Background Acute stroke lesions become more hypodense on non-contrast CT as the ischemic injury matures. Lesions transition to established infarcts at which time recanalization treatment is thought to be futile, if not harmful. It is not possible to directly quantify the degree of injury progression, so eligibility for treatment is determined using temporal criteria. In this study we used an AI approach to quantify the hypoattenuation of acute stroke lesions at baseline and explored how this impacts clinical outcome following mechanical thrombectomy.

Methods Imaging was collected from a multicentric registry of consecutive large vessel occlusion (LVO) stroke patients who underwent mechanical thrombectomy. Baseline CT scans were processed using Brainomix 360 e-ASPECTS to automatically segment the ischemic core and Brainomix in-house software to quantify the magnitude of hypodensity. Lesion hypoattenuation was quantified using the mean voxel Net-Water-Uptake (NWU). Multivariate models were used to measure the association between NWU and clinical outcome (the 3-month modified Rankin scale - mRS)

Results Of 671 patients included in this study (Age: median 72, IQR 21; females 331), successful recanalization (mTICI 2b-3) was achieved for 560 patients. e-ASPECTS, age, NWU (p=0.001, t=3.32), and recanalization status were independent predictors of outcome. In patients without successful recanalization (mTICI 0–2a), NWU was not found to be an independent predictor of outcome (p=0.52).

Conclusion The results from this study suggest that hypodensity measured using NWU might allow to identify patients at risk of futile recanalization. The ability to determine treatment eligibility using information extracted from routine imaging would allow safe extension of treatment to patients with unclear onset time, and would account for differences in rates of infarct progression between patients.

• Download figure
• Open in new tab
• Download powerpoint

Abstract O-045 Figure 1

Probability of achieving a 90 days mRS of 0–6 as a function of NWU, in both recanalized (blue, mTICI 2b-3) and not recanalized patients (red, mTICI 0–2a)

Disclosures W. Brinjikji: None. D. Carone: 5; C; Brainomix ltd. A. Perry: 5; C; Brainomix ltd. A. Rai: 2; C; Stryker, Cerenovus. A. Al Halak: None. D. Kallmes: None. G. Harston: 5; C; Brainomix Ltd.