输入影像组合与ADC阈值对U-Net分割急性缺血性卒中病灶的影响
本研究回顾性纳入212例急性缺血性卒中患者,评估不同输入影像组合(ADC-ADC-ADC、DWI-ADC-ADC、DWI-DWI-ADC、DWI-DWI-DWI)与ADC阈值(0.6、0.8、1.8 × 10-3 mm2/s)对U-Net分割性能的影响,以Dice相似系数(DSC)评价。结果显示不同组合与阈值间DSC显著不同,采用DWI-ADC-ADC组合在ADC阈值0.6 × 10-3 mm2/s时获得最高DSC。
要点
- DWI-ADC-ADC组合且ADC阈值0.6 × 10-3 mm2/s时U-Net分割急性缺血性卒中病灶DSC最高。
- 混合U-Net在ADC阈值0.6与0.8 × 10-3 mm2/s时优于均一U-Net(p < .001)。
- ADC阈值1.8 × 10-3 mm2/s时DWI-DWI-DWI组合与混合U-Net性能相似(p = .062至1)。
核心结论
- U-Net分割急性缺血性卒中病灶的性能随输入影像组合和ADC阈值变化,最优为DWI-ADC-ADC组合且ADC阈值0.6 × 10-3 mm2/s。
研究设计与样本
- 回顾性研究纳入212例急性缺血性卒中患者,比较四种输入影像组合与三个ADC阈值(0.6、0.8、1.8 × 10-3 mm2/s)对U-Net分割性能的影响,以Dice相似系数评价,采用Kruskal-Wallis检验及Tukey-Kramer事后检验,p < .05为显著。
诊断标准与关键数值
- 以Dice相似系数(DSC)评价分割性能;混合U-Net在ADC阈值0.6和0.8 × 10-3 mm2/s时优于均一U-Net(p < .001)。
- DWI-DWI-DWI组合在ADC阈值1.8 × 10-3 mm2/s时与混合U-Net性能相似(p = .062至1)。
- DWI-ADC-ADC组合在ADC阈值0.6 × 10-3 mm2/s时获得最高DSC。
临床应用与阅片要点
- 若采用U-Net辅助分割急性缺血性卒中病灶,可优先尝试DWI-ADC-ADC输入组合并设定ADC阈值0.6 × 10-3 mm2/s以优化分割效果。
局限性
- 原文未明确报告研究局限性;作为回顾性单中心研究,结论外推需谨慎。
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: To evaluate the effect of the weighting of input imaging combo and ADC threshold on the performance of the U-Net and to find an optimized input imaging combo and ADC threshold in segmenting acute ischemic stroke (AIS) lesion.
METHODS: This study retrospectively enrolled a total of 212 patients having AIS. Four combos, including ADC-ADC-ADC (AAA), DWI-ADC-ADC (DAA), DWI-DWI-ADC (DDA), and DWI-DWI-DWI (DDD), were used as input images, respectively. Three ADC thresholds including 0.6, 0.8 and 1.8 × 10-3 mm2/s were applied. Dice similarity coefficient (DSC) was used to evaluate the segmentation performance of U-Nets. Nonparametric Kruskal-Wallis test with Tukey-Kramer post-hoc tests were used for comparison. A p < .05 was considered statistically significant.
RESULTS: The DSC significantly varied among different combos of images and different ADC thresholds. Hybrid U-Nets outperformed uniform U-Nets at ADC thresholds of 0.6 × 10-3 mm2/s and 0.8 × 10-3 mm2/s (p < .001). The U-Net with imaging combo of DDD had segmentation performance similar to hybrid U-Nets at an ADC threshold of 1.8 × 10-3 mm2/s (p = .062 to 1). The U-Net using the imaging combo of DAA at the ADC threshold of 0.6 × 10-3 mm2/s achieved the highest DSC in the segmentation of AIS lesion.
CONCLUSIONS: The segmentation performance of U-Net for AIS varies among the input imaging combos and ADC thresholds. The U-Net is optimized by choosing the imaging combo of DAA at an ADC threshold of 0.6 × 10-3 mm2/s in segmentating AIS lesion with highest DSC.
KEY POINTS: • Segmentation performance of U-Net for AIS differs among input imaging combos. • Segmentation performance of U-Net for AIS differs among ADC thresholds. • U-Net is optimized using DAA with ADC = 0.6 × 10-3 mm2/s.
引用
- Li, Lin, Chung, et al. The role of input imaging combination and ADC threshold on segmentation of acute ischemic stroke lesion using U-Net. Eur Radiol. 2023. PMID: 37095361. doi:10.1007/s00330-023-09622-z
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。