Marcus Adam, Mair Grant, Chen Liang, Hallett Charles, Cuervas-Mons Claudia Ghezzou, Roi Dylan, Rueckert Daniel, Bentley Paul
Department of Brain Sciences, Imperial College London, London, UK.
Centre for Clinical Brain Sciences, University of Edinburgh, Edinburgh, UK.
NPJ Digit Med. 2024 Dec 6;7(1):338. doi: 10.1038/s41746-024-01325-z.
Estimating progression of acute ischemic brain lesions - or biological lesion age - holds huge practical importance for hyperacute stroke management. The current best method for determining lesion age from non-contrast computerised tomography (NCCT), measures Relative Intensity (RI), termed Net Water Uptake (NWU). We optimised lesion age estimation from NCCT using a convolutional neural network - radiomics (CNN-R) model trained upon chronometric lesion age (Onset Time to Scan: OTS), while validating against chronometric and biological lesion age in external datasets (N = 1945). Coefficients of determination (R) for OTS prediction, using CNN-R, and RI models were 0.58 and 0.32 respectively; while CNN-R estimated OTS showed stronger associations with ischemic core:penumbra ratio, than RI and chronometric, OTS (ρ = 0.37, 0.19, 0.11); and with early lesion expansion (regression coefficients >2x for CNN-R versus others) (all comparisons: p < 0.05). Concluding, deep-learning analytics of NCCT lesions is approximately twice as accurate as NWU for estimating chronometric and biological lesion ages.
评估急性缺血性脑损伤的进展情况，即生物损伤年龄，对于超急性中风的治疗具有重大的实际意义。目前，从非增强计算机断层扫描（NCCT）确定损伤年龄的最佳方法是测量相对强度（RI），即净吸水量（NWU）。我们使用基于计时损伤年龄（扫描开始时间：OTS）训练的卷积神经网络-放射组学（CNN-R）模型，优化了从NCCT进行的损伤年龄估计，同时在外部数据集（N = 1945）中针对计时和生物损伤年龄进行了验证。使用CNN-R和RI模型预测OTS的决定系数（R）分别为0.58和0.32；与RI和计时OTS相比，CNN-R估计的OTS与缺血核心：半暗带比值的相关性更强（ρ = 0.37、0.19、0.11）；并且与早期损伤扩展的相关性更强（CNN-R的回归系数比其他模型大2倍以上）（所有比较：p <0.05）。结论是，对于估计计时和生物损伤年龄，NCCT损伤的深度学习分析的准确性约为NWU的两倍。
