Abstract
Acute stroke is one of the leading causes of disability and death worldwide. Regarding clinical diagnoses, a rapid and accurate procedure is necessary for patients suffering from acute stroke. This study proposes an automatic identification scheme for acute ischemic stroke using deep convolutional neural networks (DCNNs) based on non-contrast computed tomographic (NCCT) images. Our image database for the classification model was composed of 1254 grayscale NCCT images from 96 patients (573 images) with acute ischemic stroke and 121 normal controls (681 images). According to the consensus of critical stroke findings by two neuroradiologists, a gold standard was established and used to train the proposed DCNN using machine-generated image features. Including the earliest DCNN, AlexNet, the popular Inception-v3, and ResNet-101 were proposed. To train the limited data size, transfer learning with ImageNet parameters was also used. The established models were evaluated by tenfold cross-validation and tested on an independent dataset containing 50 patients with acute ischemic stroke (108 images) and 58 normal controls (117 images) from another institution. AlexNet without pretrained parameters achieved an accuracy of 97.12%, a sensitivity of 98.11%, a specificity of 96.08%, and an area under the receiver operating characteristic curve (AUC) of 0.9927. Using transfer learning, transferred AlexNet, transferred Inception-v3, and transferred ResNet-101 achieved accuracies between 90.49 and 95.49%. Tested with a dataset from another institution, AlexNet showed an accuracy of 60.89%, a sensitivity of 18.52%, and a specificity of 100%. Transferred AlexNet, Inception-v3, and ResNet-101 achieved accuracies of 81.77%, 85.78%, and 80.89%, respectively. The proposed DCNN architecture as a computer-aided diagnosis system showed that training from scratch can generate a customized model for a specific scanner, and transfer learning can generate a more generalized model to provide diagnostic suggestions of acute ischemic stroke to radiologists.
Similar content being viewed by others
References
World Health Organization W, Organization WH. The top 10 causes of death. 2014.
Feigin VL, Norrving B, Mensah GA. Global burden of stroke. Circulation research. 2017;120(3):439-48.
Krishnamurthi RV, Moran AE, Feigin VL, Barker-Collo S, Norrving B, Mensah GA, et al. Stroke prevalence, mortality and disability-adjusted life years in adults aged 20-64 years in 1990-2013: data from the global burden of disease 2013 study. Neuroepidemiology. 2015;45(3):190-202.
Savva GM, Stephan BC, Group AsSVDSR. Epidemiological studies of the effect of stroke on incident dementia: a systematic review. Stroke. 2010;41(1):e41-e6.
Phillips LA, Diefenbach MA, Abrams J, Horowitz CR. Stroke and TIA survivors’ cognitive beliefs and affective responses regarding treatment and future stroke risk differentially predict medication adherence and categorised stroke risk. Psychology & health. 2015;30(2):218-32.
Sacco RL, Adams R, Albers G, Alberts MJ, Benavente O, Furie K, et al. Guidelines for prevention of stroke in patients with ischemic stroke or transient ischemic attack: a statement for healthcare professionals from the American Heart Association/American Stroke Association Council on Stroke: co-sponsored by the Council on Cardiovascular Radiology and Intervention: the American Academy of Neurology affirms the value of this guideline. Stroke. 2006;37(2):577-617.
de Castro-Afonso LH, Nakiri GS, Pontes-Neto OM, dos Santos AC, Abud DG. International Survey on the Management of Wake-Up Stroke. Cerebrovascular diseases extra. 2016;6(1):22-6.
Hur J, Choi BW. Cardiac CT imaging for ischemic stroke: current and evolving clinical applications. Radiology. 2017;283(1):14-28.
Goldstein JH, Denslow SA, Goldstein SJ, Marx WF, Short JG, Taylor RD, et al. Intra-Arterial Therapy for Acute Stroke and the Effect of Technological Advances on Recanalization Findings in a Community Hospital. North Carolina medical journal. 2016;77(2):79-86.
