Ability of Radiomics Versus Humans in Predicting First-Pass Effect After Endovascular Treatment in the ESCAPE-NA1 Trial

. 2023 May ; 3 (3) : e000525. [epub] 20220920

Status PubMed-not-MEDLINE Jazyk angličtina Země Spojené státy americké Médium electronic-ecollection

Typ dokumentu časopisecké články

Perzistentní odkaz   https://www.medvik.cz/link/pmid41584964

BACKGROUND: First-pass effect (FPE), that is, achieving reperfusion with a single thrombectomy device pass, is associated with better clinical outcomes in patients with acute stroke. FPE is therefore increasingly used as a marker of device and procedural efficacy. We aimed to evaluate the ability of thrombus-based radiomics models to predict FPE in patients undergoing endovascular thrombectomy and compare performance with experts and nonradiomics thrombus characteristics. METHODS: Patients with thin-slice noncontrast computed tomography and computed tomography angiography from the ESCAPE-NA1 (Efficacy and Safety of Nerinetide for the Treatment of Acute Ischemic Stroke) trial were included. Thrombi were manually segmented on all images. Data were randomly split into a derivation set that included a training and a validation subset and an independent test set. Radiomics features were extracted from the derivation set. The machine learning models were compared with 3 expert stroke physicians in predicting FPE in the test set using area under the receiver operating characteristic curves. RESULTS: Thin-slice images of 554 patients were divided into a derivation set (training [n=388] and validation [n=55]) and a test set (n=111). A radiomics model using the combination of noncontrast computed tomography, computed tomography angiography, and noncontrast computed tomography-computed tomography angiography difference achieved the highest performance (area under the curve, 0.74 [95% CI, 0.64-0.84]) for prediction of FPE. This was higher than the mean area under the curve of the 3 experts (0.62 [95% CI, 0.53-0.71], P=0.01 for difference in area under the curves). The radiomics model also performed better than nonradiomics-based thrombus features such as volume and permeability measurements in predicting FPE (P<0.05). Addition of device type did not improve the performance of the chosen radiomics model in predicting FPE. CONCLUSION: A radiomics-based machine learning model of thrombus characteristics from noncontrast computed tomography and computed tomography angiography performs better than experts and traditional nonradiomics imaging features in predicting FPE in patients with acute stroke treated with endovascular thrombectomy.

Zobrazit více v PubMed

Goyal M, Menon BK, van Zwam WH, Dippel DW, Mitchell PJ, Demchuk AM, Dávalos A, Majoie CB, van der Lugt A, de Miquel MA, et al. Endovascular thrombectomy after large‐vessel ischaemic stroke: a meta‐analysis of individual patient data from five randomised trials. Lancet. 2016;387:1723‐1731. PubMed

Alawieh A, Vargas J, Fargen KM, Langley EF, Starke RM, De Leacy R, Chatterjee R, Rai A, Dumont T, Kan P, et al. Impact of procedure time on outcomes of thrombectomy for stroke. J Am Coll Cardiol. 2019;73:879‐890. PubMed

Nikoubashman O, Dekeyzer S, Riabikin A, Keulers A, Reich A, Mpotsaris A, Wiesmann M. True first‐pass effect. Stroke. 2019;50:2140‐2146. PubMed

Zaidat OO, Castonguay AC, Linfante I, Gupta R, Martin CO, Holloway WE, Mueller‐Kronast N, English JD, Dabus G, Malisch TW, et al. First pass effect: a new measure for stroke thrombectomy devices. Stroke. 2018;49:660‐666. PubMed

Bai X, Zhang X, Wang J, Zhang Y, Dmytriw AA, Wang T, Xu R, Ma Y, Li L, Feng Y, et al. Factors influencing recanalization after mechanical thrombectomy with first‐pass effect for acute ischemic stroke: a systematic review and meta‐analysis. Front Neurol. 2021;12:628523. PubMed PMC

