Data Science Office, Mass General Brigham, 100 Cambridge St, Suite 1303, Boston, MA, 02114, USA.
Department of Radiology, Massachusetts General Hospital, Harvard Medical School, Boston, MA, USA.
Sci Rep. 2023 Jan 5;13(1):189. doi: 10.1038/s41598-023-27496-5.
Non-contrast head CT (NCCT) is extremely insensitive for early (< 3-6 h) acute infarct identification. We developed a deep learning model that detects and delineates suspected early acute infarcts on NCCT, using diffusion MRI as ground truth (3566 NCCT/MRI training patient pairs). The model substantially outperformed 3 expert neuroradiologists on a test set of 150 CT scans of patients who were potential candidates for thrombectomy (60 stroke-negative, 90 stroke-positive middle cerebral artery territory only infarcts), with sensitivity 96% (specificity 72%) for the model versus 61-66% (specificity 90-92%) for the experts; model infarct volume estimates also strongly correlated with those of diffusion MRI (r > 0.98). When this 150 CT test set was expanded to include a total of 364 CT scans with a more heterogeneous distribution of infarct locations (94 stroke-negative, 270 stroke-positive mixed territory infarcts), model sensitivity was 97%, specificity 99%, for detection of infarcts larger than the 70 mL volume threshold used for patient selection in several major randomized controlled trials of thrombectomy treatment.
非对比头部 CT（NCCT）对早期（<3-6 小时）急性梗死的识别非常不敏感。我们开发了一种深度学习模型，该模型使用弥散 MRI 作为ground truth（3566 对 NCCT/MRI 训练患者对）来检测和描绘 NCCT 上疑似早期急性梗死。该模型在 150 例可能接受血栓切除术治疗的患者 CT 扫描的测试集中（60 例中风阴性，90 例中风阳性仅大脑中动脉区域梗死），对专家表现出明显的优势，敏感性为 96%（特异性为 72%），而专家的敏感性为 61-66%（特异性为 90-92%）；模型梗死体积估计也与弥散 MRI 具有很强的相关性（r>0.98）。当将这个包含 364 例 CT 扫描的 150 例 CT 测试集扩展到包括更具异质性的梗死位置分布（94 例中风阴性，270 例中风阳性混合区域梗死）时，模型对梗死体积大于几项主要血栓切除术治疗随机对照试验中用于患者选择的 70ml 体积阈值的检测的敏感性为 97%，特异性为 99%。
