IS-Net: Automatic Ischemic Stroke Lesion Segmentation on CT Images

Ischemic stroke is an acute cerebral vascular disease and makes up about 80% of all stroke cases. Noncontrast computed tomography (NCCT) is a widely applied imaging technique for ischemic stroke assessment. However, it is challenging to identify ischemic lesion on NCCT images due to its high variability in location, contrast, and geometry. In this work, we propose IS-Net, an encoder-decoder convolutional neural network for automatic ischemic stroke lesion segmentation on NCCT images. The proposed IS-Net takes a hierarchical network as backbone while the pyramid feature aggregation (PFA) module is designed to aggregate features from multistages of backbone, and reasonable feature fusion strategy is considered in PFA to enhance multilevel propagation. To fully mine the boundary cues, the edge constraint scheme is introduced by deep supervision which broadcasts low-level features to different modules. In addition, to overcome the limitation of fixed geometric structure of convolution for multirange dependency exploitation, a nonlocal parallel decoder is introduced with deformable convolution and self-attention. The proposed IS-Net is evaluated on manually labeled follow-up NCCT dataset composed of 1004 cases (totally 9020 images). The proposed IS-Net is compared with the state-of-the-art segmentation models and illustrates the highest score on segmentation criteria and sensitivity.