Menon BK, Al‐Ajlan FS, Najm M, Puig J, Castellanos M, Dowlatshahi D, Calleja A, Sohn SI, Ahn SH, Poppe A, et al. Association of clinical, imaging, and thrombus characteristics with recanalization of visible intracranial occlusion in patients with acute ischemic stroke. JAMA. 2018;320:1017‐1026. PubMed PMC

Zaidat OO, Mueller‐Kronast NH, Hassan AE, Haussen DC, Jadhav AP, Froehler MT, Jahan R, Ali Aziz‐Sultan M, Klucznik RP, Saver JL, et al. Impact of balloon guide catheter use on clinical and angiographic outcomes in the STRATIS stroke thrombectomy registry. Stroke. 2019;50:697‐704. PubMed

den Hartog SJ, Zaidat O, Roozenbeek B, van Es A, Bruggeman AAE, Emmer BJ, Majoie CBLM, van Zwam WH, van den Wijngaard IR, van Doormaal PJ, et al. Effect of first‐pass reperfusion on outcome after endovascular treatment for ischemic stroke. J Am Heart Assoc. 2021;10:e019988. PubMed PMC

Jadhav AP, Desai SM, Budzik RF, Gupta R, Baxter B, English JD, Bartolini BM, Krajina A, Haussen DC, Nogueira RG, et al. First pass effect in patients with large vessel occlusion strokes undergoing neurothrombectomy: insights from the Trevo Retriever Registry. J Neurointerv Surg. 2021;13:619‐622. PubMed

Gillies RJ, Kinahan PE, Hricak H. Radiomics: images are more than pictures, they are data. Radiology. 2016;278:563‐577. PubMed PMC

Hofmeister J, Bernava G, Rosi A, Vargas MI, Carrera E, Montet X, Burgermeister S, Poletti PA, Platon A, Lovblad KO, et al. Clot‐based radiomics predict a mechanical thrombectomy strategy for successful recanalization in acute ischemic stroke. Stroke. 2020;51:2488‐2494. PubMed PMC

Qiu W, Kuang H, Nair J, Assis Z, Najm M, McDougall C, McDougall B, Chung K, Wilson AT, Goyal M, et al. Radiomics‐based intracranial thrombus features on CT and CTA predict recanalization with intravenous alteplase in patients with acute ischemic stroke. AJNR Am J Neuroradiol. 2019;40:39‐44. PubMed PMC

Hill MD, Goyal M, Menon BK, Nogueira RG, McTaggart RA, Demchuk AM, Poppe AY, Buck BH, Field TS, Dowlatshahi D, et al. Efficacy and safety of nerinetide for the treatment of acute ischaemic stroke (ESCAPE‐NA1): a multicentre, double‐blind, randomised controlled trial. Lancet. 2020;395:878‐887. PubMed

Beare R, Lowekamp B, Yaniv Z. Image segmentation, registration and characterization in R with SimpleITK. J Stat Softw. 2018;86:8. PubMed PMC

Fedorov A, Beichel R, Kalpathy‐Cramer J, Finet J, Fillion‐Robin JC, Pujol S, Bauer C, Jennings D, Fennessy F, Sonka M, et al. 3D slicer as an image computing platform for the quantitative imaging network. Magn Reson Imaging. 2012;30:1323‐1341. PubMed PMC

Yushkevich PA, Piven J, Hazlett HC, Smith RG, Ho S, Gee JC, Gerig G. User‐guided 3d active contour segmentation of anatomical structures: significantly improved efficiency and reliability. Neuroimage. 2006;31:1116‐1128. PubMed

Granitto PM, Furlanello C, Biasioli F, Gasperi F. Recursive feature elimination with random forest for PTR‐MS analysis of agroindustrial products. Chemom Intell Lab Syst. 2006;83:83‐90.

