VICE: Visual Identification and Correction of Neural Circuit Errors
This work addresses a domain-specific bottleneck in neuroscience by improving the efficiency of proofreading neural circuit reconstructions, though it is incremental as it builds on existing segmentation methods.
The paper tackles the problem of time-consuming manual proofreading of neuron segmentation errors in electron microscopy data by introducing an analytics framework that automates error detection and uses interactive 3D visualizations to streamline the process, resulting in users finding it more efficient for proofreading and understanding connectivity graphs.
A connectivity graph of neurons at the resolution of single synapses provides scientists with a tool for understanding the nervous system in health and disease. Recent advances in automatic image segmentation and synapse prediction in electron microscopy (EM) datasets of the brain have made reconstructions of neurons possible at the nanometer scale. However, automatic segmentation sometimes struggles to segment large neurons correctly, requiring human effort to proofread its output. General proofreading involves inspecting large volumes to correct segmentation errors at the pixel level, a visually intensive and time-consuming process. This paper presents the design and implementation of an analytics framework that streamlines proofreading, focusing on connectivity-related errors. We accomplish this with automated likely-error detection and synapse clustering that drives the proofreading effort with highly interactive 3D visualizations. In particular, our strategy centers on proofreading the local circuit of a single cell to ensure a basic level of completeness. We demonstrate our framework's utility with a user study and report quantitative and subjective feedback from our users. Overall, users find the framework more efficient for proofreading, understanding evolving graphs, and sharing error correction strategies.