Yi-Qun Zhang1,2, Ao-Fei Liu1, Feng-Yuan Man3, Ying-Ying Zhang1, Chen Li1, Yun-E Liu1, Ji Zhou1, Ai-Ping Zhang1, Yang-Dong Zhang4, Jin Lv5,6, Wei-Jian Jiang7. 1. Department of Vascular Neurosurgery, New Era Stroke Care and Research Institute, The PLA Rocket Force Characteristic Medical Center, Beijing, 100088, China. 2. Department of Critical Care Medicine, New Era Stroke Care and Research Institute, The PLA Rocket Force Characteristic Medical Center, Beijing, 100088, China. 3. Department of Radiology, New Era Stroke Care and Research Institute, The PLA Rocket Force Characteristic Medical Center, Beijing, 100088, China. 4. Central Laboratory of Research Department, The PLA Rocket Force Characteristic Medical Center, Beijing, 100088, People's Republic of China. zhangyd262@163.com. 5. Department of Vascular Neurosurgery, New Era Stroke Care and Research Institute, The PLA Rocket Force Characteristic Medical Center, Beijing, 100088, China. lvjin6630@hotmail.com. 6. Central Laboratory of Research Department, The PLA Rocket Force Characteristic Medical Center, Beijing, 100088, People's Republic of China. lvjin6630@hotmail.com. 7. Department of Vascular Neurosurgery, New Era Stroke Care and Research Institute, The PLA Rocket Force Characteristic Medical Center, Beijing, 100088, China. cjr.jiangweijian@vip.163.com.
Abstract
PURPOSE: We aimed to investigate the ability of MRI radiomics features-based machine learning (ML) models to classify the time since stroke onset (TSS), which could aid in stroke assessment and treatment options. METHODS: This study involved 84 patients with acute ischemic stroke due to anterior circulation artery occlusion (51 in the training cohort and 33 in the independent test cohort). Region of infarct segmentation was manually outlined by 3D-slicer software. Image processing including registration, normalization and radiomics features calculation were done in R (version 3.6.1). A total of 4312 radiomic features from each image sequence were captured and used in six ML models to estimate stroke onset time for binary classification (≤ 4.5 h). Receiver-operating characteristic curve (ROC) and other parameters were calculated to evaluate the performance of the models in both training and test cohorts. RESULTS: Twelve radiomics and six clinic features were selected to construct the ML models for TSS classification. The deep learning model-based DWI/ADC radiomic features performed the best for binary TSS classification in the independent test cohort, with an AUC of 0.754, accuracy of 0.788, sensitivity of 0.952, specificity of 0.500, positive predictive value of 0.769, and negative predictive value of 0.857, respectively. Furthermore, adding clinical information did not improve the performance of the DWI/ADC-based deep learning model. The TSS prediction models can be visited at: http://123.57.65.199:3838/deeptss/ . CONCLUSIONS: A unique deep learning model based on DWI/ADC radiomic features was constructed for TSS classification, which could aid in decision making for thrombolysis in patients with unknown stroke onset.
PURPOSE: We aimed to investigate the ability of MRI radiomics features-based machine learning (ML) models to classify the time since stroke onset (TSS), which could aid in stroke assessment and treatment options. METHODS: This study involved 84 patients with acute ischemic stroke due to anterior circulation artery occlusion (51 in the training cohort and 33 in the independent test cohort). Region of infarct segmentation was manually outlined by 3D-slicer software. Image processing including registration, normalization and radiomics features calculation were done in R (version 3.6.1). A total of 4312 radiomic features from each image sequence were captured and used in six ML models to estimate stroke onset time for binary classification (≤ 4.5 h). Receiver-operating characteristic curve (ROC) and other parameters were calculated to evaluate the performance of the models in both training and test cohorts. RESULTS: Twelve radiomics and six clinic features were selected to construct the ML models for TSS classification. The deep learning model-based DWI/ADC radiomic features performed the best for binary TSS classification in the independent test cohort, with an AUC of 0.754, accuracy of 0.788, sensitivity of 0.952, specificity of 0.500, positive predictive value of 0.769, and negative predictive value of 0.857, respectively. Furthermore, adding clinical information did not improve the performance of the DWI/ADC-based deep learning model. The TSS prediction models can be visited at: http://123.57.65.199:3838/deeptss/ . CONCLUSIONS: A unique deep learning model based on DWI/ADC radiomic features was constructed for TSS classification, which could aid in decision making for thrombolysis in patients with unknown stroke onset.
Authors: Bruce C V Campbell; Henry Ma; Peter A Ringleb; Mark W Parsons; Leonid Churilov; Martin Bendszus; Christopher R Levi; Chung Hsu; Timothy J Kleinig; Marc Fatar; Didier Leys; Carlos Molina; Tissa Wijeratne; Sami Curtze; Helen M Dewey; P Alan Barber; Kenneth S Butcher; Deidre A De Silva; Christopher F Bladin; Nawaf Yassi; Johannes A R Pfaff; Gagan Sharma; Andrew Bivard; Patricia M Desmond; Stefan Schwab; Peter D Schellinger; Bernard Yan; Peter J Mitchell; Joaquín Serena; Danilo Toni; Vincent Thijs; Werner Hacke; Stephen M Davis; Geoffrey A Donnan Journal: Lancet Date: 2019-05-22 Impact factor: 79.321
Authors: Lauranne Scheldeman; Anke Wouters; Florent Boutitie; Patrick Dupont; Soren Christensen; Bastian Cheng; Martin Ebinger; Matthias Endres; Jochen B Fiebach; Christian Gerloff; Keith W Muir; Norbert Nighoghossian; Salvador Pedraza; Claus Z Simonsen; Vincent Thijs; Götz Thomalla; Robin Lemmens Journal: Ann Neurol Date: 2020-04-20 Impact factor: 10.422
Authors: Götz Thomalla; Jochen B Fiebach; Leif Østergaard; Salvador Pedraza; Vincent Thijs; Norbert Nighoghossian; Pascal Roy; Keith W Muir; Martin Ebinger; Bastian Cheng; Ivana Galinovic; Tae-Hee Cho; Josep Puig; Florent Boutitie; Claus Z Simonsen; Matthias Endres; Jens Fiehler; Christian Gerloff Journal: Int J Stroke Date: 2013-03-12 Impact factor: 5.266
Authors: Götz Thomalla; Philipp Rossbach; Michael Rosenkranz; Susanne Siemonsen; Anna Krützelmann; Jens Fiehler; Christian Gerloff Journal: Ann Neurol Date: 2009-06 Impact factor: 10.422