An automatic eHealth platform for cardiovascular and cerebrovascular disease detection

Cardiovascular and cerebrovascular disease has become the number-one killer to human life in the world We study and design an aided diagnosis eHealth platform for cerebrovascular and cerebrovascular disease detection with 3-tier architecture. The architecture has three layers: User Interface Layer, Business Logic Layer and Data Access Layer. We employ several key technologies for the platform We use a novel statistical cerebrovascular segmentation algorithm with particle swarm optimization to segment the cerebral vascular. We apply a multiscale enhancement and dynamic balloon tracking (MSCAR-DBT) method to segment the heart vascular. We propose Ball B-Spline curve to reconstruct the blood vessels. We use ray-casting volume rendering with compute unified device architecture (CUDA). Experiments on 108 patients´ computed tomography data or magnetic resonance imaging data stored in the system verify the feasibility and validity of each model we propose. We also test the platform on several hospitals in Beijing and receive a positive feedback from doctors.