The Project is to build a machine learning model under deployment to segment the CTscans of the brain for detection of various hemorrhage caused from strokes.
Intracranial hemorrhage refers to any bleeding within the intracranial vault, including the brain parenchyma and surrounding meningeal spaces. Intracerebral hemorrhage, or ICH, is a devastating disease. The overall incidence of spontaneous ICH worldwide is 24.6 per 100,000 person-years with approximately 40,000 to 67,000 cases per year. The 30-day mortality rate ranges from 35% to 52% with only 20% of survivors expected to have full functional recovery at 6 months. Approximately half of this mortality occurs within the first 24 hours. A recent population-based meta-analysis showed that risk factors for ICH include male sex, older age, and Asian ethnicity. ICH is twice as frequent in low-to-middle income countries compared to high-income countries.
The most important risk factors for ICH include hypertension (HTN) and cerebral amyloid angiopathy (CAA). HTN-related ICH is more likely to occur in deep structures, and the risk of ICH increases with increasing blood pressure values. CAA tends to occur in association with advanced age, and CAA-related ICH tends to occur in lobar regions. Other Factors include - Alchohol Intake, Cholestrol, Genetics, Anticoagulation and drug abuse.
We are going to detect following subtypes:-
- Install packages from requirments.txt
- Download the Repository
- Run python3 app.py
V1 -> This is potentially the first version for the detection algorithm can check here Notebook