SAHVER: Subarachnoid Hemorrhage Volumetric Expediting Resolution

Introduction: Subarachnoid Hemorrhage Volumetric Artificial Intelligence (SAHVAI) is a novel model that segments and quantifies Subarachnoid Hemorrhage Volume (SAHV) on non-contrast CT (NCCT) scans and generates a 3D brain volumetric map called SAHVAI-3D. It is enhanced into SAHVAI-4D when measured over time. Precise measurement of SAHV is critical to future discoveryies. For example, IRRAflow is a FDA-approved ventricular irrigation and drainage system that can expedite removal of SAH blood products. Objective: Utilize SAHVAI model to compare and quantify the course of SAHV resolution over time and generate SAHVAI-3D brain maps to help visualize significant SAHV resolution patterns and predict vasospasm. Methods: We applied SAHVAI to SAH cases with mFS(3-4) using the NCCT scans among three groups. Group A included 1 SAH patient treated with the IRRAflow system. Group B included one SAH patient presented GCS 15 two days after ictus with no requirement for EVD. Group C included 10 patients who underwent regular EVD placement per standard of care. Results: Group A showed expedited resolution of SAHV (1.87mL/day) with an mRS of 0 on discharge and minimal vasospasm (Figures 1, 2). Group B showed 16mL increase in SAHV suspected for aneurysmal rebleeding days (5-9), and the patient later died (mRS of 6) (Figure 3). Group C showed reduction of SAHV of ~ 0.5ml /day (Figure 4). Further, the resultant 3D brain maps revealed that areas with the highest density of blood concentration were correlated with the severity and location of the vasospasm in all groups (Table 1). Conclusion: SAHVAI, SAHVAI-3D and SAHVAI-4D are novel methods that reliably quantifies SAHV blood volume and changes over time including SAH blood resolution or rebleeding events. SAHVER is a model that shows how interventions such as IRRAflow can expedite SAHV resolution compared to passive EVD and non-CSF drainage groups.