在单张T2加权图像上诊断宫颈癌:深度学习与放射科医生的比较
本研究纳入418例接受MRI检查的患者,利用矢状位T2加权图像训练卷积神经网络(DCNN)模型,并与三位盲法阅片的放射科医生比较诊断宫颈癌的效能。结果显示DCNN模型与放射科医生诊断效能相当或更优,敏感度0.883 vs 0.783-0.867,特异度0.933 vs 0.917-0.950,AUC为0.932,准确率比较P=0.272-0.62。
要点
- DCNN模型在单张矢状位T2加权图像上诊断宫颈癌的AUC达0.932,与经验丰富的放射科医生相当或更优。
- 模型敏感度0.883、特异度0.933,放射科医生敏感度0.783-0.867、特异度0.917-0.950。
- 模型准确率0.908,与放射科医生(0.867-0.892)相比差异无统计学显著(P=0.272-0.62)。
核心结论
- 深度学习在单张T2加权图像上诊断宫颈癌的效能与经验丰富的放射科医生相当。
研究设计与样本
- 本研究为回顾性研究,纳入2013年6月至2020年5月间接受MRI检查的418例患者(年龄21-91岁,平均50.2岁),其中177例病理确诊宫颈癌、241例非癌患者。
- 使用矢状位T2加权图像,采用Xception架构的卷积神经网络(DCNN)模型,以117例癌症患者的488张图像和181例非癌患者的509张图像进行50个epoch的训练。
- 测试集为60例癌症患者和60例非癌患者的各60张图像,由三位经验丰富的放射科医生独立盲法阅片作为对照。
诊断标准与关键数值
- DCNN模型诊断宫颈癌的敏感度为0.883,特异度为0.933,准确率为0.908,AUC为0.932。
- 三位放射科医生诊断宫颈癌的敏感度为0.783-0.867,特异度为0.917-0.950,准确率为0.867-0.892。
- DCNN模型与放射科医生准确率比较的P值为0.272-0.62。
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
PURPOSE: To compare deep learning with radiologists when diagnosing uterine cervical cancer on a single T2-weighted image.
METHODS: This study included 418 patients (age range, 21-91 years; mean, 50.2 years) who underwent magnetic resonance imaging (MRI) between June 2013 and May 2020. We included 177 patients with pathologically confirmed cervical cancer and 241 non-cancer patients. Sagittal T2-weighted images were used for analysis. A deep learning model using convolutional neural networks (DCNN), called Xception architecture, was trained with 50 epochs using 488 images from 117 cancer patients and 509 images from 181 non-cancer patients. It was tested with 60 images for 60 cancer and 60 non-cancer patients. Three blinded experienced radiologists also interpreted these 120 images independently. Sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUC) were compared between the DCNN model and radiologists.
RESULTS: The DCNN model and the radiologists had a sensitivity of 0.883 and 0.783-0.867, a specificity of 0.933 and 0.917-0.950, and an accuracy of 0.908 and 0.867-0.892, respectively. The DCNN model had an equal to, or better, diagnostic performance than the radiologists (AUC = 0.932, and p for accuracy = 0.272-0.62).
CONCLUSION: Deep learning provided diagnostic performance equivalent to experienced radiologists when diagnosing cervical cancer on a single T2-weighted image.
引用
- Urushibara A, Saida T, Mori K, et al. Diagnosing uterine cervical cancer on a single T2-weighted image: Comparison between deep learning versus radiologists. Eur J Radiol. 2020. PMID: 33338759. doi:10.1016/j.ejrad.2020.109471
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。