当前位置: X-MOL 学术npj Digit. Med. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Deep learning biomarker of chronometric and biological ischemic stroke lesion age from unenhanced CT
npj Digital Medicine ( IF 12.4 ) Pub Date : 2024-12-06 , DOI: 10.1038/s41746-024-01325-z
Adam Marcus, Grant Mair, Liang Chen, Charles Hallett, Claudia Ghezzou Cuervas-Mons, Dylan Roi, Daniel Rueckert, Paul Bentley

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 (R2) 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 (ρ2 = 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.



中文翻译:


来自未增强 CT 的计时和生物缺血性卒中病变年龄的深度学习生物标志物



估计急性缺血性脑病灶的进展 - 或生物病灶年龄 - 对于超急性中风管理具有巨大的实际意义。目前通过非对比计算机断层扫描 (NCCT) 确定病变年龄的最佳方法是测量相对强度 (RI),称为净水分摄取 (NWU)。我们使用根据计时病灶年龄训练的卷积神经网络 - 放射组学 (CNN-R) 模型优化了 NCCT 的病灶年龄估计 (扫描开始时间:OTS),同时在外部数据集中验证了计时和生物病灶年龄 (N = 1945)。使用 CNN-R 和 RI 模型预测 OTS 的决定系数 (R2) 分别为 0.58 和 0.32;而 CNN-R 估计的 OTS 与缺血核心:半影比的相关性强于 RI 和计时 OTS (ρ2 = 0.37、0.19、0.11);和早期病变扩大 (CNN-R 与其他回归系数 >2x) (所有比较: p < 0.05)。总之,NCCT 病变的深度学习分析在估计计时和生物病变年龄方面的精度大约是 NWU 的两倍。

更新日期:2024-12-06
down
wechat
bug