Anke Wouters1,2,3,4, David Robben5,6,7, Soren Christensen8, Henk A Marquering9,10, Yvo B W E M Roos4, Robert J van Oostenbrugge11, Wim H van Zwam12, Diederik W J Dippel13, Charles B L M Majoie9, Wouter J Schonewille14, Aad van der Lugt15, Maarten Lansberg16, Gregory W Albers16, Paul Suetens5,6, Robin Lemmens1,2,3. 1. Department of Neurology, University Hospitals Leuven, Belgium (A.W., R.L.). 2. Department of Neurosciences, Experimental Neurology, KU Leuven - University of Leuven, Belgium (A.W., R.L.). 3. Center for Brain & Disease Research, Laboratory of Neurobiology, VIB, Leuven, Belgium (A.W., R.L.). 4. Department of Neurology, Academic Medical Center, the Netherlands (A.W., Y.B.W.E.M.R.). 5. Medical Imaging Research Center (MIRC), KU Leuven, Belgium (D.R., P.S.). 6. Medical Image Computing (MIC), ESAT-PSI, Department of Electrical Engineering, KU Leuven, Belgium (D.R., P.S.). 7. Icometrix, Leuven, Belgium (D.R.). 8. GrayNumber Analytics, Lomma, Sweden (S.C.). 9. Department of Radiology and Nuclear Medicine, Academic Medical Center, Amsterdam, the Netherlands (H.A.M., C.B.L.M.M.). 10. Department of Biomedical Engineering and Physics, Academic Medical Center, Amsterdam, the Netherlands (H.A.M.). 11. Department of Neurology, Maastricht University Medical Center and Cardiovascular Research Institute (CARIM), the Netherlands (R.J.v.O.). 12. Department of Radiology, Maastricht University Medical Center and Cardiovascular Research Institute (CARIM), the Netherlands (W.H.v.Z.). 13. Department of Neurology, Erasmus MC University Medical Center, Rotterdam, Netherlands (D.W.J.D.). 14. Department of Neurology, St. Antonius Hospital, Nieuwegein, and University Medical Center Utrecht (W.J.S.). 15. Department of Radiology and Nuclear Medicine, Erasmus MC University Medical Center, Rotterdam, the Netherlands (A.v.d.L.). 16. Stanford Stroke Center, Stanford University, CA (M.L., G.W.A.).
Abstract
BACKGROUND AND PURPOSE: Computed tomography perfusion imaging allows estimation of tissue status in patients with acute ischemic stroke. We aimed to improve prediction of the final infarct and individual infarct growth rates using a deep learning approach. METHODS: We trained a deep neural network to predict the final infarct volume in patients with acute stroke presenting with large vessel occlusions based on the native computed tomography perfusion images, time to reperfusion and reperfusion status in a derivation cohort (MR CLEAN trial [Multicenter Randomized Clinical Trial of Endovascular Treatment for Acute Ischemic Stroke in the Netherlands]). The model was internally validated in a 5-fold cross-validation and externally in an independent dataset (CRISP study [CT Perfusion to Predict Response to Recanalization in Ischemic Stroke Project]). We calculated the mean absolute difference between the predictions of the deep learning model and the final infarct volume versus the mean absolute difference between computed tomography perfusion imaging processing by RAPID software (iSchemaView, Menlo Park, CA) and the final infarct volume. Next, we determined infarct growth rates for every patient. RESULTS: We included 127 patients from the MR CLEAN (derivation) and 101 patients of the CRISP study (validation). The deep learning model improved final infarct volume prediction compared with the RAPID software in both the derivation, mean absolute difference 34.5 versus 52.4 mL, and validation cohort, 41.2 versus 52.4 mL (P<0.01). We obtained individual infarct growth rates enabling the estimation of final infarct volume based on time and grade of reperfusion. CONCLUSIONS: We validated a deep learning-based method which improved final infarct volume estimations compared with classic computed tomography perfusion imaging processing. In addition, the deep learning model predicted individual infarct growth rates which could enable the introduction of tissue clocks during the management of acute stroke.
