设计与样本

  • 回顾性研究,纳入2010年1月至2020年12月使用两家厂商设备接受增强胸部CT的患者,乳腺癌确诊患者分为训练组(n=201)和验证组(n=26),测试组(n=30)使用任一厂商处理后的CT图像。

诊断标准与关键数值

  • 深度学习模型在验证集的AUC为0.976,在测试集的AUC为0.967;阅片者使用四点诊断置信度评分,采用jackknife替代自由响应ROC分析计算FOM。

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

AIM: To investigate the effect of deep learning on the diagnostic performance of radiologists and radiology residents in detecting breast cancers on computed tomography (CT).

MATERIALS AND METHODS: In this retrospective study, patients undergoing contrast-enhanced chest CT between January 2010 and December 2020 using equipment from two vendors were included. Patients with confirmed breast cancer were categorised as the training (n=201) and validation (n=26) group and the testing group (n=30) using processed CT images from either vendor. The trained deep-learning model was applied to test group patients with (30 females; mean age = 59.2 ± 15.8 years) and without (19 males, 21 females; mean age = 64 ± 15.9 years) breast cancer. Image-based diagnostic performance of the deep-learning model was evaluated with the area under the receiver operating characteristic curve (AUC). Two radiologists and three radiology residents were asked to detect malignant lesions by recording a four-point diagnostic confidence score before and after referring to the result from the deep-learning model, and their diagnostic performance was evaluated using jackknife alternative free-response receiver operating characteristic analysis by calculating the figure of merit (FOM).

RESULTS: The AUCs of the trained deep-learning model on the validation and test data were 0.976 and 0.967, respectively. After referencing with the result of the deep learning model, the FOMs of readers significantly improved (reader 1/2/3/4/5: from 0.933/0.962/0.883/0.944/0.867 to 0.958/0.968/0.917/0.947/0.900; p=0.038).

CONCLUSION: Deep learning can help radiologists and radiology residents detect breast cancer on CT.

来源:Clin Radiol,查看原文。版权归原作者所有。

引用

  1. Yasaka K, Sato C, Hirakawa H, et al. Impact of deep learning on radiologists and radiology residents in detecting breast cancer on CT: a cross-vendor test study. Clin Radiol. 2023. PMID: 37872026. doi:10.1016/j.crad.2023.09.022

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。