深度学习自动测量幕上脑出血血肿与血肿周围水肿
研究基于两个脑出血队列的CT扫描,训练全卷积神经网络分割血肿与血肿周围水肿(PHE),并在84例外部扫描中验证。自动与人工量化一致性血肿为0.96、PHE为0.81,Dice相似系数分别为0.90和0.54,外部验证结果与两名人类评分者间一致性相当。
要点
- 深度学习算法可准确自动量化幕上脑出血的血肿与PHE体积。
- 血肿自动量化一致性优于PHE,PHE分割重叠度与人类评分者间相当。
- 快速一致的自动生物标志物量化有助于大规模脑出血队列研究。
核心结论
- 深度学习影像算法能准确测量血肿和PHE体积,外部验证确认其准确性。
研究设计与样本
- 研究基于2个脑出血研究队列,用第一队列手动标注训练全卷积神经网络,第二队列84次扫描外部验证。
主要发现
- 推导队列中血肿中位体积18 mL(IQR 8-43),PHE中位体积12 mL(IQR 5-30)。
- 自动量化一致性血肿为0.96、PHE为0.81;Dice相似系数血肿0.90(IQR 0.85-0.93)、PHE 0.54(IQR 0.39-0.65)。
- 外部验证血肿一致性0.98、DSC 0.90,PHE一致性0.90、DSC 0.55。
- 两名人类评分者间DSC血肿0.90、PHE 0.57,与算法表现相当。
临床怎么用
- 可用于大规模脑出血队列中快速、一致地自动量化血肿与PHE生物标志物。
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)。
原文
Background and Purpose- Volumes of hemorrhage and perihematomal edema (PHE) are well-established biomarkers of primary and secondary injury, respectively, in spontaneous intracerebral hemorrhage. An automated imaging pipeline capable of accurately and rapidly quantifying these biomarkers would facilitate large cohort studies evaluating underlying mechanisms of injury. Methods- Regions of hemorrhage and PHE were manually delineated on computed tomography scans of patients enrolled in 2 intracerebral hemorrhage studies. Manual ground-truth masks from the first cohort were used to train a fully convolutional neural network to segment images into hemorrhage and PHE. The primary outcome was automated-versus-human concordance in hemorrhage and PHE volumes. The secondary outcome was voxel-by-voxel overlap of segmentations, quantified by the Dice similarity coefficient (DSC). Algorithm performance was validated on 84 scans from the second study. Results- Two hundred twenty-four scans from 124 patients with supratentorial intracerebral hemorrhage were used for algorithm derivation. Median volumes were 18 mL (interquartile range, 8-43) for hemorrhage and 12 mL (interquartile range, 5-30) for PHE. Concordance was excellent (0.96) for automated quantification of hemorrhage and good (0.81) for PHE, with DSC of 0.90 (interquartile range, 0.85-0.93) and 0.54 (0.39-0.65), respectively. External validation confirmed algorithm accuracy for hemorrhage (concordance 0.98, DSC 0.90) and PHE (concordance 0.90, DSC 0.55). This was comparable with the consistency observed between 2 human raters (DSC 0.90 for hemorrhage, 0.57 for PHE). Conclusions- We have developed a deep learning-based imaging algorithm capable of accurately measuring hemorrhage and PHE volumes. Rapid and consistent automated biomarker quantification may accelerate powerful and precise studies of disease biology in large cohorts of intracerebral hemorrhage patients.
引用
- Dhar R, Falcone GJ, Chen Y, et al. Deep Learning for Automated Measurement of Hemorrhage and Perihematomal Edema in Supratentorial Intracerebral Hemorrhage. Stroke. 2019. PMID: 31805845. doi:10.1161/STROKEAHA.119.027657
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。