FISBe: A real-world benchmark dataset for instance segmentation of long-range thin filamentous structures
This addresses a gap for neuroscience and machine learning researchers by enabling benchmarking on real data, though it is incremental as it focuses on dataset creation rather than new methods.
The authors tackled the lack of real-world datasets for instance segmentation of long-range thin filamentous structures by releasing the FlyLight Instance Segmentation Benchmark (FISBe), a publicly available multi-neuron light microscopy dataset with pixel-wise annotations, and provided baselines to advance methodology for capturing long-range dependencies.
Instance segmentation of neurons in volumetric light microscopy images of nervous systems enables groundbreaking research in neuroscience by facilitating joint functional and morphological analyses of neural circuits at cellular resolution. Yet said multi-neuron light microscopy data exhibits extremely challenging properties for the task of instance segmentation: Individual neurons have long-ranging, thin filamentous and widely branching morphologies, multiple neurons are tightly inter-weaved, and partial volume effects, uneven illumination and noise inherent to light microscopy severely impede local disentangling as well as long-range tracing of individual neurons. These properties reflect a current key challenge in machine learning research, namely to effectively capture long-range dependencies in the data. While respective methodological research is buzzing, to date methods are typically benchmarked on synthetic datasets. To address this gap, we release the FlyLight Instance Segmentation Benchmark (FISBe) dataset, the first publicly available multi-neuron light microscopy dataset with pixel-wise annotations. In addition, we define a set of instance segmentation metrics for benchmarking that we designed to be meaningful with regard to downstream analyses. Lastly, we provide three baselines to kick off a competition that we envision to both advance the field of machine learning regarding methodology for capturing long-range data dependencies, and facilitate scientific discovery in basic neuroscience.