SSHMT: Semi-supervised Hierarchical Merge Tree for Electron Microscopy Image Segmentation
This work addresses the costly data annotation problem for researchers in biomedical imaging, offering an incremental improvement over existing region-based methods.
The paper tackles the problem of reducing the need for extensive ground truth data in electron microscopy image segmentation by proposing a semi-supervised approach that uses only 3% to 7% of labeled data, achieving performance close to state-of-the-art supervised methods with full data and significantly outperforming supervised methods with the same limited subset.
Region-based methods have proven necessary for improving segmentation accuracy of neuronal structures in electron microscopy (EM) images. Most region-based segmentation methods use a scoring function to determine region merging. Such functions are usually learned with supervised algorithms that demand considerable ground truth data, which are costly to collect. We propose a semi-supervised approach that reduces this demand. Based on a merge tree structure, we develop a differentiable unsupervised loss term that enforces consistent predictions from the learned function. We then propose a Bayesian model that combines the supervised and the unsupervised information for probabilistic learning. The experimental results on three EM data sets demonstrate that by using a subset of only 3% to 7% of the entire ground truth data, our approach consistently performs close to the state-of-the-art supervised method with the full labeled data set, and significantly outperforms the supervised method with the same labeled subset.