Dual-Energy CT Follow-Up After Stroke Thrombolysis Alters Assessment of Hemorrhagic Complications

Abstract

Background and Purpose: We aimed to determine whether dual-energy CT (DECT) follow-up can differentiate contrast staining (CS) from intracranial hemorrhage (ICH) in stroke patients treated with intravenous thrombolysis (IVT), who had undergone acute stroke imaging using CT angiography (CTA), and CT perfusion (CTP). Materials and Methods: Between November 2012 and January 2018, 168 patients at our comprehensive stroke center underwent DECT follow-up within 36 h after IVT and acute CTA with or without CTP but did not receive intra-arterial imaging or treatment. Two independent readers evaluated plain monochromatic CT (pCT) alone and compared this with a second reading of a combined DECT approach using pCT and water- and iodine-weighted images, establishing and grading the ICH diagnosis, per Heidelberg and Safe Implementation of Treatments in Stroke Monitoring Study (SITS-MOST) classifications. Results: On pCT alone within 36 h, 31/168 (18.5%) patients had findings diagnosed as ICH. Using combined DECT (cDECT) changed ICH diagnosis to "CS only" in 3/168 (1.8%) patients, constituting 3/31 (9.7%) of cases with initially pCT-diagnosed ICH. These three cases had pCT diagnoses of one SAH, one minor, and one more extensive petechial hemorrhage (hemorrhagic infarction types 1 and 2), respectively. pCT alone had a 100% sensitivity, 98% specificity, 90% positive predictive value (PPV), 100% negative predictive value (NPV), and 98% accuracy for any ICH, compared to the cDECT. Inter-reader agreement for ICH classification using pCT compared to DECT was weighted kappa 0.92 (95% CI 0.87-0.98) vs. 0.91 (0.85-0.95). Conclusion: Compared to pCT, DECT within 36 h after IV thrombolysis for acute ischemic stroke, changes the radiological diagnosis of post-treatment ICH to "CS only" in a small proportion of patients. Studies are warranted of whether the altered radiological reports have an impact on patient management, for example initiation timing of antithrombotic secondary prevention.

Keywords: acute ischemic stroke; computed tomography; intracerebral hemorrhage (ICH); intravenous thrombolysis; spectral computed tomography.

Figure 1

Flowchart of distribution of no ICH v. ICH: ^aContrast staining mimicking ICH.

Figure 2

Flowchart of the ICH findings. SICH, symptomatic intracranial hemorrhage. ^aContrast staining mimicking ICH. ^bSICH fulfilling both ECASS II and SITS-MOST criteria, both cases with PH2. ^cSICH per the ECASS II definition, with one case each of HI2, PH1, and PHr1. All SICH showed the same image on pCT or cDECT. The differences between different subcategories are non-significant with p > 0.25.

Figure 3

Case example. Male, 72 years old, with hypertension. Right-sided hemiparesis with NIHSS 24 points at stroke onset and a left-sided M1 occlusion and a (missed) very subtle infarction with ASPECT 3. Routine drip-and-ship from a primary stroke center following IVT initiation to a thrombectomy center. IVT was stopped due to clinical worsening before arrival. The repeated stroke imaging there showed extensive manifest infarction (ASPECT 3) on the left side but also a hemorrhage within an infarct on the right side. Rejected for thrombectomy. (A) SECT 1 h 15 min after IVT initiation with signs of hemorrhage*. (B) pCT, (C) wDECT, and (D) iDECT, all at 10 h, on pCT alone judged to be a HI2 bleeding**; however, wDECT and iDECT showed iodine*** within an infarct, originating from an IV contrast injection for a CTA done immediately prior to initial IVT administration. Clinical workup showed a previously undiagnosed atrial fibrillation, with cardioembolism deemed to be the likely cause of stroke.