Abstract
A deep learning algorithm for time-of-flight MR angiography source images detected cerebral aneurysms noted in radiological reports with a sensitivity of 91%–93% and improved aneurysm detection by 4.8%–13% compared with the initial reports.
Purpose
To develop and evaluate a supportive algorithm using deep learning for detecting cerebral aneurysms at time-of-flight MR angiography to provide a second assessment of images already interpreted by radiologists.
Materials and Methods
MR images reported by radiologists to contain aneurysms were extracted from four institutions for the period from November 2006 through October 2017. The images were divided into three data sets: training data set, internal test data set, and external test data set. The algorithm was constructed by deep learning with the training data set, and its sensitivity to detect aneurysms in the test data sets was evaluated. To find aneurysms that had been overlooked in the initial reports, two radiologists independently performed a blinded interpretation of aneurysm candidates detected by the algorithm. When there was disagreement, the final diagnosis was made in consensus. The number of newly detected aneurysms was also evaluated.
Results
The training data set, which provided training and validation data, included 748 aneurysms (mean size, 3.1 mm ± 2.0 [standard deviation]) from 683 examinations; 318 of these examinations were on male patients (mean age, 63 years ± 13) and 365 were on female patients (mean age, 64 years ± 13). Test data were provided by the internal test data set (649 aneurysms [mean size, 4.1 mm ± 3.2] in 521 examinations, including 177 male patients and 344 female patients with mean age of 66 years ± 12 and 67 years ± 13, respectively) and the external test data set (80 aneurysms [mean size, 4.1 mm ± 2.1] in 67 examinations, including 19 male patients and 48 female patients with mean age of 63 years ± 12 and 68 years ± 12, respectively). The sensitivity was 91% (592 of 649) and 93% (74 of 80) for the internal and external test data sets, respectively. The algorithm improved aneurysm detection in the internal and external test data sets by 4.8% (31 of 649) and 13% (10 of 80), respectively, compared with the initial reports.
Conclusion
A deep learning algorithm detected cerebral aneurysms in radiologic reports with high sensitivity and improved aneurysm detection compared with the initial reports.
© RSNA, 2018
See also the editorial by Flanders in this issue.
References
- 1. . Subarachnoid haemorrhage. Lancet 2007;369(9558):306–318.
- 2. The natural course of unruptured cerebral aneurysms in a Japanese cohort. N Engl J Med 2012;366(26):2474–2482.
- 3. . A multinational comparison of subarachnoid hemorrhage epidemiology in the WHO MONICA stroke study. Stroke 2000;31(5):1054–1061.
- 4. . Case-fatality rates and functional outcome after subarachnoid hemorrhage: a systematic review. Stroke 1997;28(3):660–664.
- 5. . Can noninvasive imaging accurately depict intracranial aneurysms? A systematic review. Radiology 2000;217(2):361–370.
- 6. . Deep learning. Nature 2015;521(7553):436–444.
- 7. . Deep learning at chest radiography: automated classification of pulmonary tuberculosis by using convolutional neural networks. Radiology 2017;284(2):574–582.
- 8. . Performance of a deep-learning neural network model in assessing skeletal maturity on pediatric hand radiographs. Radiology 2018;287(1):313–322.
- 9. . Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016; 770–778.
- 10. Feasibility of a curvature-based enhanced display system for detecting cerebral aneurysms in MR angiography. Magn Reson Med Sci 2003;2(1):29–36.
- 11. . Sensitivity analysis of kappa-fold cross validation in prediction error estimation. IEEE Trans Pattern Anal Mach Intell 2010;32(3):569–575.
- 12. Automated computerized scheme for detection of unruptured intracranial aneurysms in three-dimensional magnetic resonance angiography. Acad Radiol 2004;11(10):1093–1104.
- 13. Intracranial aneurysms at MR angiography: effect of computer-aided diagnosis on radiologists’ detection performance. Radiology 2005;237(2):605–610.
- 14. Diagnostic accuracy and reading time to detect intracranial aneurysms on MR angiography using a computer-aided diagnosis system. AJR Am J Roentgenol 2008;190(2):459–465.
- 15. . Computer-aided detection of intracranial aneurysms in MR angiography. J Digit Imaging 2011;24(1):86–95.
- 16. Computer-aided diagnosis improves detection of small intracranial aneurysms on MRA in a clinical setting. AJNR Am J Neuroradiol 2014;35(10):1897–1902.
- 17. Deep neural network-based computer-assisted detection of cerebral aneurysms in MR angiography. J Magn Reson Imaging 2018;47(4):948–953.
- 18. Performance improvement in computerized detection of cerebral aneurysms by retraining classifier using feedback data collected in routine reading environment. J Biomed Graph Comput 2014;4(4):12.
- 19. Computer-assisted detection of crebral aneurysms in MR angiography in a routine image-reading environment: effects on diagnosis by radiologists. AJNR Am J Neuroradiol 2016;37(6):1038–1043.
- 20. Unruptured intracranial aneurysms: natural history, clinical outcome, and risks of surgical and endovascular treatment. Lancet 2003;362(9378):103–110.
Article History
Received: Apr 15 2018Revision requested: June 1 2018
Revision received: Aug 27 2018
Accepted: Sept 4 2018
Published online: Oct 23 2018
Published in print: Jan 2019
