CORAL: A Benchmark for Structure-aware and Brain-wide Neuron Reconstruction in Light Microscopy
2026-08-31 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors address the challenge of automatically mapping neurons from microscope images, especially for large-scale brain data. They introduce CORAL, a new benchmark to test how well methods reconstruct neuron structures both in small image blocks and across the whole brain. They also create a new way to measure how correct the shape and connectivity of neurons are, not just how close the points match. To enable full brain mapping, they develop a system that links local reconstructions into a global one. Their work highlights that focusing on the structure of neurons is important and that better methods are still needed for complete brain-wide neuron mapping.
neuron reconstructionlight microscopycomputational neuroanatomyfMOST datasetstructure-aware evaluationtopological correctnessbrain-wide reconstructionneuron tracinglocal-to-global processbenchmark
Authors
Zekang Yang, Jiamin Li, Zhenghua Li, Jiaqi Fan, Zengcai Guo, Xiaolin Hu
Abstract
Automatic neuron reconstruction from light microscopy images is a central problem in computational neuroanatomy. While recent methods have achieved encouraging results on local image blocks, it remains unclear whether such progress translates to reconstruction that is both structurally accurate and scalable to the whole-brain scale. We present CORAL, the first benchmark for structure-aware evaluation of automatic neuron reconstruction from light microscopy images at both local and whole-brain scales. Built on a high-quality whole-brain fMOST dataset with carefully curated annotations, CORAL establishes two progressive tasks: block-level reconstruction, which evaluates reconstruction methods under limited spatial context, and brain-wide reconstruction, which assesses complete neuron reconstruction at the whole-brain scale. To account for topological correctness beyond geometric distance similarity, we introduce a structure-aware metric based on fiber prediction. To further achieve complete neuron reconstruction across the entire brain, we develop a brain-wide neuron tracing framework that extends arbitrary local reconstruction methods to the whole-brain scale through an iterative local-to-global process. Using this benchmark, we provide the first structure-aware comparison of mainstream methods for local neuron reconstruction and further evaluate their performance in brain-wide reconstruction. Our results underscore the importance of structure-aware evaluation and the need for more robust methods for complete neuron reconstruction.