Department of Medical Imaging, Jinling Hospital, Nanjing University School of Medicine, Nanjing, China,
Department of Medical Imaging, Jinling Hospital, The First School of Clinical Medicine, Southern Medical University, Nanjing, China.
Cerebrovasc Dis. 2024;53(1):105-114. doi: 10.1159/000530412. Epub 2023 Apr 12.
Diabetes markedly affects the formation and development of intracranial atherosclerosis. The study was aimed at evaluating whether radiomics features can help distinguish plaques primarily associated with diabetes.
We retrospectively analyzed patients who were admitted to our center because of acute ischemic stroke due to intracranial atherosclerosis between 2016 and 2022. Clinical data, blood biomarkers, conventional plaque features, and plaque radiomics features were collected for all patients. Odds ratios (ORs) with 95% confidence intervals (CIs) were determined from logistic regression models. The receiver operating characteristic (ROC) curve and area under the ROC curve (AUC) were used to describe diagnostic performance. The DeLong test was used to compare differences between models.
Overall, 157 patients (115 men; mean age, 58.7 ± 10.7 years) were enrolled. Multivariate logistic regression analysis showed that plaque length (OR: 1.17; 95% CI: 1.07-1.28) and area (OR: 1.13; 95% CI: 1.02-1.24) were independently associated with diabetes. On combining plaque length and area as a conventional model, the AUCs of the training and validation cohorts for identifying diabetes patients were 0.789 and 0.720, respectively. On combining radiomics features on T1WI and contrast-enhanced T1WI sequences, a better diagnostic value was obtained in the training and validation cohorts (AUC: 0.889 and 0.861). The DeLong test showed the model combining radiomics and conventional plaque features performed better than the conventional model in both cohorts (p < 0.05).
The use of radiomics features of intracranial plaques on high-resolution magnetic resonance imaging can effectively distinguish culprit plaques with diabetes as the primary pathological cause, which will provide new avenues of research into plaque formation and precise treatment.
糖尿病显著影响颅内动脉粥样硬化的形成和发展。本研究旨在评估放射组学特征是否有助于区分主要与糖尿病相关的斑块。
我们回顾性分析了 2016 年至 2022 年间因颅内动脉粥样硬化导致急性缺血性卒中而入住我院的患者。收集了所有患者的临床数据、血液生物标志物、常规斑块特征和斑块放射组学特征。使用逻辑回归模型确定比值比（OR）及其 95%置信区间（CI）。受试者工作特征（ROC）曲线和曲线下面积（AUC）用于描述诊断性能。使用 DeLong 检验比较模型之间的差异。
共有 157 例患者（115 例男性；平均年龄 58.7 ± 10.7 岁）纳入本研究。多变量逻辑回归分析显示，斑块长度（OR：1.17；95%CI：1.07-1.28）和面积（OR：1.13；95%CI：1.02-1.24）与糖尿病独立相关。将斑块长度和面积结合作为常规模型，其在训练和验证队列中识别糖尿病患者的 AUC 分别为 0.789 和 0.720。将 T1WI 和对比增强 T1WI 序列的放射组学特征相结合，可在训练和验证队列中获得更好的诊断价值（AUC：0.889 和 0.861）。DeLong 检验表明，在两个队列中，结合放射组学和常规斑块特征的模型均优于常规模型（p < 0.05）。
高分辨率磁共振成像上颅内斑块的放射组学特征可有效区分以糖尿病为主要病理原因的罪犯斑块，这将为斑块形成和精准治疗的研究提供新途径。
