联合DWI与优化ADC阈值提高急性缺血性卒中分割的观察者间一致性和深度学习模型性能
本研究评估ADC阈值对急性缺血性卒中观察者间一致性和深度学习模型分割性能的影响。12个深度学习模型基于76例患者的DWI-ADC组合和6个ADC阈值训练,在另外67例同院患者和78例他院患者中测试。结果显示ADC阈值0.6×10⁻³ mm²/s联合DWI可降低观察者和模型间差异,并获得最佳分割性能(DSC 0.971±0.021)。
要点
- ADC阈值0.6×10⁻³ mm²/s联合DWI时DSC达0.971±0.021,优于DWI单独使用的0.738±0.214。
- ADC阈值0.6×10⁻³ mm²/s联合DWI使95%一致性界限从DWI的11.23 cm²降至0.59 cm²。
- DSC与ADC阈值在多数病灶大小、两院及两名观察者中呈负相关,与卒中病灶大小呈正相关。
核心结论
- 联合ADC阈值0.6×10⁻³ mm²/s与DWI可减少观察者间和深度学习模型间差异,并实现深度学习模型对急性缺血性卒中病灶的最佳分割性能。
研究设计与样本
- 研究论文。12个深度学习模型在76例急性缺血性卒中患者的DWI-ADC组合上以6个不同ADC阈值训练,真值由2名观察者手动勾画。在同院另外67例患者和另一家医院78例患者中测试。采用Bland-Altman图和组内相关系数(ICC)评估观察者与模型间一致性,Dice相似系数(DSC)评估真值与自动分割的相似性,Mann-Whitney U检验进行组间比较,线性回归分析评估DSC与ADC阈值及AIS病灶大小的关系,p<.05为统计学显著。
关键影像表现/征象
- 手动分割的观察者间一致性和观察者内重复性极佳(所有ICC>0.98,p<.001)。
- 95%一致性界限从DWI真值的11.23 cm²降至ADC阈值0.6×10⁻³ mm²/s联合DWI预测的0.59 cm²。
- 深度学习模型整体DSC从DWI的0.738±0.214提升至ADC阈值0.6×10⁻³ mm²/s联合DWI的0.971±0.021。
- DSC与ADC阈值在多数病灶大小、两家医院及两名观察者中呈负相关(多数p<.05),与卒中病灶大小在所有ADC阈值、两家医院及两名观察者中呈正相关(所有p<.001)。
- ADC阈值0.6×10⁻³ mm²/s消除了任意卒中大小下观察者间或医院间DSC的差异(p=.07至>.99)。
诊断标准与关键数值
- 以DSC评估分割相似性,DWI单独使用时整体DSC为0.738±0.214,ADC阈值0.6×10⁻³ mm²/s联合DWI时整体DSC为0.971±0.021。
- 以Bland-Altman 95%一致性界限评估一致性,DWI真值为11.23 cm²,ADC阈值0.6×10⁻³ mm²/s联合DWI预测为0.59 cm²。
- 以ICC评估观察者间和观察者内一致性,手动分割所有ICC>0.98(p<.001)。
临床应用与阅片要点
- 在急性缺血性卒中病灶分割中,联合ADC阈值0.6×10⁻³ mm²/s与DWI可降低观察者间和深度学习模型间差异并提升分割性能。
- ADC阈值0.6×10⁻³ mm²/s联合DWI在任意卒中大小下消除了观察者间或医院间DSC差异(p=.07至>.99)。
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
OBJECTIVES: To examine the role of ADC threshold on agreement across observers and deep learning models (DLMs) plus segmentation performance of DLMs for acute ischemic stroke (AIS).
METHODS: Twelve DLMs, which were trained on DWI-ADC-ADC combination from 76 patients with AIS using 6 different ADC thresholds with ground truth manually contoured by 2 observers, were tested by additional 67 patients in the same hospital and another 78 patients in another hospital. Agreement between observers and DLMs were evaluated by Bland-Altman plot and intraclass correlation coefficient (ICC). The similarity between ground truth (GT) defined by observers and between automatic segmentation performed by DLMs was evaluated by Dice similarity coefficient (DSC). Group comparison was performed using the Mann-Whitney U test. The relationship between the DSC and ADC threshold as well as AIS lesion size was evaluated by linear regression analysis. A p < .05 was considered statistically significant.
RESULTS: Excellent interobserver agreement and intraobserver repeatability in the manual segmentation (all ICC > 0.98, p < .001) were achieved. The 95% limit of agreement was reduced from 11.23 cm2 for GT on DWI to 0.59 cm2 for prediction at an ADC threshold of 0.6 × 10-3 mm2/s combined with DWI. The segmentation performance of DLMs was improved with an overall DSC from 0.738 ± 0.214 on DWI to 0.971 ± 0.021 on an ADC threshold of 0.6 × 10-3 mm2/s combined with DWI.
CONCLUSIONS: Combining an ADC threshold of 0.6 × 10-3 mm2/s with DWI reduces interobserver and inter-DLM difference and achieves best segmentation performance of AIS lesions using DLMs.
KEY POINTS: • Higher Dice similarity coefficient (DSC) in predicting acute ischemic stroke lesions was achieved by ADC thresholds combined with DWI than by DWI alone (all p < .05). • DSC had a negative association with the ADC threshold in most sizes, both hospitals, and both observers (most p < .05) and a positive association with the stroke size in all ADC thresholds, both hospitals, and both observers (all p < .001). • An ADC threshold of 0.6 × 10-3 mm2/s eliminated the difference of DSC at any stroke size between observers or between hospitals (p = .07 to > .99).
引用
- Juan, Lin, Li, et al. Improving interobserver agreement and performance of deep learning models for segmenting acute ischemic stroke by combining DWI with optimized ADC thresholds. Eur Radiol. 2022. PMID: 35201408. doi:10.1007/s00330-022-08633-6
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。