Scholarlink

Purpose <p>Prediction of stroke symptoms from perfusion patterns in ischemic stroke imaging would be desirable for decision making in relevant clinical scenarios as for example after incomplete mechanical thrombectomy or in perioperative strokes. Aim was to train a&#xa0;model to detect a&#xa0;major stroke defined as NIHSS &gt; 5.</p> Methods <p>Retrospective study of patients from the prospectively collected local Stroke Registry with large-/medium-vessel anterior circulation or without occlusion from 01/2015–12/2021 (N = 982, median age 74.5 (IQR 64.3–82), 47.5% female). Splits into training-set (80%), validation-set (10%) and temporally separated internal test-set (10%). Admission MR-perfusion Tmax-maps from 6&#xa0;different MR-scanners were used as input for an 18-layer 3D-ResNet to predict major stroke (NIHSS &gt; 5). Association of reported and predicted NIHSS &gt; 5 with 90-days modified Rankin Scale (mRS) &gt; 2 was tested using multivariate logistic regression.</p> Results <p>Vessel occlusion was observed in 80% and NIHSS &gt; 5 in 50% of all patients. On the internal test-set, Receiver Operating Characteristic area under the curve (ROC-AUC) was 0.87 (95%-CI ± 0.04) and Precision-Recall-AUC (PR-AUC) 0.85 (95%-CI ± 0.05). Accuracy was 78%, weighted F1-score 0.78. Including only vessel occlusions in the internal test-set, ROC-AUC was 0.81 (95%-CI ± 0.05) and PR-AUC 0.87 (95%-CI ± 0.05), accuracy was 73%, weighted F1-score 0.73. Reported NIHSS &gt; 5 (aOR 2.03, 95%-CI 0.94–4.38, <i>p</i> = 0.07) and predicted NIHSS &gt; 5 (aOR 3.61, 95%-CI 0.88–14.88, <i>p</i> = 0.08) both predicted 90-days mRS &gt; 2, with similar model performance (BIC: 310.6 vs. 310.7; AIC: 252.4 vs. 252.5).</p> Conclusion <p>Prediction of a&#xa0;major stroke (NIHSS &gt; 5) from MR-perfusion Tmax-maps was feasible and performed well on our internal test set.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Prediction of Major Stroke (NIHSS > 5) Based on MR Perfusion Imaging Using a 3D ResNet

  • 期刊论文

  • 发表日期：

    2026年2月17日

查看全文
  • Christoph C. Kurmann,
  • Adnan Mujanovic,
  • Morin Beyeler,
  • Leander Clénin,
  • Philipp Becker,
  • Roman Rohner,
  • Richard McKinley,
  • Shaokai Zheng,
  • Marta Olive Gadea,
  • Eike Immo Piechowiak,
  • Tomas Dobrocky,
  • Sara Pilgram-Pastor,
  • Valerian Altersberger,
  • Bruce Campbell,
  • Thomas Raphael Meinel,
  • David Seiffge,
  • Urs Fischer,
  • Jan Gralla,
  • Johannes Kaesmacher

摘要

Purpose

Prediction of stroke symptoms from perfusion patterns in ischemic stroke imaging would be desirable for decision making in relevant clinical scenarios as for example after incomplete mechanical thrombectomy or in perioperative strokes. Aim was to train a model to detect a major stroke defined as NIHSS > 5.

Methods

Retrospective study of patients from the prospectively collected local Stroke Registry with large-/medium-vessel anterior circulation or without occlusion from 01/2015–12/2021 (N = 982, median age 74.5 (IQR 64.3–82), 47.5% female). Splits into training-set (80%), validation-set (10%) and temporally separated internal test-set (10%). Admission MR-perfusion Tmax-maps from 6 different MR-scanners were used as input for an 18-layer 3D-ResNet to predict major stroke (NIHSS > 5). Association of reported and predicted NIHSS > 5 with 90-days modified Rankin Scale (mRS) > 2 was tested using multivariate logistic regression.

Results

Vessel occlusion was observed in 80% and NIHSS > 5 in 50% of all patients. On the internal test-set, Receiver Operating Characteristic area under the curve (ROC-AUC) was 0.87 (95%-CI ± 0.04) and Precision-Recall-AUC (PR-AUC) 0.85 (95%-CI ± 0.05). Accuracy was 78%, weighted F1-score 0.78. Including only vessel occlusions in the internal test-set, ROC-AUC was 0.81 (95%-CI ± 0.05) and PR-AUC 0.87 (95%-CI ± 0.05), accuracy was 73%, weighted F1-score 0.73. Reported NIHSS > 5 (aOR 2.03, 95%-CI 0.94–4.38, p = 0.07) and predicted NIHSS > 5 (aOR 3.61, 95%-CI 0.88–14.88, p = 0.08) both predicted 90-days mRS > 2, with similar model performance (BIC: 310.6 vs. 310.7; AIC: 252.4 vs. 252.5).

Conclusion

Prediction of a major stroke (NIHSS > 5) from MR-perfusion Tmax-maps was feasible and performed well on our internal test set.