Open AccessUse of quantitative angiographic methods with a data-driven model to evaluate reperfusion status (mTICI) during thrombectomy
Author(s) -
Mohammad Mahdi Shiraz Bhurwani,
Kenneth V. Snyder,
Muhammad Waqas,
Maxim Mokin,
Ryan A. Rava,
Alexander R. Podgorsak,
Felix Chin,
Jason M Davies,
Elad I. Levy,
Adnan H. Siddiqui,
Ciprian N. Ionita
Publication year - 2021
Publication title -
neuroradiology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.811
H-Index - 94
eISSN - 1432-1920
pISSN - 0028-3940
DOI - 10.1007/s00234-020-02598-3
Subject(s) - medicine , digital subtraction angiography , occlusion , neuroradiology , thrombolysis , receiver operating characteristic , stroke (engine) , cerebral infarction , angiography , infarction , radiology , cardiology , neurology , ischemia , myocardial infarction , mechanical engineering , psychiatry , engineering
Intra-procedural assessment of reperfusion during mechanical thrombectomy (MT) for emergent large vessel occlusion (LVO) stroke is traditionally based on subjective evaluation of digital subtraction angiography (DSA). However, semi-quantitative diagnostic tools which encode hemodynamic properties in DSAs, such as angiographic parametric imaging (API), exist and may be used for evaluation of reperfusion during MT. The objective of this study was to use data-driven approaches, such as convolutional neural networks (CNNs) with API maps, to automatically assess reperfusion in the neuro-vasculature during MT procedures based on the modified thrombolysis in cerebral infarction (mTICI) scale.