NIS3D: ACompletely Annotated Benchmark for Dense 3DNuclei Image Segmentation

The5 existing nuclei segmentation benchmarks either worked on 2D only or annotated6 a small number of 3D cells, perhaps due to the high cost of 3D annotation for7 large-scale data. To fulfill the critical need, we constructed NIS3D, a 3D, high8 cell density, large-volume, and completely annotated Nuclei Image Segmentation9 benchmark, assisted by our newly designed semi-automatic annotation software.10 NIS3D provides more than 22,000 cells across multiple most-used species in this11 area. Each cell is labeled by three independent annotators, so we can measure the12 variability of each annotation. A confidence score is computed for each cell, allow-13 ing more nuanced testing and performance comparison. A comprehensive review14 on the methods of segmenting 3D dense nuclei was conducted. The benchmark was15 used to evaluate the performance of several selected state-of-the-art segmentation16 algorithms. The best of current methods is still far away from human-level accuracy,17 corroborating the necessity of generating such a benchmark. The testing results18 also demonstrated the strength and weakness of each method and pointed out the19 directions of further methodological development.