Developing a model for estimating infarction onset time based on computed tomography radiomics in patients with acute middle cerebral artery occlusion

Background Radiomics analysis is a newly emerging quantitative image analysis technique. The aim of this study was to extract a radiomics signature from the computed tomography (CT) imaging to determine the infarction onset time in patients with acute middle cerebral artery occlusion (MCAO). Methods A total of 123 patients with acute MCAO in the M1 segment (85 patients in the development cohort and 38 patients in the validation cohort) were enrolled in the present study. Clinicoradiological profiles, including head CT without contrast enhancement and computed tomographic angiography (CTA), were collected. The time from stroke onset (TFS) was classified into two subcategories: ≤ 4.5 h, and > 4.5 h. The middle cerebral artery (MCA) territory on CT images was segmented to extract and score the radiomics features associated with the TFS. In addition, the clinicoradiological factors related to the TFS were identified. Subsequently, a combined model of the radiomics signature and clinicoradiological factors was constructed to distinguish the TFS ≤ 4.5 h. Finally, we evaluated the overall performance of our constructed model in an external validation sample of ischemic stroke patients with acute MCAO in the M1 segment. Results The area under the curve (AUC) of the radiomics signature for discriminating the TFS in the development and validation cohorts was 0.770 (95% confidence interval (CI): 0.665–0.875) and 0.792 (95% CI: 0.633–0.950), respectively. The AUC of the combined model comprised of the radiomics signature, age and ASPECTS on CT in the development and validation cohorts was 0.808 (95% CI: 0.701–0.916) and 0.833 (95% CI: 0.702–0.965), respectively. In the external validation cohort, the AUC of the radiomics signature was 0.755 (95% CI: 0.614–0.897), and the AUC of the combined model was 0.820 (95% CI: 0.712–0.928). Conclusions The CT-based radiomics signature is a valuable tool for discriminating the TFS in patients with acute MCAO in the M1 segment, which may guide the use of thrombolysis therapy in patients with indeterminate stroke onset time.

[1]  S. Bombois,et al.  Texture Features of Magnetic Resonance Images: an Early Marker of Post-stroke Cognitive Impairment , 2019, Translational Stroke Research.

[2]  P. Pang,et al.  MRI-based Radiomics nomogram to detect primary rectal cancer with synchronous liver metastases , 2019, Scientific Reports.

[3]  E. DeLong,et al.  Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. , 1988, Biometrics.

[4]  J. Arenillas,et al.  Perfusion Computed Tomography-Guided Intravenous Thrombolysis for Acute Ischemic Stroke beyond 4.5 Hours: A Case-Control Study , 2012, Cerebrovascular Diseases.

[5]  Keith Muir,et al.  Effects of alteplase beyond 3 h after stroke in the Echoplanar Imaging Thrombolytic Evaluation Trial (EPITHET): a placebo-controlled randomised trial , 2008, The Lancet Neurology.

[6]  Marc Fisher,et al.  Stroke , 2008, The Lancet.

[7]  Filippo Cademartiri,et al.  Cardiac computed tomography radiomics: an emerging tool for the non-invasive assessment of coronary atherosclerosis. , 2020, Cardiovascular diagnosis and therapy.

[8]  Hilde van der Togt,et al.  Publisher's Note , 2003, J. Netw. Comput. Appl..

[9]  Haruko Yamamoto,et al.  THrombolysis for Acute Wake-up and unclear-onset Strokes with alteplase at 0·6 mg/kg (THAWS) Trial , 2014, International journal of stroke : official journal of the International Stroke Society.

[10]  A. Demchuk,et al.  CT Angiography Clot Burden Score and Collateral Score: Correlation with Clinical and Radiologic Outcomes in Acute Middle Cerebral Artery Infarct , 2009, American Journal of Neuroradiology.

[11]  D. Blezek,et al.  A quantitative symmetry‐based analysis of hyperacute ischemic stroke lesions in noncontrast computed tomography , 2017, Medical physics.

[12]  Impact of Collateral Circulation on Early Outcome and Risk of Hemorrhagic Complications after Systemic Thrombolysis , 2014, International journal of stroke : official journal of the International Stroke Society.

[13]  Xiang Yao,et al.  CT radiomics features as a diagnostic tool for classifying basal ganglia infarction onset time , 2020, Journal of the Neurological Sciences.

[14]  Y. Loh,et al.  Clinical Outcomes in Middle Cerebral Artery Trunk Occlusions Versus Secondary Division Occlusions After Mechanical Thrombectomy: Pooled Analysis of the Mechanical Embolus Removal in Cerebral Ischemia (MERCI) and Multi MERCI Trials , 2010, Stroke.

[15]  Hyun Goo Kang,et al.  Magnetic Resonance Imaging in Acute Ischemic Stroke Treatment , 2014, Journal of stroke.

[16]  Estanislao Arana,et al.  Influence of gray level and space discretization on brain tumor heterogeneity measures obtained from magnetic resonance images , 2016, Comput. Biol. Medicine.

[17]  David Moratal,et al.  Identification of the presence of ischaemic stroke lesions by means of texture analysis on brain magnetic resonance images , 2019, Comput. Medical Imaging Graph..

[18]  Ernst Klotz,et al.  Ischemic brain tissue water content: CT monitoring during middle cerebral artery occlusion and reperfusion in rats. , 2007, Radiology.

[19]  D. Saloner,et al.  Identification of high-risk plaque features in intracranial atherosclerosis: initial experience using a radiomic approach , 2018, European Radiology.

[20]  V. Caso,et al.  Neuroimaging in Intracerebral Hemorrhage , 2014, Stroke.

[21]  M. Mokin,et al.  ASPECTS (Alberta Stroke Program Early CT Score) Measurement Using Hounsfield Unit Values When Selecting Patients for Stroke Thrombectomy , 2017, Stroke.

[22]  L. Pace,et al.  Clinically significant prostate cancer detection on MRI: A radiomic shape features study. , 2019, European Journal of Radiology.

[23]  Yumei Li,et al.  Prediction of Malignant Acute Middle Cerebral Artery Infarction via Computed Tomography Radiomics , 2020, Frontiers in Neuroscience.

[24]  M. Endres,et al.  Fluid-Attenuated Inversion Recovery Evolution Within 12 Hours From Stroke Onset: A Reliable Tissue Clock? , 2010, Stroke.

[25]  A. Alexandrov,et al.  Reperfusion Therapies of Acute Ischemic Stroke: Potentials and Failures , 2014, Front. Neurol..

[26]  Jinhua Yu,et al.  White Matter High Signals Interfere with Noncontrast Computed Tomography in the Early Identification of Cerebral Infarction , 2020, Cerebrovascular Diseases.

[27]  C. Gerloff,et al.  Negative fluid‐attenuated inversion recovery imaging identifies acute ischemic stroke at 3 hours or less , 2009, Annals of neurology.