Consistent Recurrent Neural Networks for 3D Neuron Segmentation
This work addresses neuron segmentation in biomedical imaging, which is incremental as it builds on existing methods with consistency improvements.
The paper tackles the problem of 3D neuron segmentation by proposing a recurrent network that generates binary masks with spatio-temporal consistency, achieving state-of-the-art performance on the SNEMI3D challenge.
We present a recurrent network for the 3D reconstruction of neurons that sequentially generates binary masks for every object in an image with spatio-temporal consistency. Our network models consistency in two parts: (i) local, which allows exploring non-occluding and temporally-adjacent object relationships with bi-directional recurrence. (ii) non-local, which allows exploring long-range object relationships in the temporal domain with skip connections. Our proposed network is end-to-end trainable from an input image to a sequence of object masks, and, compared to methods relying on object boundaries, its output does not require post-processing. We evaluate our method on three benchmarks for neuron segmentation and achieved state-of-the-art performance on the SNEMI3D challenge.