A deep learning algorithm may automate intracranial aneurysm detection on MR angiography with high diagnostic performance

To develop a deep learning algorithm for automated detection and localization of intracranial aneurysms on time-of-flight MR angiography and evaluate its diagnostic performance. In a retrospective and multicenter study, MR images with aneurysms based on radiological reports were extracted. The examinations were randomly divided into two data sets: training set of 468 examinations and internal test set of 120 examinations. Additionally, 50 examinations without aneurysms were randomly selected and added to the internal test set. External test data set consisted of 56 examinations with intracranial aneurysms and 50 examinations without aneurysms, which were extracted based on radiological reports from a different institution. After manual ground truth segmentation of aneurysms, a deep learning algorithm based on 3D ResNet architecture was established with the training set. Its sensitivity, positive predictive value, and specificity were evaluated in the internal and external test sets. MR images included 551 aneurysms (mean diameter, 4.17 ± 2.49 mm) in the training, 147 aneurysms (mean diameter, 3.98 ± 2.11 mm) in the internal test, 63 aneurysms (mean diameter, 3.23 ± 1.69 mm) in the external test sets. The sensitivity, the positive predictive value, and the specificity were 87.1%, 92.8%, and 92.0% for the internal test set and 85.7%, 91.5%, and 98.0% for the external test set, respectively. A deep learning algorithm detected intracranial aneurysms with a high diagnostic performance which was validated using external data set. • A deep learning-based algorithm for the automated diagnosis of intracranial aneurysms demonstrated a high sensitivity, positive predictive value, and specificity. • The high diagnostic performance of the algorithm was validated using external test data set from a different institution with a different scanner. • The algorithm might be robust and effective for general use in real clinical settings.

[1]  Michael Forsting,et al.  European Stroke Organization Guidelines for the Management of Intracranial Aneurysms and Subarachnoid Haemorrhage , 2013, Cerebrovascular Diseases.

[2]  Jin Pyeong Jeon,et al.  Machine Learning Application for Rupture Risk Assessment in Small-Sized Intracranial Aneurysm , 2019, Journal of clinical medicine.

[3]  A. Ng,et al.  Deep Learning–Assisted Diagnosis of Cerebral Aneurysms Using the HeadXNet Model , 2019, JAMA network open.

[4]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[5]  Osamu Abe,et al.  Deep neural network‐based computer‐assisted detection of cerebral aneurysms in MR angiography , 2018, Journal of magnetic resonance imaging : JMRI.

[6]  A. Molyneux,et al.  Risk Analysis of Unruptured Intracranial Aneurysms: Prospective 10-Year Cohort Study , 2016, Stroke.

[7]  Kunio Doi,et al.  Diagnostic accuracy and reading time to detect intracranial aneurysms on MR angiography using a computer-aided diagnosis system. , 2008, AJR. American journal of roentgenology.

[8]  Ming-Hua Li,et al.  Accurate diagnosis of small cerebral aneurysms ≤5 mm in diameter with 3.0-T MR angiography. , 2014, Radiology.

[9]  Bradley James Erickson,et al.  Computer-Aided Detection of Intracranial Aneurysms in MR Angiography , 2011, Journal of Digital Imaging.

[10]  Joseph N Stember,et al.  Convolutional Neural Networks for the Detection and Measurement of Cerebral Aneurysms on Magnetic Resonance Angiography , 2018, Journal of Digital Imaging.

[11]  K. Nozaki,et al.  Rupture risk of small unruptured cerebral aneurysms. , 2019, Journal of neurosurgery.

[12]  P. Nelemans,et al.  Diagnosing Intracranial Aneurysms With MR Angiography: Systematic Review and Meta-Analysis , 2014, Stroke.

[13]  U. Schoepf,et al.  Artificial Intelligence in the Management of Intracranial Aneurysms: Current Status and Future Perspectives , 2020, American Journal of Neuroradiology.

[14]  S. Juvela,et al.  Intracranial Aneurysm Parameters for Predicting a Future Subarachnoid Hemorrhage: A Long‐Term Follow‐up Study , 2017, Neurosurgery.

[15]  O. Kwon,et al.  Natural History of Unruptured Intracranial Aneurysms : A Retrospective Single Center Analysis , 2016, Journal of Korean Neurosurgical Society.

[16]  M. Wiesmann,et al.  Deep Learning–Based Detection of Intracranial Aneurysms in 3D TOF-MRA , 2018, American Journal of Neuroradiology.

[17]  J. Provenzale,et al.  Current imaging assessment and treatment of intracranial aneurysms. , 2011, AJR. American journal of roentgenology.

[18]  Daiju Ueda,et al.  Deep Learning for MR Angiography: Automated Detection of Cerebral Aneurysms. , 2019, Radiology.

[19]  Chao Li,et al.  Threshold segmentation algorithm for automatic extraction of cerebral vessels from brain magnetic resonance angiography images , 2015, Journal of Neuroscience Methods.

[20]  G. Rinkel,et al.  Subarachnoid haemorrhage , 2006, BMJ : British Medical Journal.

[21]  A. Cruickshank,et al.  Subarachnoid haemorrhage , 2007, The Lancet.

[22]  A. Algra,et al.  Prevalence of unruptured intracranial aneurysms, with emphasis on sex, age, comorbidity, country, and time period: a systematic review and meta-analysis , 2011, The Lancet Neurology.

[23]  D J Blezek,et al.  Computer-Aided Diagnosis Improves Detection of Small Intracranial Aneurysms on MRA in a Clinical Setting , 2014, American Journal of Neuroradiology.

[24]  S. Fukuhara,et al.  The natural course of unruptured cerebral aneurysms in a Japanese cohort. , 2012, The New England journal of medicine.

[25]  Kunio Doi,et al.  Intracranial aneurysms at MR angiography: effect of computer-aided diagnosis on radiologists' detection performance. , 2005, Radiology.