BACKGROUND: Endovascular mechanical thrombectomy (EMT) is an effective method to treat acute ischemic stroke (AIS) patients due to large vessel occlusion (LVO). However, stratifying AIS patients who can and cannot benefit from EMT remains a clinical challenge. OBJECTIVE: To develop a new quantitative image marker computed from pre-intervention computed tomography perfusion (CTP) images and evaluate its feasibility to predict clinical outcome among AIS patients undergoing EMT after diagnosis of LVO. METHODS: A retrospective dataset of 31 AIS patients with pre-intervention CTP images is assembled. A computer-aided detection (CAD) scheme is developed to pre-process CTP images of different scanning series for each study case, perform image segmentation, quantify contrast-enhanced blood volumes in bilateral cerebral hemispheres, and compute features related to asymmetrical cerebral blood flow patterns based on the cumulative cerebral blood flow curves of two hemispheres. Next, image markers based on a single optimal feature and machine learning (ML) models fused with multi-features are developed and tested to classify AIS cases into two classes of good and poor prognosis based on the Modified Rankin Scale. Performance of image markers is evaluated using the area under the ROC curve (AUC) and accuracy computed from the confusion matrix. RESULTS: The ML model using the neuroimaging features computed from the slopes of the subtracted cumulative blood flow curves between two cerebral hemispheres yields classification performance of AUC = 0.878±0.077 with an overall accuracy of 90.3%. CONCLUSIONS: This study demonstrates feasibility of developing a new quantitative imaging method and marker to predict AIS patients' prognosis in the hyperacute stage, which can help clinicians optimally treat and manage AIS patients.
BACKGROUND: Endovascular mechanical thrombectomy (EMT) is an effective method to treat acute ischemic stroke (AIS) patients due to large vessel occlusion (LVO). However, stratifying AIS patients who can and cannot benefit from EMT remains a clinical challenge. OBJECTIVE: To develop a new quantitative image marker computed from pre-intervention computed tomography perfusion (CTP) images and evaluate its feasibility to predict clinical outcome among AIS patients undergoing EMT after diagnosis of LVO. METHODS: A retrospective dataset of 31 AIS patients with pre-intervention CTP images is assembled. A computer-aided detection (CAD) scheme is developed to pre-process CTP images of different scanning series for each study case, perform image segmentation, quantify contrast-enhanced blood volumes in bilateral cerebral hemispheres, and compute features related to asymmetrical cerebral blood flow patterns based on the cumulative cerebral blood flow curves of two hemispheres. Next, image markers based on a single optimal feature and machine learning (ML) models fused with multi-features are developed and tested to classify AIS cases into two classes of good and poor prognosis based on the Modified Rankin Scale. Performance of image markers is evaluated using the area under the ROC curve (AUC) and accuracy computed from the confusion matrix. RESULTS: The ML model using the neuroimaging features computed from the slopes of the subtracted cumulative blood flow curves between two cerebral hemispheres yields classification performance of AUC = 0.878±0.077 with an overall accuracy of 90.3%. CONCLUSIONS: This study demonstrates feasibility of developing a new quantitative imaging method and marker to predict AIS patients' prognosis in the hyperacute stage, which can help clinicians optimally treat and manage AIS patients.
Entities:
Keywords:
Acute ischemic stroke (AIS); computer-aided detection and diagnosis (CAD); prediction of AIS prognosis; quantitative image markers
Authors: Harold P Adams; Robert J Adams; Thomas Brott; Gregory J del Zoppo; Anthony Furlan; Larry B Goldstein; Robert L Grubb; Randall Higashida; Chelsea Kidwell; Thomas G Kwiatkowski; John R Marler; George J Hademenos Journal: Stroke Date: 2003-04 Impact factor: 7.914
Authors: Bappaditya Ray; Stephen R Ross; Gopichand Danala; Faranak Aghaei; Claire Delpirou Nouh; Lance Ford; Kimberly M Hollabaugh; Brittany N Karfonta; Joshua A Santucci; Benjamin O Cornwell; Bradley N Bohnstedt; Bin Zheng; George L Dale; Calin I Prodan Journal: J Crit Care Date: 2019-03-14 Impact factor: 3.425
Authors: Kyle P O'Connor; Mausaminben Y Hathidara; Gopichandh Danala; Chao Xu; Tressie M McCoy; Evgeny V Sidorov; Bin Zheng; Bradley N Bohnstedt; Bappaditya Ray Journal: World Neurosurg Date: 2019-11-28 Impact factor: 2.104
Authors: William A Copen; Livia T Morais; Ona Wu; Lee H Schwamm; Pamela W Schaefer; R Gilberto González; Albert J Yoo Journal: PLoS One Date: 2015-07-20 Impact factor: 3.240