Multi-input segmentation of damaged brain in acute ischemic stroke patients using slow fusion with skip connection
This provides a fast, automatic tool to aid treatment decisions for stroke patients, but it is incremental as it builds on existing neural network methods for medical image segmentation.
The paper tackles the problem of automatically segmenting ischemic regions (core and penumbra) in acute ischemic stroke patients using parametric maps from computed tomography perfusion images, achieving Dice coefficients of 0.81 for penumbra and 0.52 for core on a test set.
Time is a fundamental factor during stroke treatments. A fast, automatic approach that segments the ischemic regions helps treatment decisions. In clinical use today, a set of color-coded parametric maps generated from computed tomography perfusion (CTP) images are investigated manually to decide a treatment plan. We propose an automatic method based on a neural network using a set of parametric maps to segment the two ischemic regions (core and penumbra) in patients affected by acute ischemic stroke. Our model is based on a convolution-deconvolution bottleneck structure with multi-input and slow fusion. A loss function based on the focal Tversky index addresses the data imbalance issue. The proposed architecture demonstrates effective performance and results comparable to the ground truth annotated by neuroradiologists. A Dice coefficient of 0.81 for penumbra and 0.52 for core over the large vessel occlusion test set is achieved. The full implementation is available at: https://git.io/JtFGb.