使用密集特征融合神经网络自动判别肝脏MRI不同序列与期相:初步研究
本研究回顾性纳入384例肝脏MRI检查的3869个序列与期相,构建并验证密集特征融合神经网络(DFuNN)自动识别10种平扫序列与增强期相,以两位放射科医师共识判读为参考标准。DFuNN在独立测试集上对完整序列与期相输入的平均敏感度范围为88.06%至100%,平均特异度范围为99.12%至99.94%,中位准确率范围为98.02%至99.95%。无肝硬化患者的预测准确率显著高于肝硬化患者(P=0.0153),其他因素间准确率无显著差异。
要点
- DFuNN可自动识别肝脏MRI平扫序列与增强期相,测试集中位准确率范围为98.02%至99.95%。
- 融合模块可提升DFuNN性能,且对完整与不完整序列和期相均表现良好。
- 无肝硬化患者的预测准确率显著高于肝硬化患者(P=0.0153)。
核心结论
- DFuNN能够自动且准确地识别特定的平扫MRI序列与增强MRI期相。
研究设计与样本
- 回顾性研究,共纳入384例肝脏MRI检查的3869个序列与期相,训练/验证集为287例患者的2886个序列,测试集为97例患者的983个序列,纳入10种平扫序列与增强期相,以两位放射科医师(分别有20年和10年经验)共识判读为参考标准。
诊断标准与关键数值
- 测试集中完整序列与期相输入的平均敏感度范围为88.06%至100%,平均特异度范围为99.12%至99.94%,中位准确率范围为98.02%至99.95%,以两位放射科医师共识判读为参考标准。
局限性
- 本研究为回顾性研究。
- 本研究为初步研究。
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 develop and validate a dense feature fusion neural network (DFuNN) to automatically recognize different sequences and phases of liver magnetic resonance imaging (MRI).
MATERIALS AND METHODS: In total, 3869 sequences and phases from 384 liver MRI examinations, divided into training/validation (n = 2886 sequences from 287 patients) and test (n = 983 sequences from 97 patients) sets, were used in this retrospective study. Ten unenhanced sequences and enhanced phases were included. Manual sequence recognition, performed by two radiologists (20 and 10 years of experience) in a consensus reading, was used as the reference standard. The sensitivity, specificity, accuracy, and area under the receiver operating characteristic curve (AUC) were calculated to evaluate the performance of the DFuNN on an identical unseen test set. Finally, we evaluated the factors impacting the model precision.
RESULTS: A fusion block improved the performance of the DFuNN. DFuNN with a fusion block achieved good recognition performance for both complete and incomplete sequences and phases in the test set. The average sensitivity of recognition performance for complete sequence and phase inputs ranged from 88.06 to 100%, the average specificity ranged from 99.12 to 99.94%, and the median accuracy ranged from 98.02 to 99.95%. The DFuNN prediction accuracy for patients without cirrhosis were significantly higher than those for patients with cirrhosis (P = 0.0153). No significant difference was found in the accuracy across other factors.
CONCLUSION: DFuNN can automatically and accurately identify specific unenhanced MRI sequences and enhanced MRI phases.
引用
- Wang SH, Du J, Xu H, et al. Automatic discrimination of different sequences and phases of liver MRI using a dense feature fusion neural network: a preliminary study. Abdom Radiol (NY). 2021. PMID: 34057565. doi:10.1007/s00261-021-03142-4
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。