BACKGROUND AND PURPOSE: Computed tomography perfusion imaging allows estimation of tissue status in patients with acute ischemic stroke. We aimed to improve prediction of the final infarct and individual infarct growth rates using a deep learning approach. METHODS: We trained a deep neural network to predict the final infarct volume in patients with acute stroke presenting with large vessel occlusions based on the native computed tomography perfusion images, time to reperfusion and reperfusion status in a derivation cohort (MR CLEAN trial [Multicenter Randomized Clinical Trial of Endovascular Treatment for Acute Ischemic Stroke in the Netherlands]). The model was internally validated in a 5-fold cross-validation and externally in an independent dataset (CRISP study [CT Perfusion to Predict Response to Recanalization in Ischemic Stroke Project]). We calculated the mean absolute difference between the predictions of the deep learning model and the final infarct volume versus the mean absolute difference between computed tomography perfusion imaging processing by RAPID software (iSchemaView, Menlo Park, CA) and the final infarct volume. Next, we determined infarct growth rates for every patient. RESULTS: We included 127 patients from the MR CLEAN (derivation) and 101 patients of the CRISP study (validation). The deep learning model improved final infarct volume prediction compared with the RAPID software in both the derivation, mean absolute difference 34.5 versus 52.4 mL, and validation cohort, 41.2 versus 52.4 mL (P<0.01). We obtained individual infarct growth rates enabling the estimation of final infarct volume based on time and grade of reperfusion. CONCLUSIONS: We validated a deep learning-based method which improved final infarct volume estimations compared with classic computed tomography perfusion imaging processing. In addition, the deep learning model predicted individual infarct growth rates which could enable the introduction of tissue clocks during the management of acute stroke.
Entities:
Keywords:
deep learning; infarction; ischemic stroke; perfusion imaging; reperfusion
Authors: Archana Purushotham; Bruce C V Campbell; Matus Straka; Michael Mlynash; Jean-Marc Olivot; Roland Bammer; Stephanie M Kemp; Gregory W Albers; Maarten G Lansberg Journal: Int J Stroke Date: 2013-06-27 Impact factor: 5.266
Authors: Amber Bucker; Anna M Boers; Joseph C J Bot; Olvert A Berkhemer; Hester F Lingsma; Albert J Yoo; Wim H van Zwam; Robert J van Oostenbrugge; Aad van der Lugt; Diederik W J Dippel; Yvo B W E M Roos; Charles B L M Majoie; Henk A Marquering Journal: Stroke Date: 2017-03-28 Impact factor: 7.914
Authors: Jeffrey L Saver; Mayank Goyal; Aad van der Lugt; Bijoy K Menon; Charles B L M Majoie; Diederik W Dippel; Bruce C Campbell; Raul G Nogueira; Andrew M Demchuk; Alejandro Tomasello; Pere Cardona; Thomas G Devlin; Donald F Frei; Richard du Mesnil de Rochemont; Olvert A Berkhemer; Tudor G Jovin; Adnan H Siddiqui; Wim H van Zwam; Stephen M Davis; Carlos Castaño; Biggya L Sapkota; Puck S Fransen; Carlos Molina; Robert J van Oostenbrugge; Ángel Chamorro; Hester Lingsma; Frank L Silver; Geoffrey A Donnan; Ashfaq Shuaib; Scott Brown; Bruce Stouch; Peter J Mitchell; Antoni Davalos; Yvo B W E M Roos; Michael D Hill Journal: JAMA Date: 2016-09-27 Impact factor: 56.272
Authors: Jean-Marc Olivot; Michael Mlynash; Vincent N Thijs; Stephanie Kemp; Maarten G Lansberg; Lawrence Wechsler; Roland Bammer; Michael P Marks; Gregory W Albers Journal: Stroke Date: 2008-12-24 Impact factor: 7.914
Authors: Anke Wouters; Søren Christensen; Matus Straka; Michael Mlynash; John Liggins; Roland Bammer; Vincent Thijs; Robin Lemmens; Gregory W Albers; Maarten G Lansberg Journal: Front Neurol Date: 2017-10-13 Impact factor: 4.003
Authors: Stefan Winzeck; Arsany Hakim; Richard McKinley; José A A D S R Pinto; Victor Alves; Carlos Silva; Maxim Pisov; Egor Krivov; Mikhail Belyaev; Miguel Monteiro; Arlindo Oliveira; Youngwon Choi; Myunghee Cho Paik; Yongchan Kwon; Hanbyul Lee; Beom Joon Kim; Joong-Ho Won; Mobarakol Islam; Hongliang Ren; David Robben; Paul Suetens; Enhao Gong; Yilin Niu; Junshen Xu; John M Pauly; Christian Lucas; Mattias P Heinrich; Luis C Rivera; Laura S Castillo; Laura A Daza; Andrew L Beers; Pablo Arbelaezs; Oskar Maier; Ken Chang; James M Brown; Jayashree Kalpathy-Cramer; Greg Zaharchuk; Roland Wiest; Mauricio Reyes Journal: Front Neurol Date: 2018-09-13 Impact factor: 4.003