The DOI matches its Crossref record; 35 of the 35 references it cites were found in a registry or an index.
Deep learning algorithms for detection of critical findings in head CT scans: a retrospective study
Abstract
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.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“The CQ500 dataset, consisting of 1154 available CT scans from 491 patients, was downloaded from the Qure.ai website51.”
From Towards a holistic framework for multimodal LLM in 3D brain CT radiology report generation (2025) · cites this paper as [51]
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538
Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2016) · arXiv · doi:10.48550/arxiv.1606.00915 · Cited by 22,392
The meaning and use of the area under a receiver operating characteristic (ROC) curve.
Hanley, J. A., & McNeil, B. J. (1982) · Radiology · doi:10.1148/radiology.143.1.7063747 · Cited by 21,856
Statistical Methods for Rates and Proportions
Fleiss, J. L., Levin, B., & Paik, M. C. (2003) · Wiley Series in Probability and Statistics · doi:10.1002/0471445428 · Cited by 18,646
A survey on deep learning in medical image analysis
Litjens, G., Kooi, T., Bejnordi, B. E., Setio, A. A. A., Ciompi, F., Ghafoorian, M., van der Laak, J. A. W. M., van Ginneken, B., & Sánchez, C. I. (2017) · Medical Image Analysis · doi:10.1016/j.media.2017.07.005 · Cited by 15,332
Dermatologist-level classification of skin cancer with deep neural networks
Esteva, A., Kuprel, B., Novoa, R. A., Ko, J., Swetter, S. M., Blau, H. M., & Thrun, S. (2017) · Nature · doi:10.1038/nature21056 · Cited by 14,362
Measuring nominal scale agreement among many raters.
Fleiss, J. L. (1971) · Psychological Bulletin · doi:10.1037/h0031619 · Cited by 8,733
Guidelines for the Early Management of Patients With Acute Ischemic Stroke
Jauch, E. C., Saver, J. L., Adams, H. P., Bruno, A., Connors, J. J. “., Demaerschalk, B. M., Khatri, P., McMullan, P. W., Qureshi, A. I., Rosenfield, K., et al. (2013) · Stroke · doi:10.1161/str.0b013e318284056a · Cited by 7,698
Gulshan, V., Peng, L., Coram, M., Stumpe, M. C., Wu, D., Narayanaswamy, A., Venugopalan, S., Widner, K., Madams, T., Cuadros, J., et al. (2016) · JAMA · doi:10.1001/jama.2016.17216 · Cited by 7,697
(2005) · PubMed · Cited by 7,011
Research works printed but not linked: 1
- Yamada A, Teramoto A, Otsuka T, Kudo K, Anno H, Fujita H. Preliminary study on the automated skull fracture detection in CT images using black-hat transform. 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society; Orlando, FL; Aug 17–20, 2016. 6437–40. · DOI
Cited by
Sorted by citations
High-performance medicine: the convergence of human and artificial intelligence
Topol, E. J. (2019) · Nature Medicine · doi:10.1038/s41591-018-0300-7 · Cited by 10,450
Rajkomar, A., Dean, J., & Kohane, I. (2019) · New England Journal of Medicine · doi:10.1056/nejmra1814259 · Cited by 4,579
Key challenges for delivering clinical impact with artificial intelligence
Kelly, C. J., Karthikesalingam, A., Suleyman, M., Corrado, G., & King, D. (2019) · BMC Medicine · doi:10.1186/s12916-019-1426-2 · Cited by 3,136
Deep learning-enabled medical computer vision
Esteva, A., Chou, K., Yeung, S., Naik, N., Madani, A., Mottaghi, A., Liu, Y., Topol, E., Dean, J., & Socher, R. (2021) · npj Digital Medicine · doi:10.1038/s41746-020-00376-2 · Cited by 1,406
A Weakly-Supervised Framework for COVID-19 Classification and Lesion Localization From Chest CT
Zheng, C., Deng, X., Fu, Q., Zhou, Q., Feng, J., Ma, H., Liu, W., & Wang, X. (2020) · IEEE Transactions on Medical Imaging · doi:10.1109/tmi.2020.2995965 · Cited by 1,253
Metadata
- Authors
- Chilamkurthy, S., Ghosh, R., Tanamala, S., Biviji, M., Campeau, N. G., Venugopal, V. K., Mahajan, V., Rao, P., & Warier, P.
- Affiliations
- Qure.ai Technologies Private Limited (India) (IN)
- Mayo Clinic (US)
- Corresponding author
- Chilamkurthy, Sasank
- Venue
- The Lancet
- Publisher
- Elsevier BV
- Published
- 2018-12
- Volume
- 392
- Issue
- 10162
- Pages
- 2388-2396
- ISSN
- 0099-5355 (ISSN-L)
- 0140-6736
- OpenAlex
- W2896817483
- Cited by
- 1,020
- References
- 33
- Citations by year
- 2026: 96 · 2025: 144 · 2024: 163 · 2023: 148 · 2022: 115 · 2021: 146 · 2020: 134 · 2019: 66 · 2018: 7
- FWCI
- 23.93
- Type
- journal article
- Language
- en
- Open access
- closed
- Locations
- The Lancet (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Health Sciences › Medicine › Health Informatics › Artificial Intelligence in Healthcare and Education
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Brain Tumor Detection and Classification
- Physical Sciences › Engineering › Biomedical Engineering › Medical Imaging and Analysis
- Keywords
- automated detection, head CT, intracranial hemorrhage, intraventricular hemorrhage, subdural hematoma, subarachnoid hemorrhage, epidural hematoma, intraparenchymal hemorrhage, calvarial fractures, midline shift, mass effect, deep learning
- MeSH terms
- Deep Learning, Algorithms, Brain Injuries, Head, Humans, Retrospective Studies, Skull Fractures, Tomography, X-Ray Computed, Triage, Trauma Severity Indices, Intracranial Hemorrhages, Datasets as Topic
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
