Large kernel refine fusion net for neuron membrane segmentation

2D neuron membrane segmentation for Electron Microscopy (EM) images is a key step in the 3D neuron reconstruction task. Compared with the semantic segmentation tasks for general images, the boundary segmentation in EM images is more challenging. In EM segmentation tasks, we need not only to segment the ambiguous membrane boundaries from bubble-like noise in the images, but also to remove shadow-like intracellular structure. In order to address these problems, we propose a Large Kernel Refine Fusion Net, an encoder-decoder architecture with fusion of features at multiple resolution levels. We incorporate large convolutional blocks to ensure the valid receptive fields for the feature maps are large enough, which can reduce information loss. Our model can also process the background together with the membrane boundary by using residual cascade pooling blocks. In addition, the postprocessing method in our work is simple but effective for a final refinement of the output probability map. Our method was evaluated and achieved competitive performances on two EM membrane segmentation tasks: ISBI2012 EM segmentation challenge and mouse piriform cortex segmentation task.