W Qiu1, H Kuang1, J Nair1,2, Z Assis1, M Najm1, C McDougall1, B McDougall1, K Chung3, A T Wilson1, M Goyal1,4,5, M D Hill1,4,6,5, A M Demchuk1,4,5, B K Menon7,4,6,5. 1. From the Departments of Clinical Neurosciences (W.Q., H.K., J.N., Z.A. M.N., C.M., A.T.W., B.M., M.G., M.D.H., A.M.D., B.K.M.). 2. Department of Radiology (J.N.), McMaster University, Hamilton, Ontario, Canada. 3. Calgary Stroke Program, Mechanical and Manufacturing Engineering (K.C.). 4. Radiology (M.D.H., A.M.D., M.G., B.K.M.). 5. Hotchkiss Brain Institute (M.D.H., A.M.D., M.G., B.K.M.), Calgary, Alberta, Canada. 6. Community Health Sciences (M.D.H., B.K.M.), University of Calgary, Calgary, Alberta, Canada. 7. From the Departments of Clinical Neurosciences (W.Q., H.K., J.N., Z.A. M.N., C.M., A.T.W., B.M., M.G., M.D.H., A.M.D., B.K.M.) docbijoymenon@gmail.com.
Abstract
BACKGROUND AND PURPOSE: Thrombus characteristics identified on non-contrast CT (NCCT) are potentially associated with recanalization with intravenous (IV) alteplase in patients with acute ischemic stroke (AIS). Our aim was to determine the best radiomics-based features of thrombus on NCCT and CT angiography associated with recanalization with IV alteplase in AIS patients and proximal intracranial thrombi. MATERIALS AND METHODS: With a nested case-control design, 67 patients with ICA/M1 MCA segment thrombus treated with IV alteplase were included in this analysis. Three hundred twenty-six radiomics features were extracted from each thrombus on both NCCT and CTA images. Linear discriminative analysis was applied to select features most strongly associated with early recanalization with IV alteplase. These features were then used to train a linear support vector machine classifier. Ten times 5-fold cross-validation was used to evaluate the accuracy of the trained classifier and the stability of the selected features. RESULTS: Receiver operating characteristic curves showed that thrombus radiomics features are predictive of early recanalization with IV alteplase. The combination of radiomics features from NCCT, CTA, and radiomics changes is best associated with early recanalization with IV alteplase (area under the curve = 0.85) and was significantly better than any single feature such as thrombus length (P < .001), volume (P < .001), and permeability as measured by mean attenuation increase (P < .001), maximum attenuation in CTA (P < .001), maximum attenuation increase (P < .001), and assessment of residual flow grade (P < .001). CONCLUSIONS: Thrombus radiomics features derived from NCCT and CTA are more predictive of recanalization with IV alteplase in patients with acute ischemic stroke with proximal occlusion than previously known thrombus imaging features such as length, volume, and permeability.
BACKGROUND AND PURPOSE:Thrombus characteristics identified on non-contrast CT (NCCT) are potentially associated with recanalization with intravenous (IV) alteplase in patients with acute ischemic stroke (AIS). Our aim was to determine the best radiomics-based features of thrombus on NCCT and CT angiography associated with recanalization with IV alteplase in AISpatients and proximal intracranial thrombi. MATERIALS AND METHODS: With a nested case-control design, 67 patients with ICA/M1 MCA segment thrombus treated with IV alteplase were included in this analysis. Three hundred twenty-six radiomics features were extracted from each thrombus on both NCCT and CTA images. Linear discriminative analysis was applied to select features most strongly associated with early recanalization with IV alteplase. These features were then used to train a linear support vector machine classifier. Ten times 5-fold cross-validation was used to evaluate the accuracy of the trained classifier and the stability of the selected features. RESULTS: Receiver operating characteristic curves showed that thrombus radiomics features are predictive of early recanalization with IV alteplase. The combination of radiomics features from NCCT, CTA, and radiomics changes is best associated with early recanalization with IV alteplase (area under the curve = 0.85) and was significantly better than any single feature such as thrombus length (P < .001), volume (P < .001), and permeability as measured by mean attenuation increase (P < .001), maximum attenuation in CTA (P < .001), maximum attenuation increase (P < .001), and assessment of residual flow grade (P < .001). CONCLUSIONS:Thrombus radiomics features derived from NCCT and CTA are more predictive of recanalization with IV alteplase in patients with acute ischemic stroke with proximal occlusion than previously known thrombus imaging features such as length, volume, and permeability.
