Search

Summary 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. Funding Qure.ai.

Background: Currently, no large dataset-derived standard has been established for normal or pathologic human cerebral ventricular and cranial vault volumes. Manual image segmentation is impractical and laborious, and most efforts utilize linear or two-dimensional approaches. Automated volumetric measurements could be used to construct normal reference tables and assist in diagnosis and follow-up of hydrocephalus or craniofacial syndromes. In this work we utilize big data and deep learning algorithms to measure ventricular and cranial vault volumes in head computed tomography (CT) scans. Methods: A dataset comprising 13,851 scans was utilized to deploy U-net deep learning networks to segment and quantify lateral cerebral ventricular and cranial vault volumes in relation to age and sex. The models were validated against manual segmentations. The radiological reports of the dataset were annotated using a rule-based natural language processing (NLP) framework to identify normal scans, cerebral atrophy, or hydrocephalus. Findings: U-net models were fast with high fidelity when compared to manual segmentations for both lateral ventricular and cranial vault volume measurements (DICE 0·909 and 0·983, respectively). The NLP identified 6,239 (44·7%) normal radiological reports, 1,827 (13·1%) with cerebral atrophy and 1,185 (8·5%) with hydrocephalus. Age- and sex-based refence tables with medians, 25th and 75th percentiles for scans classified as normal, atrophy and hydrocephalus were constructed. The median lateral ventricular volume in normal scans was statistically significantly smaller compared to hydrocephalus (15·7 mL [11·1, 22·2] vs 82·0 mL [51·1, 126] respectively, P