Heiferman DM, Li DD, Pecoraro NC, Smolenski AM, Tsimpas A, Ashley Jr WW. Intra-arterial alteplase thrombolysis during mechanical thrombectomy for acute ischemic stroke. Journal of Stroke and Cerebrovascular Diseases. 2017;26(12):3004-8.
Kurz K, Ringstad G, Odland A, Advani R, Farbu E, Kurz M. Radiological imaging in acute ischaemic stroke. Eur J Neurol. 2016;23:8-17.
Kranz P, Eastwood J. Does diffusion-weighted imaging represent the ischemic core? An evidence-based systematic review. American Journal of Neuroradiology. 2009;30(6):1206-12.
von Kummer R, Dzialowski I. Imaging of cerebral ischemic edema and neuronal death. Neuroradiology. 2017;59(6):545-53.
Powers WJ, Rabinstein AA, Ackerson T, Adeoye OM, Bambakidis NC, Becker K, et al. 2018 guidelines for the early management of patients with acute ischemic stroke: a guideline for healthcare professionals from the American Heart Association/American Stroke Association. Stroke. 2018;49(3):e46-e99.
Muir KW, Buchan A, von Kummer R, Rother J, Baron J-C. Imaging of acute stroke. The Lancet Neurology. 2006;5(9):755-68.
Wintermark M, Rowley HA, Lev MH. Acute stroke triage to intravenous thrombolysis and other therapies with advanced CT or MR imaging: pro CT. Radiology. 2009;251(3):619-26.
Liu L, Tian Z, Zhang Z, Fei B. Computer-aided detection of prostate cancer with MRI: technology and applications. Academic radiology. 2016;23(8):1024-46.
Jalalian A, Mashohor S, Mahmud R, Karasfi B, Saripan MIB, Ramli ARB. Foundation and methodologies in computer-aided diagnosis systems for breast cancer detection. EXCLI journal. 2017;16:113.
Virmani J, Kumar V, Kalra N, Khandelwal N. SVM-based characterisation of liver cirrhosis by singular value decomposition of GLCM matrix. International Journal of Artificial Intelligence and Soft Computing. 2013;3(3):276-96.
Taşcı E, Uğur A. Shape and texture based novel features for automated juxtapleural nodule detection in lung CTs. Journal of medical systems. 2015;39(5):46.
Choi JJ, Kim SH, Kang BJ, Song BJ. Detectability and usefulness of automated whole breast ultrasound in patients with suspicious microcalcifications on mammography: comparison with handheld breast ultrasound. Journal of breast cancer. 2016;19(4):429-37.
Cheng PM, Malhi HS. Transfer learning with convolutional neural networks for classification of abdominal ultrasound images. Journal of digital imaging. 2017;30(2):234-43.
Gulshan V, Peng L, Coram M, Stumpe MC, Wu D, Narayanaswamy A, et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. Jama. 2016;316(22):2402-10.
Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM, et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017;542(7639):115.
Han SS, Kim MS, Lim W, Park GH, Park I, Chang SE. Classification of the clinical images for benign and malignant cutaneous tumors using a deep learning algorithm. J Invest Dermatol. 2018;138(7):1529-38.
Krizhevsky A, Sutskever I, Hinton GE, editors. Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst; 2012.
Kim D, MacKinnon T. Artificial intelligence in fracture detection: transfer learning from deep convolutional neural networks. Clinical radiology. 2018;73(5):439-45.
Chung SW, Han SS, Lee JW, Oh K-S, Kim NR, Yoon JP, et al. Automated detection and classification of the proximal humerus fracture by using deep learning algorithm. Acta Orthop. 2018;89(4):468-73.
Zech JR, Badgeley MA, Liu M, Costa AB, Titano JJ, Oermann EK. Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: A cross-sectional study. PLoS Med. 2018;15(11):e1002683.
Liang G, Zheng L. A transfer learning method with deep residual network for pediatric pneumonia diagnosis. Computer Methods and Programs in Biomedicine. 2019.
Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, et al., editors. Going deeper with convolutions. Proceedings of the IEEE conference on computer vision and pattern recognition; 2015.
He K, Zhang X, Ren S, Sun J, editors. Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition; 2016.
Smajlović D, Sinanović O. Sensitivity of the neuroimaging techniques in ischemic stroke. Medicinski arhiv. 2004;58(5):282-4.
Camargo EC, Furie KL, Singhal AB, Roccatagliata L, Cunnane ME, Halpern EF, et al. Acute brain infarct: detection and delineation with CT angiographic source images versus nonenhanced CT scans. Radiology. 2007;244(2):541-8.
Prakkamakul S, Yoo AJ. ASPECTS CT in acute ischemia: review of current data. Topics in Magnetic Resonance Imaging. 2017;26(3):103-12.
Yong SW, Bang OY, Lee PH, Li WY. Internal and cortical border-zone infarction: clinical and diffusion-weighted imaging features. Stroke. 2006;37(3):841-6.
Bal S, Bhatia R, Menon BK, Shobha N, Puetz V, Dzialowski I, et al. Time dependence of reliability of noncontrast computed tomography in comparison to computed tomography angiography source image in acute ischemic stroke. International Journal of Stroke. 2015;10(1):55-60.
Demeestere J, Scheldeman L, Cornelissen SA, Heye S, Wouters A, Dupont P, et al. Alberta stroke program early CT score versus computed tomographic perfusion to predict functional outcome after successful reperfusion in acute ischemic stroke. Stroke. 2018;49(10):2361-7.
Yan S, Jin X, Zhang X, Zhang S, Liebeskind DS, Lou M. Extensive cerebral microbleeds predict parenchymal haemorrhage and poor outcome after intravenous thrombolysis. J Neurol Neurosurg Psychiatry. 2015:jnnp-2014–309857.
Nowinski WL, Gupta V, Qian G, He J, Poh LE, Ambrosius W, et al. Automatic detection, localization, and volume estimation of ischemic infarcts in noncontrast computed tomographic scans: method and preliminary results. Investigative radiology. 2013;48(9):661-70.
Tyan Y-S, Wu M-C, Chin C-L, Kuo Y-L, Lee M-S, Chang H-Y. Ischemic stroke detection system with a computer-aided diagnostic ability using an unsupervised feature perception enhancement method. Journal of Biomedical Imaging. 2014;2014:19.
Gomolka RS, Chrzan RM, Urbanik A, Nowinski WL. A quantitative method using head noncontrast CT scans to detect hyperacute nonvisible ischemic changes in patients with stroke. Journal of Neuroimaging. 2016;26(6):581-7.
Maegerlein C, Fischer J, Mönch S, Berndt M, Wunderlich S, Seifert CL, et al. Automated Calculation of the Alberta Stroke Program Early CT Score: Feasibility and Reliability. Radiology. 2019;291(1):141-8.
Rutczyńska A, Przelaskowski A, Jasionowska M, Ostrek G. Method of brain structure extraction for CT-based stroke detection. Information Technologies in Biomedicine: Springer; 2010. p. 133–44.
Wu G, Lin J, Chen X, Li Z, Wang Y, Zhao J, et al. Early identification of ischemic stroke in noncontrast computed tomography. Biomed Signal Process Control. 2019;52:41-52.
Funding
The authors received financial support from the Ministry of Science and Technology of Taiwan (MOST 108-2221-E-004-010-MY3), the University System of Taipei Joint Research Program (USTP-NTPU-TMU-107-01), and the Mackay Memorial Hospital (MMH-106-150).
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
Conflict of Interest
The authors declare no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Lo, CM., Hung, PH. & Lin, DT. Rapid Assessment of Acute Ischemic Stroke by Computed Tomography Using Deep Convolutional Neural Networks. J Digit Imaging 34, 637–646 (2021). https://doi.org/10.1007/s10278-021-00457-y
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10278-021-00457-y