期刊
LANCET
卷 392, 期 10162, 页码 2388-2396出版社
ELSEVIER SCIENCE INC
DOI: 10.1016/S0140-6736(18)31645-3
关键词
-
资金
- Qure.ai
Background Non-contrast head CT scan is the current standard for initial imaging of patients with head trauma or stroke symptoms. We aimed to develop and validate a set of deep learning algorithms for automated detection of the following key findings from these scans: intracranial haemorrhage and its types (ie, intraparenchymal, intraventricular, subdural, extradural, and subarachnoid); calvarial fractures; midline shift; and mass effect. Methods We retrospectively collected a dataset containing 313 318 head CT scans together with their clinical reports from around 20 centres in India between Jan 1, 2011, and June 1, 2017. A randomly selected part of this dataset (Qure25k dataset) was used for validation and the rest was used to develop algorithms. An additional validation dataset (CQ500 dataset) was collected in two batches from centres that were different from those used for the development and Qure25k datasets. We excluded postoperative scans and scans of patients younger than 7 years. The original clinical radiology report and consensus of three independent radiologists were considered as gold standard for the Qure25k and CQ500 datasets, respectively. Areas under the receiver operating characteristic curves (AUCs) were primarily used to assess the algorithms. Findings The Qure25k dataset contained 21 095 scans (mean age 43 years; 9030 [43%] female patients), and the CQ500 dataset consisted of 214 scans in the first batch (mean age 43 years; 94 [44%] female patients) and 277 scans in the second batch (mean age 52 years; 84 [30%] female patients). On the Qure25k dataset, the algorithms achieved an AUC of 0.92 (95% CI 0.91-0.93) for detecting intracranial haemorrhage (0.90 [0.89-0.91] for intraparenchymal, 0.96 [0.94-0.97] for intraventricular, 0.92 [0.90-0.93] for subdural, 0.93 [0.91-0.95] for extradural, and 0.90 [0.89-0.92] for subarachnoid). On the CQ500 dataset, AUC was 0.94 (0.92-0.97) for intracranial haemorrhage (0.95 [0.93-0.98], 0.93 [0.87-1.00], 0.95 [0.91-0.99], 0.97 [0.91-1.00], and 0.96 [0.92-0.99], respectively). AUCs on the Qure25k dataset were 0.92 (0.91-0.94) for calvarial fractures, 0.93 (0.91-0.94) for midline shift, and 0.86 (0.85-0.87) for mass effect, while AUCs on the CQ500 dataset were 0.96 (0.92-1.00), 0.97 (0.94-1.00), and 0.92 (0.89-0.95), respectively. Interpretation Our results show that deep learning algorithms can accurately identify head CT scan abnormalities requiring urgent attention, opening up the possibility to use these algorithms to automate the triage process. Copyright (c) 2018 Elsevier Ltd. All rights reserved.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据