An efficient CNN-BiLSTM model for multi-class intracranial hemorrhage classification

Abstract

Intracranial hemorrhage (ICH) refers to a type of bleeding that occurs within the skull. ICH may be

caused by a wide range of pathology, including, trauma, hypertension, cerebral amyloid angiopa- thy, and cerebral aneurysms. Different subtypes of ICH exist based on their location in the brain,

including epidural hemorrhage (EDH), subdural hemorrhage (SDH), subarachnoid hemorrhage

(SAH), intraventricular hemorrhage (IVH), and intraparenchymal hemorrhage (IPH). Prompt de- tection and management of ICH are crucial as it is a life-threatening medical emergency with high

morbidity and mortality rates. Despite accounting for only 10-15% of all strokes, ICH is respon- sible for over 50% of stroke-related deaths. Therefore, the presence, type, and location of an ICH must be immediately diagnosed so that the patients can receive medical intervention. However, accurately identifying ICH in CT slices can be challenging due to the brain’s complex anatomy and the variability in hemorrhage appearance. [...]