Human Perception-based Evaluation Criterion for Ultra-high Resolution Cell Membrane Segmentation

Ruohua Shi, Wenyao Wang, Zhixuan Li, Liuyuan He, Kaiwen Sheng, Lei Ma, Kai Du, Tingting Jiang, Tiejun Huang

Keywords: Neuroscience, Connectomics, Human perception, EM dataset, Membrane segmentation, Evaluation criterion

Abstract: Computer vision technology is widely used in biological and medical data analysis and understanding. However, there are still two major bottlenecks in the field of cell membrane segmentation, which seriously hinder further research: lack of sufficient high-quality data and lack of suitable evaluation criteria. In order to solve these two problems, this paper first introduces an Ultra-high Resolution Image Segmentation dataset for the Cell membrane, called U-RISC, the largest annotated EM dataset for the Cell membrane with multiple iterative annotations and uncompressed high-resolution raw data. During the analysis process of the U-RISC, we found that the current popular segmentation evaluation criteria are inconsistent with human perception. This interesting phenomenon is confirmed by a subjective experiment involving twenty people. Furthermore, to resolve this inconsistency, we propose a Perceptual Hausdorff Distance (PHD) evaluation criterion to measure the quality of cell membrane segmentation results. Detailed performance comparison and discussion of classic segmentation methods along with two iterative manual annotation results under existing criteria and PHD is given.

One-sentence Summary: We established the largest annotated ultra-high resolution EM dataset for the cell membrane with multiple iterative annotations and propose a perceptual-based evaluation criterion to measure the quality of cell membrane segmentation results.

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics

Reviewed Version (pdf): https://openreview.net/references/pdf?id=E4aHFiF7o