Dutra BG, Tolhuisen ML, Alves H, Treurniet KM, Kappelhof M, Yoo AJ, Jansen IGH, Dippel DWJ, van Zwam WH, van Oostenbrugge RJ, et al. Thrombus imaging characteristics and outcomes in acute ischemic stroke patients undergoing endovascular treatment. Stroke. 2019;50:2057‐2064. PubMed

Waqas M, Li W, Patel TR, Chin F, Tutino VM, Dossani RH, Ren Z, Guerrero WR, Borlongan CV, Pressman E, et al. Clot imaging characteristics predict first pass effect of aspiration‐first approach to thrombectomy. Interv Neuroradiol. 2021;28:152‐159. PubMed PMC

Lambin P, Leijenaar RTH, Deist TM, Peerlings J, de Jong EEC, van Timmeren J, Sanduleanu S, Larue RTHM, Even AJG, Jochems A, et al. Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol. 2017;14:749‐762. PubMed

DeLong ER, DeLong DM, Clarke‐Pearson DL. Comparing the areas under two or more correlated receiver operating characteristic curves: a nonparametric approach. Biometrics. 1988;44:837‐845. PubMed

Youden WJ. Index for rating diagnostic tests. Cancer. 1950;3:32‐35. PubMed

Zaidat OO, Yoo AJ, Khatri P, Tomsick TA, von Kummer R, Saver JL, Marks MP, Prabhakaran S, Kallmes DF, Fitzsimmons BF, et al. Recommendations on angiographic revascularization grading standards for acute ischemic stroke: a consensus statement. Stroke. 2013;44:2650‐2663. PubMed PMC

LeCouffe NE, Kappelhof M, Treurniet KM, Rinkel LA, Bruggeman AE, Berkhemer OA, Wolff L, van Voorst H, Tolhuisen ML, Dippel DWJ, et al. A randomized trial of intravenous alteplase before endovascular treatment for stroke. N Engl J Med. 2021;385:1833‐1844. PubMed

Mokin M, Primiani CT, Castonguay AC, Nogueira RG, Haussen DC, English JD, Satti SR, Chen J, Farid H, Borders C, et al. First pass effect in patients treated with the Trevo stent‐retriever: a track registry study analysis. Front Neurol. 2020;11:83. PubMed PMC

Yoo AJ, Soomro J, Andersson T, Saver JL, Ribo M, Bozorgchami H, Dabus G, Liebeskind DS, Jadhav A, Mattle H, et al. Benchmarking the extent and speed of reperfusion: first pass TICI 2c‐3 is a preferred endovascular reperfusion endpoint. Front Neurol. 2021;12:669934. PubMed PMC

Sarioglu O, Sarioglu FC, Capar AE, Sokmez DF, Mete BD, Belet U. Clot‐based radiomics features predict first pass effect in acute ischemic stroke. Interv Neuroradiol. 2022;28:160‐168. PubMed PMC

Shamy MC, Pugliese M, Meisel K, Rodriguez R, Kim AS, Stahnisch FW, Smith EE. How patient demographics, imaging, and beliefs influence tissue‐type plasminogen activator use: a survey of north American neurologists. Stroke. 2016;47:2051‐2057. PubMed

Srivatsa S, Duan Y, Sheppard JP, Pahwa S, Pace J, Zhou X, Bambakidis NC. Cerebral vessel anatomy as a predictor of first‐pass effect in mechanical thrombectomy for emergent large‐vessel occlusion. J Neurosurg. 2020:1‐9. PubMed

Ducroux C, Piotin M, Gory B, Labreuche J, Blanc R, Ben Maacha M, Lapergue B, Fahed R, ASTER Trial investigators . First pass effect with contact aspiration and stent retrievers in the Aspiration versus Stent Retriever (ASTER) trial. J Neurointerv Surg. 2020;12:386‐391. PubMed PMC

Najít záznam

Citační ukazatele

Pouze přihlášení uživatelé

Možnosti archivace

Nahrávání dat ...