BACKGROUND AND PURPOSE Intra-arterial recanalization postprocedural imaging in stroke patients can result in diagnostic complications due to hyperdensities on noncontrast computed tomography (CT), which may represent either contrast extravasation or intracranial hemorrhage. If these lesions are hemorrhage, then they are risk factors becoming symptomatic, which, if not distinguished, can alter clinical management. We investigate the effects of iodinated contrast on postprocedural magnetic resonance imaging (MRI) and prevalence of equivocal imaging interpretations of postprocedural extravasated contrast versus hemorrhage while identifying protocol pitfalls. METHODS We identified 10 patients diagnosed with ischemic stroke who underwent intra-arterial recanalization in a 5-year period. These patients demonstrated a hyperdensity on a postprocedural CT within 24 hours, underwent an MRI within 48 hours, and an additional confirmatory noncontrast CT at least 72 hours postprocedure. RESULTS Postprocedural MRI in all 10 stroke patients demonstrated T1 - and T2-relaxation time changes due to residual iodine contrast agents. This lead to false positive postprocedural hemorrhage MRI interpretations in 2/10 patients, 3/10 false negative interpretations of contrast extravasation, and 5/10 equivocal interpretations suggesting extravasation or hemorrhage. Of these five cases, two were performed with gadolinium. CONCLUSION MRI done within 48 hours postprocedure can lead to false positive hemorrhage or false negative contrast extravasation interpretations in stroke patients possibly due to effects from the administered angiographic contrast. Additionally, MRI should be done both after 72 hours for confirmation and without gadolinium contrast as the effects of the gadolinium contrast and residual angiographic contrast could lead to misdiagnosis.

No abstract

No abstract

At present, clinicians are expected to manage a large volume of complex clinical, laboratory, and imaging data, necessitating sophisticated analytic approaches. Machine learning-based models can use this vast amount of data to create forecasting models. We aimed to predict short- and medium-term functional outcomes in acute ischemic stroke (AIS) patients with proximal middle cerebral artery (MCA) occlusions using machine learning models with clinical, laboratory, and quantitative imaging data as inputs. Included were consecutive AIS patients with MCA M1 and proximal M2 occlusions. The XGBoost, LightGBM, CatBoost, and Random Forest were used to predict the outcome. Minimum redundancy maximum relevancy was used for selecting features. The primary outcomes were the National Institutes of Health Stroke Scale (NIHSS) shift and the modified Rankin Score (mRS) at 90 days. The algorithm with the highest area under the receiver operating characteristic curve (AUROC) for predicting the favorable and unfavorable outcome groups at 90 days was LightGBM. Random Forest had the highest AUROC when predicting the favorable and unfavorable groups based on the NIHSS shift. Using clinical, laboratory, and imaging parameters in conjunction with machine learning, we accurately predicted the functional outcome of AIS patients with proximal MCA occlusions.