文献速递神经MR

深度学习从平扫MRI预测多发性硬化强化病灶

Deep Learning for Predicting Enhancing Lesions in Multiple Sclerosis from Noncontrast MRI.
PubMed 文献 · Radiology · 2019-12-17

本研究对2005至2009年招募的1008例多发性硬化患者的多参数MRI进行前瞻性分析,用卷积神经网络在平扫图像上逐层预测强化病灶并汇总为患者级预测,以增强T1WI强化病灶为参考标准。逐层预测敏感度78%±4.3、特异度73%±2.7、AUC 0.82±0.02,患者级预测分别为72%±9.0、70%±6.3、AUC 0.75±0.03。作者结论为深度学习结合常规MRI从平扫多参数MRI识别多发性硬化强化病灶具有中等至较高准确度。

要点

  • 平扫多参数MRI经卷积神经网络可逐层预测多发性硬化强化病灶,逐层AUC 0.82±0.02。
  • 患者级预测AUC为0.75±0.03,敏感度72%±9.0、特异度70%±6.3。
  • 1008例中519例至少见一个强化病灶,增强后T1WI强化为参考标准。

核心结论

  • 深度学习结合常规MRI从平扫多参数MRI识别多发性硬化强化病灶具有中等至较高准确度。

研究设计与样本

  • 本研究为对已有MRI数据的前瞻性分析。
  • 网络输入为1970次多参数MRI检查,来自2005至2009年招募的1008例患者。
  • 以增强后T1加权图像上的强化病灶为参考标准,采用五折交叉验证评估网络性能。

关键影像表现/征象

  • 原文未报告具体影像征象,仅以增强后T1加权图像上的强化病灶作为参考标准。

诊断标准与关键数值

  • 逐层预测的敏感度和特异度在五个测试集上平均分别为78%±4.3和73%±2.7。
  • 患者级预测的敏感度和特异度分别为72%±9.0和70%±6.3。
  • 逐层预测和患者级预测的AUC分别为0.82±0.02和0.75±0.03。
  • 1008例参与者中519例至少观察到一个强化病灶。

临床应用与阅片要点

  • 原文未据此给出临床推荐。

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

Background Enhancing lesions on MRI scans obtained after contrast material administration are commonly thought to represent disease activity in multiple sclerosis (MS); it is desirable to develop methods that can predict enhancing lesions without the use of contrast material. Purpose To evaluate whether deep learning can predict enhancing lesions on MRI scans obtained without the use of contrast material. Materials and Methods This study involved prospective analysis of existing MRI data. A convolutional neural network was used for classification of enhancing lesions on unenhanced MRI scans. This classification was performed for each slice, and the slice scores were combined by using a fully connected network to produce participant-wise predictions. The network input consisted of 1970 multiparametric MRI scans from 1008 patients recruited from 2005 to 2009. Enhanced lesions on postcontrast T1-weighted images served as the ground truth. The network performance was assessed by using fivefold cross-validation. Statistical analysis of the network performance included calculation of lesion detection rates and areas under the receiver operating characteristic curve (AUCs). Results MRI scans from 1008 participants (mean age, 37.7 years ± 9.7; 730 women) were analyzed. At least one enhancing lesion was observed in 519 participants. The sensitivity and specificity averaged across the five test sets were 78% ± 4.3 and 73% ± 2.7, respectively, for slice-wise prediction. The corresponding participant-wise values were 72% ± 9.0 and 70% ± 6.3. The diagnostic performances (AUCs) were 0.82 ± 0.02 and 0.75 ± 0.03 for slice-wise and participant-wise enhancement prediction, respectively. Conclusion Deep learning used with conventional MRI identified enhanced lesions in multiple sclerosis from images from unenhanced multiparametric MRI with moderate to high accuracy. © RSNA, 2019.

来源:Radiology,查看原文。版权归原作者所有。

引用

  1. Narayana PA, Coronado I, Sujit SJ, et al. Deep Learning for Predicting Enhancing Lesions in Multiple Sclerosis from Noncontrast MRI. Radiology. 2019. PMID: 31845845. doi:10.1148/radiol.2019191061

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。