Authors: Paul A Yushkevich; Joseph Piven; Heather Cody Hazlett; Rachel Gimpel Smith; Sean Ho; James C Gee; Guido Gerig Journal: Neuroimage Date: 2006-03-20 Impact factor: 6.556
Authors: Bijoy K Menon; Christopher D d'Esterre; Emmad M Qazi; Mohammed Almekhlafi; Leszek Hahn; Andrew M Demchuk; Mayank Goyal Journal: Radiology Date: 2015-01-29 Impact factor: 11.105
Authors: Christian H Riedel; Ulf Jensen; Axel Rohr; Marc Tietke; Karsten Alfke; Stephan Ulmer; Olav Jansen Journal: Stroke Date: 2010-07-01 Impact factor: 7.914
Authors: S M Mishra; J Dykeman; T T Sajobi; A Trivedi; M Almekhlafi; S I Sohn; S Bal; E Qazi; A Calleja; M Eesa; M Goyal; A M Demchuk; B K Menon Journal: AJNR Am J Neuroradiol Date: 2014-07-24 Impact factor: 3.825
Authors: Emilie M M Santos; Jan Willem Dankbaar; Kilian M Treurniet; Alexander D Horsch; Yvo B Roos; L Jaap Kappelle; Wiro J Niessen; Charles B Majoie; Birgitta Velthuis; Henk A Marquering Journal: Stroke Date: 2016-06-23 Impact factor: 7.914
Authors: Emilie M M Santos; Henk A Marquering; Mark D den Blanken; Olvert A Berkhemer; Anna M M Boers; Albert J Yoo; Ludo F Beenen; Kilian M Treurniet; Carrie Wismans; Kim van Noort; Hester F Lingsma; Diederik W J Dippel; Aad van der Lugt; Wim H van Zwam; Yvo B W E M Roos; Robert J van Oostenbrugge; Wiro J Niessen; Charles B Majoie Journal: Stroke Date: 2016-02-04 Impact factor: 7.914
Authors: Bijoy K Menon; Fahad S Al-Ajlan; Mohamed Najm; Josep Puig; Mar Castellanos; Dar Dowlatshahi; Ana Calleja; Sung-Il Sohn; Seong H Ahn; Alex Poppe; Robert Mikulik; Negar Asdaghi; Thalia S Field; Albert Jin; Talip Asil; Jean-Martin Boulanger; Eric E Smith; Shelagh B Coutts; Phil A Barber; Simerpreet Bal; Suresh Subramanian; Sachin Mishra; Anurag Trivedi; Sadanand Dey; Muneer Eesa; Tolulope Sajobi; Mayank Goyal; Michael D Hill; Andrew M Demchuk Journal: JAMA Date: 2018-09-11 Impact factor: 56.272
Authors: Hugo J W L Aerts; Emmanuel Rios Velazquez; Ralph T H Leijenaar; Chintan Parmar; Patrick Grossmann; Sara Carvalho; Sara Cavalho; Johan Bussink; René Monshouwer; Benjamin Haibe-Kains; Derek Rietveld; Frank Hoebers; Michelle M Rietbergen; C René Leemans; Andre Dekker; John Quackenbush; Robert J Gillies; Philippe Lambin Journal: Nat Commun Date: 2014-06-03 Impact factor: 14.919
Authors: Haoyue Zhang; Jennifer Polson; Kambiz Nael; Noriko Salamon; Bryan Yoo; William Speier; Corey Arnold Journal: IEEE EMBS Int Conf Biomed Health Inform Date: 2021-08-10
Authors: Nathan A Shlobin; Ammad A Baig; Muhammad Waqas; Tatsat R Patel; Rimal H Dossani; Megan Wilson; Justin M Cappuzzo; Adnan H Siddiqui; Vincent M Tutino; Elad I Levy Journal: World Neurosurg Date: 2021-12-08 Impact factor: 2.210
Authors: Maria Berndt; Fabian Mück; Christian Maegerlein; Silke Wunderlich; Claus Zimmer; Stefan Wirth; Sebastian Mönch; Johannes Kaesmacher; Benjamin Friedrich; Tobias Boeckh-Behrens Journal: Clin Neuroradiol Date: 2020-09-29 Impact factor: 3.649
Authors: T R Patel; S Fricano; M Waqas; M Tso; A A Dmytriw; M Mokin; J Kolega; J Tomaszewski; E I Levy; J M Davies; K V Snyder; A H Siddiqui; V M Tutino Journal: AJNR Am J Neuroradiol Date: 2020-11-26 Impact factor: 4.966